{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "aa1b19bc-49e9-4aaf-b145-fb53fec1923c",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting huggingface_hub\n",
      "  Downloading huggingface_hub-0.23.4-py3-none-any.whl.metadata (12 kB)\n",
      "Requirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (3.13.1)\n",
      "Requirement already satisfied: fsspec>=2023.5.0 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (2023.12.2)\n",
      "Requirement already satisfied: packaging>=20.9 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (23.1)\n",
      "Requirement already satisfied: pyyaml>=5.1 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (6.0.1)\n",
      "Requirement already satisfied: requests in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (2.31.0)\n",
      "Requirement already satisfied: tqdm>=4.42.1 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (4.65.0)\n",
      "Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (4.9.0)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (2.0.4)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (3.4)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (1.26.18)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (2023.11.17)\n",
      "Downloading huggingface_hub-0.23.4-py3-none-any.whl (402 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m402.6/402.6 kB\u001b[0m \u001b[31m12.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hInstalling collected packages: huggingface_hub\n",
      "Successfully installed huggingface_hub-0.23.4\n",
      "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n",
      "\u001b[0mCollecting auto-gptq\n",
      "  Downloading auto_gptq-0.7.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (18 kB)\n",
      "Requirement already satisfied: torch in /opt/conda/lib/python3.10/site-packages (2.2.0)\n",
      "Collecting datasets\n",
      "  Downloading datasets-2.20.0-py3-none-any.whl.metadata (19 kB)\n",
      "Collecting evaluate\n",
      "  Downloading evaluate-0.4.2-py3-none-any.whl.metadata (9.3 kB)\n",
      "Collecting accelerate>=0.26.0 (from auto-gptq)\n",
      "  Downloading accelerate-0.31.0-py3-none-any.whl.metadata (19 kB)\n",
      "Collecting sentencepiece (from auto-gptq)\n",
      "  Downloading sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.7 kB)\n",
      "Requirement already satisfied: numpy in /opt/conda/lib/python3.10/site-packages (from auto-gptq) (1.26.3)\n",
      "Collecting rouge (from auto-gptq)\n",
      "  Downloading rouge-1.0.1-py3-none-any.whl.metadata (4.1 kB)\n",
      "Collecting gekko (from auto-gptq)\n",
      "  Downloading gekko-1.1.3-py3-none-any.whl.metadata (3.0 kB)\n",
      "Collecting safetensors (from auto-gptq)\n",
      "  Downloading safetensors-0.4.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.8 kB)\n",
      "Collecting transformers>=4.31.0 (from auto-gptq)\n",
      "  Downloading transformers-4.42.3-py3-none-any.whl.metadata (43 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.6/43.6 kB\u001b[0m \u001b[31m2.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting peft>=0.5.0 (from auto-gptq)\n",
      "  Downloading peft-0.11.1-py3-none-any.whl.metadata (13 kB)\n",
      "Requirement already satisfied: tqdm in /opt/conda/lib/python3.10/site-packages (from auto-gptq) (4.65.0)\n",
      "Requirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from torch) (3.13.1)\n",
      "Requirement already satisfied: typing-extensions>=4.8.0 in /opt/conda/lib/python3.10/site-packages (from torch) (4.9.0)\n",
      "Requirement already satisfied: sympy in /opt/conda/lib/python3.10/site-packages (from torch) (1.12)\n",
      "Requirement already satisfied: networkx in /opt/conda/lib/python3.10/site-packages (from torch) (3.1)\n",
      "Requirement already satisfied: jinja2 in /opt/conda/lib/python3.10/site-packages (from torch) (3.1.2)\n",
      "Requirement already satisfied: fsspec in /opt/conda/lib/python3.10/site-packages (from torch) (2023.12.2)\n",
      "Collecting pyarrow>=15.0.0 (from datasets)\n",
      "  Downloading pyarrow-16.1.0-cp310-cp310-manylinux_2_28_x86_64.whl.metadata (3.0 kB)\n",
      "Collecting pyarrow-hotfix (from datasets)\n",
      "  Downloading pyarrow_hotfix-0.6-py3-none-any.whl.metadata (3.6 kB)\n",
      "Collecting dill<0.3.9,>=0.3.0 (from datasets)\n",
      "  Downloading dill-0.3.8-py3-none-any.whl.metadata (10 kB)\n",
      "Collecting pandas (from datasets)\n",
      "  Downloading pandas-2.2.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (19 kB)\n",
      "Collecting requests>=2.32.2 (from datasets)\n",
      "  Downloading requests-2.32.3-py3-none-any.whl.metadata (4.6 kB)\n",
      "Collecting tqdm (from auto-gptq)\n",
      "  Downloading tqdm-4.66.4-py3-none-any.whl.metadata (57 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.6/57.6 kB\u001b[0m \u001b[31m3.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting xxhash (from datasets)\n",
      "  Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n",
      "Collecting multiprocess (from datasets)\n",
      "  Downloading multiprocess-0.70.16-py310-none-any.whl.metadata (7.2 kB)\n",
      "Collecting aiohttp (from datasets)\n",
      "  Downloading aiohttp-3.9.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.5 kB)\n",
      "Requirement already satisfied: huggingface-hub>=0.21.2 in /opt/conda/lib/python3.10/site-packages (from datasets) (0.23.4)\n",
      "Requirement already satisfied: packaging in /opt/conda/lib/python3.10/site-packages (from datasets) (23.1)\n",
      "Requirement already satisfied: pyyaml>=5.1 in /opt/conda/lib/python3.10/site-packages (from datasets) (6.0.1)\n",
      "Requirement already satisfied: psutil in /opt/conda/lib/python3.10/site-packages (from accelerate>=0.26.0->auto-gptq) (5.9.0)\n",
      "Collecting aiosignal>=1.1.2 (from aiohttp->datasets)\n",
      "  Downloading aiosignal-1.3.1-py3-none-any.whl.metadata (4.0 kB)\n",
      "Requirement already satisfied: attrs>=17.3.0 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets) (23.1.0)\n",
      "Collecting frozenlist>=1.1.1 (from aiohttp->datasets)\n",
      "  Downloading frozenlist-1.4.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n",
      "Collecting multidict<7.0,>=4.5 (from aiohttp->datasets)\n",
      "  Downloading multidict-6.0.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.2 kB)\n",
      "Collecting yarl<2.0,>=1.0 (from aiohttp->datasets)\n",
      "  Downloading yarl-1.9.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (31 kB)\n",
      "Collecting async-timeout<5.0,>=4.0 (from aiohttp->datasets)\n",
      "  Downloading async_timeout-4.0.3-py3-none-any.whl.metadata (4.2 kB)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests>=2.32.2->datasets) (2.0.4)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests>=2.32.2->datasets) (3.4)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.10/site-packages (from requests>=2.32.2->datasets) (1.26.18)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.10/site-packages (from requests>=2.32.2->datasets) (2023.11.17)\n",
      "Collecting regex!=2019.12.17 (from transformers>=4.31.0->auto-gptq)\n",
      "  Downloading regex-2024.5.15-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (40 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.9/40.9 kB\u001b[0m \u001b[31m2.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting tokenizers<0.20,>=0.19 (from transformers>=4.31.0->auto-gptq)\n",
      "  Downloading tokenizers-0.19.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in /opt/conda/lib/python3.10/site-packages (from jinja2->torch) (2.1.3)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /opt/conda/lib/python3.10/site-packages (from pandas->datasets) (2.9.0.post0)\n",
