Hugging Face's logo

aissatoubalde
/
lab

Text Generation
Transformers
Safetensors
phi
custom_code
Inference Endpoints
text-generation-inference
Model card Files Community
aissatoubalde commited on
Commit
9091c0d
•
1 Parent(s): b5f32ab

Training in progress, epoch 0

Browse files
Files changed (7) hide show
  1. .gitattributes +1 -0
  2. .ipynb_checkpoints/Untitled-checkpoint.ipynb +6 -0
  3. Untitled.ipynb +1080 -0
  4. adapter_config.json +30 -0
  5. adapter_model.safetensors +3 -0
  6. data.csv +3 -0
  7. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ data.csv filter=lfs diff=lfs merge=lfs -text
.ipynb_checkpoints/Untitled-checkpoint.ipynb ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [],
3
+ "metadata": {},
4
+ "nbformat": 4,
5
+ "nbformat_minor": 5
6
+ }
Untitled.ipynb ADDED
@@ -0,0 +1,1080 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 1,
6
+ "id": "b3b92bc7-d105-405f-970d-804d298b9976",
7
+ "metadata": {},
8
+ "outputs": [
9
+ {
10
+ "name": "stdout",
11
+ "output_type": "stream",
12
+ "text": [
13
+ "Collecting accelerate\n",
14
+ " Downloading accelerate-0.26.1-py3-none-any.whl.metadata (18 kB)\n",
15
+ "Collecting transformers\n",
16
+ " Downloading transformers-4.37.2-py3-none-any.whl.metadata (129 kB)\n",
17
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m129.4/129.4 kB\u001b[0m \u001b[31m893.7 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:00\u001b[0m\n",
18
+ "\u001b[?25hCollecting einops\n",
19
+ " Downloading einops-0.7.0-py3-none-any.whl.metadata (13 kB)\n",
20
+ "Collecting datasets\n",
21
+ " Downloading datasets-2.16.1-py3-none-any.whl.metadata (20 kB)\n",
22
+ "Collecting peft\n",
23
+ " Downloading peft-0.8.2-py3-none-any.whl.metadata (25 kB)\n",
24
+ "Collecting bitsandbytes\n",
25
+ " Downloading bitsandbytes-0.42.0-py3-none-any.whl.metadata (9.9 kB)\n",
26
+ "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/site-packages (from accelerate) (1.26.4)\n",
27
+ "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/site-packages (from accelerate) (23.2)\n",
28
+ "Requirement already satisfied: psutil in /usr/local/lib/python3.11/site-packages (from accelerate) (5.9.8)\n",
29
+ "Requirement already satisfied: pyyaml in /usr/local/lib/python3.11/site-packages (from accelerate) (6.0.1)\n",
30
+ "Collecting torch>=1.10.0 (from accelerate)\n",
31
+ " Downloading torch-2.2.0-cp311-cp311-manylinux1_x86_64.whl.metadata (25 kB)\n",
32
+ "Collecting huggingface-hub (from accelerate)\n",
33
+ " Downloading huggingface_hub-0.20.3-py3-none-any.whl.metadata (12 kB)\n",
34
+ "Collecting safetensors>=0.3.1 (from accelerate)\n",
35
+ " Downloading safetensors-0.4.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.8 kB)\n",
36
+ "Collecting filelock (from transformers)\n",
37
+ " Downloading filelock-3.13.1-py3-none-any.whl.metadata (2.8 kB)\n",
38
+ "Collecting regex!=2019.12.17 (from transformers)\n",
39
+ " Downloading regex-2023.12.25-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (40 kB)\n",
40
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.9/40.9 kB\u001b[0m \u001b[31m121.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
41
+ "\u001b[?25hRequirement already satisfied: requests in /usr/local/lib/python3.11/site-packages (from transformers) (2.31.0)\n",
42
+ "Collecting tokenizers<0.19,>=0.14 (from transformers)\n",
43
+ " Downloading tokenizers-0.15.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n",
44
+ "Collecting tqdm>=4.27 (from transformers)\n",
45
+ " Downloading tqdm-4.66.1-py3-none-any.whl.metadata (57 kB)\n",
46
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.6/57.6 kB\u001b[0m \u001b[31m47.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
47
+ "\u001b[?25hCollecting pyarrow>=8.0.0 (from datasets)\n",
48
+ " Downloading pyarrow-15.0.0-cp311-cp311-manylinux_2_28_x86_64.whl.metadata (3.0 kB)\n",
49
+ "Collecting pyarrow-hotfix (from datasets)\n",
50
+ " Downloading pyarrow_hotfix-0.6-py3-none-any.whl.metadata (3.6 kB)\n",
51
+ "Collecting dill<0.3.8,>=0.3.0 (from datasets)\n",
52
+ " Downloading dill-0.3.7-py3-none-any.whl.metadata (9.9 kB)\n",
53
+ "Collecting pandas (from datasets)\n",
54
+ " Downloading pandas-2.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (19 kB)\n",
55
+ "Collecting xxhash (from datasets)\n",
56
+ " Downloading xxhash-3.4.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n",
57
+ "Collecting multiprocess (from datasets)\n",
58