      "Requirement already satisfied: pytz>=2020.1 in /opt/conda/lib/python3.10/site-packages (from pandas->datasets) (2023.3.post1)\n",
      "Collecting tzdata>=2022.7 (from pandas->datasets)\n",
      "  Downloading tzdata-2024.1-py2.py3-none-any.whl.metadata (1.4 kB)\n",
      "Requirement already satisfied: six in /opt/conda/lib/python3.10/site-packages (from rouge->auto-gptq) (1.16.0)\n",
      "Requirement already satisfied: mpmath>=0.19 in /opt/conda/lib/python3.10/site-packages (from sympy->torch) (1.3.0)\n",
      "Downloading auto_gptq-0.7.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (23.5 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m23.5/23.5 MB\u001b[0m \u001b[31m36.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading datasets-2.20.0-py3-none-any.whl (547 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m547.8/547.8 kB\u001b[0m \u001b[31m27.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading evaluate-0.4.2-py3-none-any.whl (84 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m84.1/84.1 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading accelerate-0.31.0-py3-none-any.whl (309 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m309.4/309.4 kB\u001b[0m \u001b[31m19.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading dill-0.3.8-py3-none-any.whl (116 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m9.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading aiohttp-3.9.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m42.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading peft-0.11.1-py3-none-any.whl (251 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m251.6/251.6 kB\u001b[0m \u001b[31m15.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading pyarrow-16.1.0-cp310-cp310-manylinux_2_28_x86_64.whl (40.8 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.8/40.8 MB\u001b[0m \u001b[31m54.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading requests-2.32.3-py3-none-any.whl (64 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m64.9/64.9 kB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading safetensors-0.4.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m46.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading tqdm-4.66.4-py3-none-any.whl (78 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m78.3/78.3 kB\u001b[0m \u001b[31m5.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading transformers-4.42.3-py3-none-any.whl (9.3 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.3/9.3 MB\u001b[0m \u001b[31m77.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading gekko-1.1.3-py3-none-any.whl (13.2 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.2/13.2 MB\u001b[0m \u001b[31m71.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading multiprocess-0.70.16-py310-none-any.whl (134 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m10.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading pandas-2.2.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (13.0 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.0/13.0 MB\u001b[0m \u001b[31m70.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\n",
      "Downloading rouge-1.0.1-py3-none-any.whl (13 kB)\n",
      "Downloading sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m52.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m13.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)\n",
      "Downloading async_timeout-4.0.3-py3-none-any.whl (5.7 kB)\n",
      "Downloading frozenlist-1.4.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (239 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m239.5/239.5 kB\u001b[0m \u001b[31m15.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading multidict-6.0.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (124 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m124.3/124.3 kB\u001b[0m \u001b[31m8.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading regex-2024.5.15-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (775 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m775.1/775.1 kB\u001b[0m \u001b[31m37.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading tokenizers-0.19.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.6 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m63.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n",
      "\u001b[?25hDownloading tzdata-2024.1-py2.py3-none-any.whl (345 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m345.4/345.4 kB\u001b[0m \u001b[31m23.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading yarl-1.9.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (301 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m301.6/301.6 kB\u001b[0m \u001b[31m21.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hInstalling collected packages: sentencepiece, xxhash, tzdata, tqdm, safetensors, rouge, requests, regex, pyarrow-hotfix, pyarrow, multidict, gekko, frozenlist, dill, async-timeout, yarl, pandas, multiprocess, aiosignal, tokenizers, aiohttp, accelerate, transformers, peft, datasets, evaluate, auto-gptq\n",
      "  Attempting uninstall: tqdm\n",
      "    Found existing installation: tqdm 4.65.0\n",
      "    Uninstalling tqdm-4.65.0:\n",
      "      Successfully uninstalled tqdm-4.65.0\n",
      "  Attempting uninstall: requests\n",
      "    Found existing installation: requests 2.31.0\n",
      "    Uninstalling requests-2.31.0:\n",
      "      Successfully uninstalled requests-2.31.0\n",
      "Successfully installed accelerate-0.31.0 aiohttp-3.9.5 aiosignal-1.3.1 async-timeout-4.0.3 auto-gptq-0.7.1 datasets-2.20.0 dill-0.3.8 evaluate-0.4.2 frozenlist-1.4.1 gekko-1.1.3 multidict-6.0.5 multiprocess-0.70.16 pandas-2.2.2 peft-0.11.1 pyarrow-16.1.0 pyarrow-hotfix-0.6 regex-2024.5.15 requests-2.32.3 rouge-1.0.1 safetensors-0.4.3 sentencepiece-0.2.0 tokenizers-0.19.1 tqdm-4.66.4 transformers-4.42.3 tzdata-2024.1 xxhash-3.4.1 yarl-1.9.4\n",
      "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n",
      "\u001b[0mCollecting optimum\n",
      "  Downloading optimum-1.20.0-py3-none-any.whl.metadata (19 kB)\n",
      "Requirement already satisfied: accelerate in /opt/conda/lib/python3.10/site-packages (0.31.0)\n",
      "Collecting coloredlogs (from optimum)\n",
      "  Downloading coloredlogs-15.0.1-py2.py3-none-any.whl.metadata (12 kB)\n",
      "Requirement already satisfied: sympy in /opt/conda/lib/python3.10/site-packages (from optimum) (1.12)\n",
      "Collecting transformers<4.42.0,>=4.26.0 (from transformers[sentencepiece]<4.42.0,>=4.26.0->optimum)\n",
      "  Downloading transformers-4.41.2-py3-none-any.whl.metadata (43 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.8/43.8 kB\u001b[0m \u001b[31m1.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: torch>=1.11 in /opt/conda/lib/python3.10/site-packages (from optimum) (2.2.0)\n",
      "Requirement already satisfied: packaging in /opt/conda/lib/python3.10/site-packages (from optimum) (23.1)\n",
      "Requirement already satisfied: numpy in /opt/conda/lib/python3.10/site-packages (from optimum) (1.26.3)\n",
      "Requirement already satisfied: huggingface-hub>=0.8.0 in /opt/conda/lib/python3.10/site-packages (from optimum) (0.23.4)\n",
      "Requirement already satisfied: datasets in /opt/conda/lib/python3.10/site-packages (from optimum) (2.20.0)\n",
      "Requirement already satisfied: psutil in /opt/conda/lib/python3.10/site-packages (from accelerate) (5.9.0)\n",
      "Requirement already satisfied: pyyaml in /opt/conda/lib/python3.10/site-packages (from accelerate) (6.0.1)\n",
      "Requirement already satisfied: safetensors>=0.3.1 in /opt/conda/lib/python3.10/site-packages (from accelerate) (0.4.3)\n",
      "Requirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.8.0->optimum) (3.13.1)\n",
      "Requirement already satisfied: fsspec>=2023.5.0 in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.8.0->optimum) (2023.12.2)\n",
      "Requirement already satisfied: requests in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.8.0->optimum) (2.32.3)\n",
      "Requirement already satisfied: tqdm>=4.42.1 in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.8.0->optimum) (4.66.4)\n",
      "Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.8.0->optimum) (4.9.0)\n",
      "Requirement already satisfied: networkx in /opt/conda/lib/python3.10/site-packages (from torch>=1.11->optimum) (3.1)\n",
      "Requirement already satisfied: jinja2 in /opt/conda/lib/python3.10/site-packages (from torch>=1.11->optimum) (3.1.2)\n",
      "Requirement already satisfied: regex!=2019.12.17 in /opt/conda/lib/python3.10/site-packages (from transformers<4.42.0,>=4.26.0->transformers[sentencepiece]<4.42.0,>=4.26.0->optimum) (2024.5.15)\n",
      "Requirement already satisfied: tokenizers<0.20,>=0.19 in /opt/conda/lib/python3.10/site-packages (from transformers<4.42.0,>=4.26.0->transformers[sentencepiece]<4.42.0,>=4.26.0->optimum) (0.19.1)\n",
      "Requirement already satisfied: sentencepiece!=0.1.92,>=0.1.91 in /opt/conda/lib/python3.10/site-packages (from transformers[sentencepiece]<4.42.0,>=4.26.0->optimum) (0.2.0)\n",
      "Collecting protobuf (from transformers[sentencepiece]<4.42.0,>=4.26.0->optimum)\n",
      "  Downloading protobuf-5.27.2-cp38-abi3-manylinux2014_x86_64.whl.metadata (592 bytes)\n",
      "Collecting humanfriendly>=9.1 (from coloredlogs->optimum)\n",
      "  Downloading humanfriendly-10.0-py2.py3-none-any.whl.metadata (9.2 kB)\n",
      "Requirement already satisfied: pyarrow>=15.0.0 in /opt/conda/lib/python3.10/site-packages (from datasets->optimum) (16.1.0)\n",
      "Requirement already satisfied: pyarrow-hotfix in /opt/conda/lib/python3.10/site-packages (from datasets->optimum) (0.6)\n",
      "Requirement already satisfied: dill<0.3.9,>=0.3.0 in /opt/conda/lib/python3.10/site-packages (from datasets->optimum) (0.3.8)\n",
      "Requirement already satisfied: pandas in /opt/conda/lib/python3.10/site-packages (from datasets->optimum) (2.2.2)\n",
      "Requirement already satisfied: xxhash in /opt/conda/lib/python3.10/site-packages (from datasets->optimum) (3.4.1)\n",
      "Requirement already satisfied: multiprocess in /opt/conda/lib/python3.10/site-packages (from datasets->optimum) (0.70.16)\n",
      "Requirement already satisfied: aiohttp in /opt/conda/lib/python3.10/site-packages (from datasets->optimum) (3.9.5)\n",
      "Requirement already satisfied: mpmath>=0.19 in /opt/conda/lib/python3.10/site-packages (from sympy->optimum) (1.3.0)\n",
      "Requirement already satisfied: aiosignal>=1.1.2 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets->optimum) (1.3.1)\n",
      "Requirement already satisfied: attrs>=17.3.0 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets->optimum) (23.1.0)\n",
      "Requirement already satisfied: frozenlist>=1.1.1 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets->optimum) (1.4.1)\n",
      "Requirement already satisfied: multidict<7.0,>=4.5 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets->optimum) (6.0.5)\n",
      "Requirement already satisfied: yarl<2.0,>=1.0 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets->optimum) (1.9.4)\n",
      "Requirement already satisfied: async-timeout<5.0,>=4.0 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets->optimum) (4.0.3)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface-hub>=0.8.0->optimum) (2.0.4)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface-hub>=0.8.0->optimum) (3.4)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface-hub>=0.8.0->optimum) (1.26.18)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface-hub>=0.8.0->optimum) (2023.11.17)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in /opt/conda/lib/python3.10/site-packages (from jinja2->torch>=1.11->optimum) (2.1.3)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /opt/conda/lib/python3.10/site-packages (from pandas->datasets->optimum) (2.9.0.post0)\n",
      "Requirement already satisfied: pytz>=2020.1 in /opt/conda/lib/python3.10/site-packages (from pandas->datasets->optimum) (2023.3.post1)\n",
      "Requirement already satisfied: tzdata>=2022.7 in /opt/conda/lib/python3.10/site-packages (from pandas->datasets->optimum) (2024.1)\n",
      "Requirement already satisfied: six>=1.5 in /opt/conda/lib/python3.10/site-packages (from python-dateutil>=2.8.2->pandas->datasets->optimum) (1.16.0)\n",
      "Downloading optimum-1.20.0-py3-none-any.whl (418 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m418.4/418.4 kB\u001b[0m \u001b[31m18.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading transformers-4.41.2-py3-none-any.whl (9.1 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.1/9.1 MB\u001b[0m \u001b[31m74.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0mm\n",
      "\u001b[?25hDownloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m6.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading protobuf-5.27.2-cp38-abi3-manylinux2014_x86_64.whl (309 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m309.3/309.3 kB\u001b[0m \u001b[31m21.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hInstalling collected packages: protobuf, humanfriendly, coloredlogs, transformers, optimum\n",
      "  Attempting uninstall: transformers\n",
      "    Found existing installation: transformers 4.42.3\n",
      "    Uninstalling transformers-4.42.3:\n",
      "      Successfully uninstalled transformers-4.42.3\n",
      "Successfully installed coloredlogs-15.0.1 humanfriendly-10.0 optimum-1.20.0 protobuf-5.27.2 transformers-4.41.2\n",
      "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n",
      "\u001b[0mCollecting git+https://github.com/huggingface/transformers.git\n",
      "  Cloning https://github.com/huggingface/transformers.git to /tmp/pip-req-build-eejcbjhz\n",
      "  Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers.git /tmp/pip-req-build-eejcbjhz\n",
      "  Resolved https://github.com/huggingface/transformers.git to commit 3345ae733b6f4aeb7204a0f3e646a3cdbaad0023\n",
      "  Installing build dependencies ... \u001b[?25ldone\n",
      "\u001b[?25h  Getting requirements to build wheel ... \u001b[?25ldone\n",
      "\u001b[?25h  Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
      "\u001b[?25hRequirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from transformers==4.43.0.dev0) (3.13.1)\n",
      "Requirement already satisfied: huggingface-hub<1.0,>=0.23.2 in /opt/conda/lib/python3.10/site-packages (from transformers==4.43.0.dev0) (0.23.4)\n",
      "Requirement already satisfied: numpy<2.0,>=1.17 in /opt/conda/lib/python3.10/site-packages (from transformers==4.43.0.dev0) (1.26.3)\n",
      "Requirement already satisfied: packaging>=20.0 in /opt/conda/lib/python3.10/site-packages (from transformers==4.43.0.dev0) (23.1)\n",
      "Requirement already satisfied: pyyaml>=5.1 in /opt/conda/lib/python3.10/site-packages (from transformers==4.43.0.dev0) (6.0.1)\n",
      "Requirement already satisfied: regex!=2019.12.17 in /opt/conda/lib/python3.10/site-packages (from transformers==4.43.0.dev0) (2024.5.15)\n",
      "Requirement already satisfied: requests in /opt/conda/lib/python3.10/site-packages (from transformers==4.43.0.dev0) (2.32.3)\n",
      "Requirement already satisfied: tokenizers<0.20,>=0.19 in /opt/conda/lib/python3.10/site-packages (from transformers==4.43.0.dev0) (0.19.1)\n",
      "Requirement already satisfied: safetensors>=0.4.1 in /opt/conda/lib/python3.10/site-packages (from transformers==4.43.0.dev0) (0.4.3)\n",