+ " Downloading multiprocess-0.70.16-py311-none-any.whl.metadata (7.2 kB)\n",
59
+ "Collecting fsspec<=2023.10.0,>=2023.1.0 (from fsspec[http]<=2023.10.0,>=2023.1.0->datasets)\n",
60
+ " Downloading fsspec-2023.10.0-py3-none-any.whl.metadata (6.8 kB)\n",
61
+ "Requirement already satisfied: aiohttp in /usr/local/lib/python3.11/site-packages (from datasets) (3.8.3)\n",
62
+ "Collecting scipy (from bitsandbytes)\n",
63
+ " Downloading scipy-1.12.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (60 kB)\n",
64
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.4/60.4 kB\u001b[0m \u001b[31m54.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
65
+ "\u001b[?25hRequirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (23.2.0)\n",
66
+ "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (2.1.1)\n",
67
+ "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (6.0.5)\n",
68
+ "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (4.0.3)\n",
69
+ "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (1.9.4)\n",
70
+ "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (1.4.1)\n",
71
+ "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (1.3.1)\n",
72
+ "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/site-packages (from huggingface-hub->accelerate) (4.9.0)\n",
73
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/site-packages (from requests->transformers) (3.6)\n",
74
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/site-packages (from requests->transformers) (2.2.0)\n",
75
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/site-packages (from requests->transformers) (2024.2.2)\n",
76
+ "Collecting sympy (from torch>=1.10.0->accelerate)\n",
77
+ " Downloading sympy-1.12-py3-none-any.whl (5.7 MB)\n",
78
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.7/5.7 MB\u001b[0m \u001b[31m32.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
79
+ "\u001b[?25hCollecting networkx (from torch>=1.10.0->accelerate)\n",
80
+ " Downloading networkx-3.2.1-py3-none-any.whl.metadata (5.2 kB)\n",
81
+ "Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/site-packages (from torch>=1.10.0->accelerate) (3.1.3)\n",
82
+ "Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch>=1.10.0->accelerate)\n",
83
+ " Downloading nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n",
84
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m23.7/23.7 MB\u001b[0m \u001b[31m61.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
85
+ "\u001b[?25hCollecting nvidia-cuda-runtime-cu12==12.1.105 (from torch>=1.10.0->accelerate)\n",
86
+ " Downloading nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n",
87
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m823.6/823.6 kB\u001b[0m \u001b[31m93.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
88
+ "\u001b[?25hCollecting nvidia-cuda-cupti-cu12==12.1.105 (from torch>=1.10.0->accelerate)\n",
89
+ " Downloading nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n",
90
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m14.1/14.1 MB\u001b[0m \u001b[31m44.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
91
+ "\u001b[?25hCollecting nvidia-cudnn-cu12==8.9.2.26 (from torch>=1.10.0->accelerate)\n",
92
+ " Downloading nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
93
+ "Collecting nvidia-cublas-cu12==12.1.3.1 (from torch>=1.10.0->accelerate)\n",
94
+ " Downloading nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n",
95
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m410.6/410.6 MB\u001b[0m \u001b[31m59.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
96
+ "\u001b[?25hCollecting nvidia-cufft-cu12==11.0.2.54 (from torch>=1.10.0->accelerate)\n",
97
+ " Downloading nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n",
98
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m121.6/121.6 MB\u001b[0m \u001b[31m59.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
99
+ "\u001b[?25hCollecting nvidia-curand-cu12==10.3.2.106 (from torch>=1.10.0->accelerate)\n",
100
+ " Downloading nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n",
101
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.5/56.5 MB\u001b[0m \u001b[31m60.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
102
+ "\u001b[?25hCollecting nvidia-cusolver-cu12==11.4.5.107 (from torch>=1.10.0->accelerate)\n",
103
+ " Downloading nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n",
104