      "Requirement already satisfied: tqdm>=4.27 in /opt/conda/lib/python3.10/site-packages (from transformers==4.43.0.dev0) (4.66.4)\n",
      "Requirement already satisfied: fsspec>=2023.5.0 in /opt/conda/lib/python3.10/site-packages (from huggingface-hub<1.0,>=0.23.2->transformers==4.43.0.dev0) (2023.12.2)\n",
      "Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/lib/python3.10/site-packages (from huggingface-hub<1.0,>=0.23.2->transformers==4.43.0.dev0) (4.9.0)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests->transformers==4.43.0.dev0) (2.0.4)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests->transformers==4.43.0.dev0) (3.4)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.10/site-packages (from requests->transformers==4.43.0.dev0) (1.26.18)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.10/site-packages (from requests->transformers==4.43.0.dev0) (2023.11.17)\n",
      "Building wheels for collected packages: transformers\n",
      "  Building wheel for transformers (pyproject.toml) ... \u001b[?25ldone\n",
      "\u001b[?25h  Created wheel for transformers: filename=transformers-4.43.0.dev0-py3-none-any.whl size=9337421 sha256=631815f19f4f77bf014036e1a5f667e8918d3097e27ac0f37debad407921e8c5\n",
      "  Stored in directory: /tmp/pip-ephem-wheel-cache-m70g28g0/wheels/e7/9c/5b/e1a9c8007c343041e61cc484433d512ea9274272e3fcbe7c16\n",
      "Successfully built transformers\n",
      "Installing collected packages: transformers\n",
      "  Attempting uninstall: transformers\n",
      "    Found existing installation: transformers 4.41.2\n",
      "    Uninstalling transformers-4.41.2:\n",
      "      Successfully uninstalled transformers-4.41.2\n",
      "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
      "optimum 1.20.0 requires transformers[sentencepiece]<4.42.0,>=4.26.0, but you have transformers 4.43.0.dev0 which is incompatible.\u001b[0m\u001b[31m\n",
      "\u001b[0mSuccessfully installed transformers-4.43.0.dev0\n",
      "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n",
      "\u001b[0mCollecting flash-attn\n",
      "  Downloading flash_attn-2.5.9.post1.tar.gz (2.6 MB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.6/2.6 MB\u001b[0m \u001b[31m45.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
      "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25ldone\n",
      "\u001b[?25hRequirement already satisfied: torch in /opt/conda/lib/python3.10/site-packages (from flash-attn) (2.2.0)\n",
      "Collecting einops (from flash-attn)\n",
      "  Downloading einops-0.8.0-py3-none-any.whl.metadata (12 kB)\n",
      "Requirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from torch->flash-attn) (3.13.1)\n",
      "Requirement already satisfied: typing-extensions>=4.8.0 in /opt/conda/lib/python3.10/site-packages (from torch->flash-attn) (4.9.0)\n",
      "Requirement already satisfied: sympy in /opt/conda/lib/python3.10/site-packages (from torch->flash-attn) (1.12)\n",
      "Requirement already satisfied: networkx in /opt/conda/lib/python3.10/site-packages (from torch->flash-attn) (3.1)\n",
      "Requirement already satisfied: jinja2 in /opt/conda/lib/python3.10/site-packages (from torch->flash-attn) (3.1.2)\n",
      "Requirement already satisfied: fsspec in /opt/conda/lib/python3.10/site-packages (from torch->flash-attn) (2023.12.2)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in /opt/conda/lib/python3.10/site-packages (from jinja2->torch->flash-attn) (2.1.3)\n",
      "Requirement already satisfied: mpmath>=0.19 in /opt/conda/lib/python3.10/site-packages (from sympy->torch->flash-attn) (1.3.0)\n",
      "Downloading einops-0.8.0-py3-none-any.whl (43 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.2/43.2 kB\u001b[0m \u001b[31m2.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hBuilding wheels for collected packages: flash-attn\n",
      "  Building wheel for flash-attn (setup.py) ... \u001b[?25ldone\n",
      "\u001b[?25h  Created wheel for flash-attn: filename=flash_attn-2.5.9.post1-cp310-cp310-linux_x86_64.whl size=120821333 sha256=7bfd5ecaaf20577cd1255eaa90d9008a09050b3408ba6388bcbc5b6144f482d0\n",
      "  Stored in directory: /root/.cache/pip/wheels/cc/ad/f6/7ccf0238790d6346e9fe622923a76ec218e890d356b9a2754a\n",
      "Successfully built flash-attn\n",
      "Installing collected packages: einops, flash-attn\n",
      "Successfully installed einops-0.8.0 flash-attn-2.5.9.post1\n",
      "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n",
      "\u001b[0m"
     ]
    }
   ],
   "source": [
    "!pip install huggingface_hub\n",
    "!pip install auto-gptq torch datasets evaluate \n",
    "!pip install --upgrade optimum accelerate\n",
    "!pip install --upgrade git+https://github.com/huggingface/transformers.git\n",
    "!pip install flash-attn --no-build-isolation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "bdedafe4-8e7d-49ac-bbee-dc7b3e82fbf7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "756f7a950bbb4df39b7a6e8c8a68240a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from huggingface_hub import HfApi, notebook_login, login\n",
    "\n",
    "token = \"\"\n",
    "\n",
    "#login(token=token)\n",
    "notebook_login()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "46f6d849-b9e7-4811-93e2-ad1d351ec81d",
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'HfApi' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[1], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m api \u001b[38;5;241m=\u001b[39m \u001b[43mHfApi\u001b[49m()\n\u001b[1;32m      3\u001b[0m quant_repo \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mGranther/Gemma-2-9B-Instruct-4Bit-GPTQ\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m      5\u001b[0m api\u001b[38;5;241m.\u001b[39mupload_file(\n\u001b[1;32m      6\u001b[0m     path_or_fileobj\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mgemma_2_9b_4bit_gptq.ipynb\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m      7\u001b[0m     path_in_repo\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mgemma_2_9b_4bit_gptq.ipynb\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m      8\u001b[0m     repo_id\u001b[38;5;241m=\u001b[39mquant_repo,\n\u001b[1;32m      9\u001b[0m     repo_type\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m     10\u001b[0m )\n",
      "\u001b[0;31mNameError\u001b[0m: name 'HfApi' is not defined"
     ]
    }
   ],
   "source": [
    "api = HfApi()\n",
    "\n",
    "quant_repo = \"Granther/Gemma-2-9B-Instruct-4Bit-GPTQ\"\n",
    "\n",
    "api.upload_file(\n",
    "    path_or_fileobj=\"gemma_2_9b_4bit_gptq.ipynb\",\n",
    "    path_in_repo=\"gemma_2_9b_4bit_gptq.ipynb\",\n",
    "    repo_id=quant_repo,\n",
    "    repo_type=\"model\",\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "0731cc89-e0a7-4bd0-ae02-7440a146fead",
   "metadata": {},
   "outputs": [],
   "source": [
    "# HyperParams\n",
    "\n",
    "model_id = \"google/gemma-2-9b-it\"\n",
    "quant_model_name = \"Gemma-2-9B-Instruct-4Bit-GPTQ\"\n",
    "quant_layers = \"model.layers\"\n",
    "bits = 4\n",
    "dataset = \"c4\"\n",
    "seq_len = 4096"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "76d347fa-71de-4d61-987a-2e55e06754ca",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "177ceac4eb4948b0b154629380f6fb6f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
    "from optimum.gptq import GPTQQuantizer, load_quantized_model\n",
    "import torch\n",
    "\n",
    "\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
    "model = AutoModelForCausalLM.from_pretrained(model_id, \n",
    "                                             attn_implementation=\"flash_attention_2\",\n",
    "                                             device_map=\"auto\",\n",
    "                                             use_cache=False,\n",
    "                                             torch_dtype=torch.float16)\n",
    "\n",
    "quantizer = GPTQQuantizer(bits=bits, dataset=dataset, \n",
    "                          block_name_to_quantize=quant_layers,\n",
    "                          group_size=128, # default\n",
    "                          use_cuda_fp16=True, # kind of just a test\n",
    "                          model_seqlen=seq_len)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "c06b1a34-fb44-48f5-903d-de0d00709ead",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "9688.58447265625\n",
      "9690.0\n",
      "9688.58447265625\n",
      "9690.0\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.10/site-packages/torch/cuda/memory.py:440: FutureWarning: torch.cuda.memory_cached has been renamed to torch.cuda.memory_reserved\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d863785632574222b3a170e8d255dae5",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing model.layers blocks :   0%|          | 0/42 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Quantizing layers inside the block:   0%|          | 0/7 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using Exllamav2 backend will reorder the weights offline, thus you will not be able to save the model with the right weights.Setting `disable_exllama=True`. You should only use Exllamav2 backend for inference. \n",
      "/opt/conda/lib/python3.10/site-packages/transformers/modeling_utils.py:4565: FutureWarning: `_is_quantized_training_enabled` is going to be deprecated in transformers 4.39.0. Please use `model.hf_quantizer.is_trainable` instead\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "# Quantize Model\n",
    "print(torch.cuda.memory_allocated()/1024**2)\n",
    "print(torch.cuda.memory_reserved()/1024**2)\n",
    "torch.cuda.empty_cache()\n",
    "print(torch.cuda.memory_allocated()/1024**2)\n",
    "print(torch.cuda.memory_reserved()/1024**2)\n",
    "\n",
    "model = quantizer.quantize_model(model, tokenizer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "6d8f96b7-9dc9-42cc-bc43-eab8f6d83777",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Save model\n",
    "\n",
    "quantizer.save(model, quant_model_name)\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
    "#tokenizer.save_pretrained()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "7d23dc0b-60f2-4fcc-9501-d132f14bbbda",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('Gemma-2-9B-Instruct-4Bit-GPTQ/tokenizer_config.json',\n",
       " 'Gemma-2-9B-Instruct-4Bit-GPTQ/special_tokens_map.json',\n",
       " 'Gemma-2-9B-Instruct-4Bit-GPTQ/tokenizer.model',\n",
       " 'Gemma-2-9B-Instruct-4Bit-GPTQ/added_tokens.json',\n",
       " 'Gemma-2-9B-Instruct-4Bit-GPTQ/tokenizer.json')"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Push model to hub\n",
    "\n",
    "tok = AutoTokenizer.from_pretrained(model_id)\n",
    "tok.save_pretrained(quant_model_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "488c2862-882b-48aa-837e-5a730026b2f3",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.10/site-packages/transformers/modeling_utils.py:4565: FutureWarning: `_is_quantized_training_enabled` is going to be deprecated in transformers 4.39.0. Please use `model.hf_quantizer.is_trainable` instead\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "58d29cccfc224245a819a73f320b3a04",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/1346 [00:00<?, ?w/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "IOPub message rate exceeded.\n",
      "The Jupyter server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--ServerApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "ServerApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "ServerApp.rate_limit_window=3.0 (secs)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from optimum.gptq import load_quantized_model\n",
    "\n",
    "model = AutoModelForCausalLM.from_pretrained(quant_model_name, device_map='auto')\n",
    "\n",
    "model = load_quantized_model(model, save_folder=quant_model_name, device_map=\"auto\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "2e06779c-cf6b-45d0-829d-a916535c1652",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Gemma2ForCausalLM(\n",
       "  (model): Gemma2Model(\n",
       "    (embed_tokens): Embedding(256000, 3584, padding_idx=0)\n",
       "    (layers): ModuleList(\n",
       "      (0-41): 42 x Gemma2DecoderLayer(\n",
       "        (self_attn): Gemma2SdpaAttention(\n",
       "          (rotary_emb): Gemma2RotaryEmbedding()\n",
       "          (k_proj): QuantLinear()\n",
       "          (o_proj): QuantLinear()\n",
       "          (q_proj): QuantLinear()\n",
       "          (v_proj): QuantLinear()\n",
       "        )\n",
       "        (mlp): Gemma2MLP(\n",
       "          (act_fn): PytorchGELUTanh()\n",
       "          (down_proj): QuantLinear()\n",
       "          (gate_proj): QuantLinear()\n",
       "          (up_proj): QuantLinear()\n",
       "        )\n",
       "        (input_layernorm): Gemma2RMSNorm()\n",
       "        (post_attention_layernorm): Gemma2RMSNorm()\n",
       "        (pre_feedforward_layernorm): Gemma2RMSNorm()\n",
       "        (post_feedforward_layernorm): Gemma2RMSNorm()\n",
       "      )\n",
       "    )\n",
       "    (norm): Gemma2RMSNorm()\n",
       "  )\n",
       "  (lm_head): Linear(in_features=3584, out_features=256000, bias=False)\n",
       ")"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.eval()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "80de9477-825a-4145-8fa7-a01ca7a26908",
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import pipeline\n",
    "\n",
    "pipe = pipeline('text-generation', model=model, tokenizer=model_id)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "5e1c7025-54ba-465e-8121-e52a78ee3fe4",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.10/site-packages/transformers/generation/utils.py:1249: UserWarning: Using the model-agnostic default `max_length` (=20) to control the generation length. We recommend setting `max_new_tokens` to control the maximum length of the generation.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "ename": "RuntimeError",
     "evalue": "Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0! (when checking argument for argument index in method wrapper_CUDA__index_select)",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[24], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mpipe\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mhello\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/transformers/pipelines/text_generation.py:262\u001b[0m, in \u001b[0;36mTextGenerationPipeline.__call__\u001b[0;34m(self, text_inputs, **kwargs)\u001b[0m\n\u001b[1;32m    260\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__call__\u001b[39m(chats, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m    261\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 262\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__call__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mtext_inputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/transformers/pipelines/base.py:1254\u001b[0m, in \u001b[0;36mPipeline.