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m124.2/124.2 MB\u001b[0m \u001b[31m50.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
105
+ "\u001b[?25hCollecting nvidia-cusparse-cu12==12.1.0.106 (from torch>=1.10.0->accelerate)\n",
106
+ " Downloading nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n",
107
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.0/196.0 MB\u001b[0m \u001b[31m40.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
108
+ "\u001b[?25hCollecting nvidia-nccl-cu12==2.19.3 (from torch>=1.10.0->accelerate)\n",
109
+ " Downloading nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl.metadata (1.8 kB)\n",
110
+ "Collecting nvidia-nvtx-cu12==12.1.105 (from torch>=1.10.0->accelerate)\n",
111
+ " Downloading nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n",
112
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m99.1/99.1 kB\u001b[0m \u001b[31m60.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
113
+ "\u001b[?25hCollecting triton==2.2.0 (from torch>=1.10.0->accelerate)\n",
114
+ " Downloading triton-2.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.4 kB)\n",
115
+ "Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.10.0->accelerate)\n",
116
+ " Downloading nvidia_nvjitlink_cu12-12.3.101-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n",
117
+ "INFO: pip is looking at multiple versions of multiprocess to determine which version is compatible with other requirements. This could take a while.\n",
118
+ "Collecting multiprocess (from datasets)\n",
119
+ " Downloading multiprocess-0.70.15-py311-none-any.whl.metadata (7.2 kB)\n",
120
+ "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/site-packages (from pandas->datasets) (2.8.2)\n",
121
+ "Collecting pytz>=2020.1 (from pandas->datasets)\n",
122
+ " Downloading pytz-2024.1-py2.py3-none-any.whl.metadata (22 kB)\n",
123
+ "Collecting tzdata>=2022.7 (from pandas->datasets)\n",
124
+ " Downloading tzdata-2023.4-py2.py3-none-any.whl.metadata (1.4 kB)\n",
125
+ "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/site-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)\n",
126
+ "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/site-packages (from jinja2->torch>=1.10.0->accelerate) (2.1.5)\n",
127
+ "Collecting mpmath>=0.19 (from sympy->torch>=1.10.0->accelerate)\n",
128
+ " Downloading mpmath-1.3.0-py3-none-any.whl (536 kB)\n",
129
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m536.2/536.2 kB\u001b[0m \u001b[31m73.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
130
+ "\u001b[?25hDownloading accelerate-0.26.1-py3-none-any.whl (270 kB)\n",
131
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m270.9/270.9 kB\u001b[0m \u001b[31m105.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
132
+ "\u001b[?25hDownloading transformers-4.37.2-py3-none-any.whl (8.4 MB)\n",
133
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.4/8.4 MB\u001b[0m \u001b[31m41.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
134
+ "\u001b[?25hDownloading einops-0.7.0-py3-none-any.whl (44 kB)\n",
135
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.6/44.6 kB\u001b[0m \u001b[31m139.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
136
+ "\u001b[?25hDownloading datasets-2.16.1-py3-none-any.whl (507 kB)\n",
137
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m507.1/507.1 kB\u001b[0m \u001b[31m77.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
138
+ "\u001b[?25hDownloading peft-0.8.2-py3-none-any.whl (183 kB)\n",
139
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m183.4/183.4 kB\u001b[0m \u001b[31m101.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
140
+ "\u001b[?25hDownloading bitsandbytes-0.42.0-py3-none-any.whl (105.0 MB)\n",
141
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m105.0/105.0 MB\u001b[0m \u001b[31m33.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
142
+ "\u001b[?25hDownloading dill-0.3.7-py3-none-any.whl (115 kB)\n",
143
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.3/115.3 kB\u001b[0m \u001b[31m97.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
144
+ "\u001b[?25hDownloading fsspec-2023.10.0-py3-none-any.whl (166 kB)\n",
145
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m166.4/166.4 kB\u001b[0m \u001b[31m197.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
146
+ "\u001b[?25hDownloading huggingface_hub-0.20.3-py3-none-any.whl (330 kB)\n",
147
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m330.1/330.1 kB\u001b[0m \u001b[31m52.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