__call__\u001b[0;34m(self, inputs, num_workers, batch_size, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1246\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mnext\u001b[39m(\n\u001b[1;32m   1247\u001b[0m         \u001b[38;5;28miter\u001b[39m(\n\u001b[1;32m   1248\u001b[0m             \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mget_iterator(\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1251\u001b[0m         )\n\u001b[1;32m   1252\u001b[0m     )\n\u001b[1;32m   1253\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1254\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun_single\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpreprocess_params\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mforward_params\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpostprocess_params\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/transformers/pipelines/base.py:1261\u001b[0m, in \u001b[0;36mPipeline.run_single\u001b[0;34m(self, inputs, preprocess_params, forward_params, postprocess_params)\u001b[0m\n\u001b[1;32m   1259\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mrun_single\u001b[39m(\u001b[38;5;28mself\u001b[39m, inputs, preprocess_params, forward_params, postprocess_params):\n\u001b[1;32m   1260\u001b[0m     model_inputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpreprocess(inputs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mpreprocess_params)\n\u001b[0;32m-> 1261\u001b[0m     model_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mforward\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_inputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mforward_params\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1262\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpostprocess(model_outputs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mpostprocess_params)\n\u001b[1;32m   1263\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m outputs\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/transformers/pipelines/base.py:1161\u001b[0m, in \u001b[0;36mPipeline.forward\u001b[0;34m(self, model_inputs, **forward_params)\u001b[0m\n\u001b[1;32m   1159\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m inference_context():\n\u001b[1;32m   1160\u001b[0m         model_inputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_ensure_tensor_on_device(model_inputs, device\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdevice)\n\u001b[0;32m-> 1161\u001b[0m         model_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_forward\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_inputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mforward_params\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1162\u001b[0m         model_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_ensure_tensor_on_device(model_outputs, device\u001b[38;5;241m=\u001b[39mtorch\u001b[38;5;241m.\u001b[39mdevice(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcpu\u001b[39m\u001b[38;5;124m\"\u001b[39m))\n\u001b[1;32m   1163\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/transformers/pipelines/text_generation.py:349\u001b[0m, in \u001b[0;36mTextGenerationPipeline._forward\u001b[0;34m(self, model_inputs, **generate_kwargs)\u001b[0m\n\u001b[1;32m    346\u001b[0m         generate_kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmin_length\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m prefix_length\n\u001b[1;32m    348\u001b[0m \u001b[38;5;66;03m# BS x SL\u001b[39;00m\n\u001b[0;32m--> 349\u001b[0m generated_sequence \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[43minput_ids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minput_ids\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mgenerate_kwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    350\u001b[0m out_b \u001b[38;5;241m=\u001b[39m generated_sequence\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m    351\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mframework \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpt\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/utils/_contextlib.py:115\u001b[0m, in \u001b[0;36mcontext_decorator.<locals>.decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    112\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m    113\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m    114\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m ctx_factory():\n\u001b[0;32m--> 115\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/transformers/generation/utils.py:1914\u001b[0m, in \u001b[0;36mGenerationMixin.generate\u001b[0;34m(self, inputs, generation_config, logits_processor, stopping_criteria, prefix_allowed_tokens_fn, synced_gpus, assistant_model, streamer, negative_prompt_ids, negative_prompt_attention_mask, **kwargs)\u001b[0m\n\u001b[1;32m   1906\u001b[0m     input_ids, model_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_expand_inputs_for_generation(\n\u001b[1;32m   1907\u001b[0m         input_ids\u001b[38;5;241m=\u001b[39minput_ids,\n\u001b[1;32m   1908\u001b[0m         expand_size\u001b[38;5;241m=\u001b[39mgeneration_config\u001b[38;5;241m.\u001b[39mnum_return_sequences,\n\u001b[1;32m   1909\u001b[0m         is_encoder_decoder\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39mis_encoder_decoder,\n\u001b[1;32m   1910\u001b[0m         \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mmodel_kwargs,\n\u001b[1;32m   1911\u001b[0m     )\n\u001b[1;32m   1913\u001b[0m     \u001b[38;5;66;03m# 13. run sample (it degenerates to greedy search when `generation_config.do_sample=False`)\u001b[39;00m\n\u001b[0;32m-> 1914\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sample\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1915\u001b[0m \u001b[43m        \u001b[49m\u001b[43minput_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1916\u001b[0m \u001b[43m        \u001b[49m\u001b[43mlogits_processor\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprepared_logits_processor\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1917\u001b[0m \u001b[43m        \u001b[49m\u001b[43mlogits_warper\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprepared_logits_warper\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1918\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstopping_criteria\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprepared_stopping_criteria\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1919\u001b[0m \u001b[43m        \u001b[49m\u001b[43mgeneration_config\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgeneration_config\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1920\u001b[0m \u001b[43m        \u001b[49m\u001b[43msynced_gpus\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msynced_gpus\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1921\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstreamer\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstreamer\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1922\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1923\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1925\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m generation_mode \u001b[38;5;129;01min\u001b[39;00m (GenerationMode\u001b[38;5;241m.\u001b[39mBEAM_SAMPLE, GenerationMode\u001b[38;5;241m.\u001b[39mBEAM_SEARCH):\n\u001b[1;32m   1926\u001b[0m     \u001b[38;5;66;03m# 11. prepare logits warper\u001b[39;00m\n\u001b[1;32m   1927\u001b[0m     prepared_logits_warper \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m   1928\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_logits_warper(generation_config, device\u001b[38;5;241m=\u001b[39minput_ids\u001b[38;5;241m.\u001b[39mdevice)\n\u001b[1;32m   1929\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m generation_config\u001b[38;5;241m.