148
+ "\u001b[?25hDownloading pyarrow-15.0.0-cp311-cp311-manylinux_2_28_x86_64.whl (38.3 MB)\n",
149
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.3/38.3 MB\u001b[0m \u001b[31m33.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
150
+ "\u001b[?25hDownloading regex-2023.12.25-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (785 kB)\n",
151
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m785.1/785.1 kB\u001b[0m \u001b[31m50.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
152
+ "\u001b[?25hDownloading safetensors-0.4.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
153
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m38.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
154
+ "\u001b[?25hDownloading tokenizers-0.15.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.6 MB)\n",
155
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m36.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
156
+ "\u001b[?25hDownloading torch-2.2.0-cp311-cp311-manylinux1_x86_64.whl (755.5 MB)\n",
157
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m755.5/755.5 MB\u001b[0m \u001b[31m10.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m0:03\u001b[0mm\n",
158
+ "\u001b[?25hDownloading nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n",
159
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m731.7/731.7 MB\u001b[0m \u001b[31m28.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
160
+ "\u001b[?25hDownloading nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl (166.0 MB)\n",
161
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m166.0/166.0 MB\u001b[0m \u001b[31m33.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
162
+ "\u001b[?25hDownloading triton-2.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (167.9 MB)\n",
163
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m167.9/167.9 MB\u001b[0m \u001b[31m26.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
164
+ "\u001b[?25hDownloading tqdm-4.66.1-py3-none-any.whl (78 kB)\n",
165
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m78.3/78.3 kB\u001b[0m \u001b[31m77.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
166
+ "\u001b[?25hDownloading filelock-3.13.1-py3-none-any.whl (11 kB)\n",
167
+ "Downloading multiprocess-0.70.15-py311-none-any.whl (135 kB)\n",
168
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m135.4/135.4 kB\u001b[0m \u001b[31m77.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
169
+ "\u001b[?25hDownloading pandas-2.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (13.0 MB)\n",
170
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.0/13.0 MB\u001b[0m \u001b[31m28.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
171
+ "\u001b[?25hDownloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\n",
172
+ "Downloading scipy-1.12.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (38.4 MB)\n",
173
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.4/38.4 MB\u001b[0m \u001b[31m28.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
174
+ "\u001b[?25hDownloading xxhash-3.4.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n",
175
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.8/194.8 kB\u001b[0m \u001b[31m92.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
176
+ "\u001b[?25hDownloading pytz-2024.1-py2.py3-none-any.whl (505 kB)\n",
177
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m505.5/505.5 kB\u001b[0m \u001b[31m49.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
178
+ "\u001b[?25hDownloading tzdata-2023.4-py2.py3-none-any.whl (346 kB)\n",
179
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m346.6/346.6 kB\u001b[0m \u001b[31m100.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
180
+ "\u001b[?25hDownloading networkx-3.2.1-py3-none-any.whl (1.6 MB)\n",
181
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m34.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
182
+ "\u001b[?25hDownloading nvidia_nvjitlink_cu12-12.3.101-py3-none-manylinux1_x86_64.whl (20.5 MB)\n",
183
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m20.5/20.5 MB\u001b[0m \u001b[31m22.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
184