\u001b[39mdo_sample\n\u001b[1;32m   1930\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1931\u001b[0m     )\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/transformers/generation/utils.py:2651\u001b[0m, in \u001b[0;36mGenerationMixin._sample\u001b[0;34m(self, input_ids, logits_processor, stopping_criteria, generation_config, synced_gpus, streamer, logits_warper, **model_kwargs)\u001b[0m\n\u001b[1;32m   2648\u001b[0m model_inputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprepare_inputs_for_generation(input_ids, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mmodel_kwargs)\n\u001b[1;32m   2650\u001b[0m \u001b[38;5;66;03m# forward pass to get next token\u001b[39;00m\n\u001b[0;32m-> 2651\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m   2652\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_inputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2653\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m   2654\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2655\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2656\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   2658\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m synced_gpus \u001b[38;5;129;01mand\u001b[39;00m this_peer_finished:\n\u001b[1;32m   2659\u001b[0m     \u001b[38;5;28;01mcontinue\u001b[39;00m  \u001b[38;5;66;03m# don't waste resources running the code we don't need\u001b[39;00m\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1509\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1518\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1519\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1523\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/accelerate/hooks.py:166\u001b[0m, in \u001b[0;36madd_hook_to_module.<locals>.new_forward\u001b[0;34m(module, *args, **kwargs)\u001b[0m\n\u001b[1;32m    164\u001b[0m         output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m    165\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 166\u001b[0m     output \u001b[38;5;241m=\u001b[39m \u001b[43mmodule\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_old_forward\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m module\u001b[38;5;241m.\u001b[39m_hf_hook\u001b[38;5;241m.\u001b[39mpost_forward(module, output)\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/transformers/models/gemma2/modeling_gemma2.py:1068\u001b[0m, in \u001b[0;36mGemma2ForCausalLM.forward\u001b[0;34m(self, input_ids, attention_mask, position_ids, past_key_values, inputs_embeds, labels, use_cache, output_attentions, output_hidden_states, return_dict, cache_position)\u001b[0m\n\u001b[1;32m   1065\u001b[0m return_dict \u001b[38;5;241m=\u001b[39m return_dict \u001b[38;5;28;01mif\u001b[39;00m return_dict \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39muse_return_dict\n\u001b[1;32m   1067\u001b[0m \u001b[38;5;66;03m# decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)\u001b[39;00m\n\u001b[0;32m-> 1068\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1069\u001b[0m \u001b[43m    \u001b[49m\u001b[43minput_ids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minput_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1070\u001b[0m \u001b[43m    \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1071\u001b[0m \u001b[43m    \u001b[49m\u001b[43mposition_ids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mposition_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1072\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpast_key_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1073\u001b[0m \u001b[43m    \u001b[49m\u001b[43minputs_embeds\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minputs_embeds\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1074\u001b[0m \u001b[43m    \u001b[49m\u001b[43muse_cache\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_cache\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1075\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1076\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1077\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_dict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1078\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcache_position\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_position\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1079\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1081\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m   1082\u001b[0m logits \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlm_head(hidden_states)\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1509\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1518\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1519\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1523\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/transformers/models/gemma2/modeling_gemma2.py:868\u001b[0m, in \u001b[0;36mGemma2Model.forward\u001b[0;34m(self, input_ids, attention_mask, position_ids, past_key_values, inputs_embeds, use_cache, output_attentions, output_hidden_states, return_dict, cache_position)\u001b[0m\n\u001b[1;32m    865\u001b[0m     use_cache \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[1;32m    867\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m inputs_embeds \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 868\u001b[0m     inputs_embeds \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43membed_tokens\u001b[49m\u001b[43m(\u001b[49m\u001b[43minput_ids\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    870\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m cache_position \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    871\u001b[0m     cache_position \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39marange(\u001b[38;5;241m0\u001b[39m, inputs_embeds\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m1\u001b[39m], device\u001b[38;5;241m=\u001b[39minputs_embeds\u001b[38;5;241m.\u001b[39mdevice)\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1509\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1518\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1519\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1523\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/accelerate/hooks.py:166\u001b[0m, in \u001b[0;36madd_hook_to_module.<locals>.new_forward\u001b[0;34m(module, *args, **kwargs)\u001b[0m\n\u001b[1;32m    164\u001b[0m         output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m    165\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 166\u001b[0m     output \u001b[38;5;241m=\u001b[39m \u001b[43mmodule\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_old_forward\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m module\u001b[38;5;241m.\u001b[39m_hf_hook\u001b[38;5;241m.\u001b[39mpost_forward(module, output)\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/modules/sparse.py:163\u001b[0m, in \u001b[0;36mEmbedding.forward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    162\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[0;32m--> 163\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43membedding\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    164\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpadding_idx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmax_norm\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    165\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mnorm_type\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mscale_grad_by_freq\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msparse\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/functional.py:2237\u001b[0m, in \u001b[0;36membedding\u001b[0;34m(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse)\u001b[0m\n\u001b[1;32m   2231\u001b[0m     \u001b[38;5;66;03m# Note [embedding_renorm set_grad_enabled]\u001b[39;00m\n\u001b[1;32m   2232\u001b[0m     \u001b[38;5;66;03m# XXX: equivalent to\u001b[39;00m\n\u001b[1;32m   2233\u001b[0m     \u001b[38;5;66;03m# with torch.no_grad():\u001b[39;00m\n\u001b[1;32m   2234\u001b[0m     \u001b[38;5;66;03m#   torch.embedding_renorm_\u001b[39;00m\n\u001b[1;32m   2235\u001b[0m     \u001b[38;5;66;03m# remove once script supports set_grad_enabled\u001b[39;00m\n\u001b[1;32m   2236\u001b[0m     _no_grad_embedding_renorm_(weight, \u001b[38;5;28minput\u001b[39m, max_norm, norm_type)\n\u001b[0;32m-> 2237\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43membedding\u001b[49m\u001b[43m(\u001b[49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpadding_idx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mscale_grad_by_freq\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msparse\u001b[49m\u001b[43m)\u001b[49m\n",
      "\u001b[0;31mRuntimeError\u001b[0m: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0! (when checking argument for argument index in method wrapper_CUDA__index_select)"
     ]
    }
   ],
   "source": [
    "pipe(\"hello\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "057d400f-f111-4bdc-8d6d-b56183871e48",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "06d04226b00a4d31a253862e061f8639",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.embed_tokens.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.norm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Peak VRAM used: 15768.32 MB\n"
     ]
    }
   ],
   "source": [
    "# Load Model\n",
    "\n",
    "from accelerate import init_empty_weights\n",
    "\n",
    "with init_empty_weights():\n",
    "    empty_model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, attn_implementation=\"flash_attention_2\")\n",
    "empty_model.tie_weights()\n",
    "\n",
    "#model = load_quantized_model(empty_model, save_folder=quant_model_name, device_map=\"auto\")\n",
    "\n",
    "print(f\"Peak VRAM used: {torch.cuda.max_memory_allocated('cuda') / 1024 ** 2:.2f} MB\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "87b48679-e56c-4e99-9e73-627a56b77ce9",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.10/site-packages/transformers/modeling_utils.py:4565: FutureWarning: `_is_quantized_training_enabled` is going to be deprecated in transformers 4.39.0. Please use `model.hf_quantizer.is_trainable` instead\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b50f5513f57a4be89382a892cfc8358a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/1346 [00:00<?, ?w/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "IOPub message rate exceeded.\n",
      "The Jupyter server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--ServerApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "ServerApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "ServerApp.rate_limit_window=3.0 (secs)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "model = load_quantized_model(empty_model, save_folder=quant_model_name, device_map=\"auto\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "a57efe83-6cc5-4440-b6bc-d4309befd3cb",
   "metadata": {},
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "module 'torch.cuda' has no attribute 'empty_reserved'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[21], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcuda\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mempty_reserved\u001b[49m()\n",
      "\u001b[0;31mAttributeError\u001b[0m: module 'torch.cuda' has no attribute 'empty_reserved'"
     ]
    }
   ],
   "source": [
    "torch.cuda.empty_cache()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "13f9c297-237a-48c3-bd99-1978e73dde64",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c1387c06ecc04655824674484418a5f3",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.embed_tokens.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.0.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.1.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.2.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.3.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.4.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.5.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.6.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.7.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.8.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.9.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.10.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.11.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.12.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.13.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.14.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.15.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.16.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.17.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.18.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.19.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.20.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.21.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.22.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.23.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.24.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.25.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.26.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.27.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.28.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.29.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.30.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.31.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.32.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.33.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.34.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.35.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.36.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.37.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.38.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.39.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.40.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.pre_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.layers.41.post_feedforward_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for model.norm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)\n",
      "  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '\n",
      "/opt/conda/lib/python3.10/site-packages/transformers/modeling_utils.py:4565: FutureWarning: `_is_quantized_training_enabled` is going to be deprecated in transformers 4.39.0. Please use `model.hf_quantizer.is_trainable` instead\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "4ab059b2f77e4e70a2e2711e1ee9c8db",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/1346 [00:00<?, ?w/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "IOPub message rate exceeded.\n",
      "The Jupyter server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--ServerApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "ServerApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "ServerApp.rate_limit_window=3.0 (secs)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from optimum.gptq import GPTQQuantizer, load_quantized_model\n",
    "import torch\n",
    "\n",
    "from accelerate import init_empty_weights\n",
    "with init_empty_weights():\n",
    "    empty_model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16)\n",
    "empty_model.tie_weights()\n",
    "quantized_model = load_quantized_model(empty_model, save_folder=quant_model_name, device_map=\"auto\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3ff3ddf0-b1de-4ea5-b1a3-724d02b90bc6",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Calculate perplexity\n",
    "from auto_gptq import Perplexity"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}