+ "\u001b[?25hInstalling collected packages: pytz, mpmath, xxhash, tzdata, tqdm, sympy, scipy, safetensors, regex, pyarrow-hotfix, pyarrow, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, networkx, fsspec, filelock, einops, dill, triton, pandas, nvidia-cusparse-cu12, nvidia-cudnn-cu12, multiprocess, huggingface-hub, bitsandbytes, tokenizers, nvidia-cusolver-cu12, transformers, torch, datasets, accelerate, peft\n",
185
+ "Successfully installed accelerate-0.26.1 bitsandbytes-0.42.0 datasets-2.16.1 dill-0.3.7 einops-0.7.0 filelock-3.13.1 fsspec-2023.10.0 huggingface-hub-0.20.3 mpmath-1.3.0 multiprocess-0.70.15 networkx-3.2.1 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.19.3 nvidia-nvjitlink-cu12-12.3.101 nvidia-nvtx-cu12-12.1.105 pandas-2.2.0 peft-0.8.2 pyarrow-15.0.0 pyarrow-hotfix-0.6 pytz-2024.1 regex-2023.12.25 safetensors-0.4.2 scipy-1.12.0 sympy-1.12 tokenizers-0.15.1 torch-2.2.0 tqdm-4.66.1 transformers-4.37.2 triton-2.2.0 tzdata-2023.4 xxhash-3.4.1\n"
186
+ ]
187
+ }
188
+ ],
189
+ "source": [
190
+ "!pip install accelerate transformers einops datasets peft bitsandbytes"
191
+ ]
192
+ },
193
+ {
194
+ "cell_type": "code",
195
+ "execution_count": 2,
196
+ "id": "46a53303-b585-4b02-956f-4af173410e25",
197
+ "metadata": {},
198
+ "outputs": [
199
+ {
200
+ "name": "stderr",
201
+ "output_type": "stream",
202
+ "text": [
203
+ "/usr/local/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
204
+ " from .autonotebook import tqdm as notebook_tqdm\n"
205
+ ]
206
+ }
207
+ ],
208
+ "source": [
209
+ "import torch\n",
210
+ "from datasets import load_dataset, Dataset\n",
211
+ "from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments, Trainer, DataCollatorForLanguageModeling, BitsAndBytesConfig\n",
212
+ "from peft import LoraConfig, get_peft_model\n",
213
+ "import os"
214
+ ]
215
+ },
216
+ {
217
+ "cell_type": "code",
218
+ "execution_count": 3,
219
+ "id": "ffa3ee11-3929-4032-8758-322cda3a912e",
220
+ "metadata": {},
221
+ "outputs": [
222
+ {
223
+ "name": "stderr",
224
+ "output_type": "stream",
225
+ "text": [
226
+ "tokenizer_config.json: 100%|██████████| 7.34k/7.34k [00:00<00:00, 13.7MB/s]\n",
227
+ "vocab.json: 100%|██████████| 798k/798k [00:00<00:00, 17.5MB/s]\n",
228
+ "merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 43.7MB/s]\n",
229
+ "tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 16.5MB/s]\n",
230
+ "added_tokens.json: 100%|██████████| 1.08k/1.08k [00:00<00:00, 2.35MB/s]\n",
231
+ "special_tokens_map.json: 100%|██████████| 99.0/99.0 [00:00<00:00, 269kB/s]\n",
232
+ "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
233
+ ]
234
+ }
235
+ ],
236
+ "source": [
237
+ "tokenizer = AutoTokenizer.from_pretrained(\"microsoft/phi-2\", trust_remote_code=True)\n",
238
+ "tokenizer.pad_token = tokenizer.eos_token"
239
+ ]
240
+ },
241
+ {
242
+ "cell_type": "code",
243
+ "execution_count": 4,
244
+ "id": "b17096e6-c633-4d88-8cfc-fb738c1e4ca0",
245
+ "metadata": {
246
+ "scrolled": true
247
+ },
248
+ "outputs": [
249
+ {
250
+ "name": "stderr",
251
+ "output_type": "stream",
252
+ "text": [
253
+ "config.json: 100%|██████████| 863/863 [00:00<00:00, 2.00MB/s]\n",
254
+ "configuration_phi.py: 100%|██████████| 9.26k/9.26k [00:00<00:00, 11.4MB/s]\n",
255
+ "A new version of the following files was downloaded from https://huggingface.co/microsoft/phi-2:\n",
256
+ "- configuration_phi.py\n",
257
+ ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n",
258
+ "modeling_phi.py: 100%|██████████| 62.7k/62.7k [00:00<00:00, 48.8MB/s]\n",
259
+ "A new version of the following files was downloaded from https://huggingface.co/microsoft/phi-2:\n",
260
+ "- modeling_phi.py\n",
261
+ ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n",
262
+ "model.safetensors.index.json: 100%|██████████| 35.7k/35.7k [00:00<00:00, 33.7MB/s]\n",
263
+ "Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]\n",
264
+ "model-00001-of-00002.safetensors: 0%| | 0.00/5.00G [00:00<?, ?B/s]\u001b[A\n",
265
+ "model-00001-of-00002.safetensors: 0%| | 10.5M/5.00G [00:00<00:55, 90.4MB/s]\u001b[A\n",
266
+ "model-00001-of-00002.safetensors: 1%| | 31.5M/5.00G [00:00<00:41, 119MB/s] \u001b[A\n",
267
+ "model-00001-of-00002.safetensors: 1%| | 52.4M/5.00G [00:00<00:37, 133MB/s]\u001b[A\n",
268
+ "model-00001-of-00002.safetensors: 1%|▏ | 73.4M/5.00G [00:00<00:35, 140MB/s]\u001b[A\n",
269
+ "model-00001-of-00002.safetensors: 2%|▏ | 94.4M/5.00G [00:00<00:34, 143MB/s]\u001b[A\n",
270
+ "model-00001-of-00002.safetensors: 2%|▏ | 115M/5.00G [00:00<00:33, 146MB/s] \u001b[A\n",
271
+ "model-00001-of-00002.safetensors: 3%|▎ | 136M/5.00G [00:00<00:34, 142MB/s]\u001b[A\n",
272
+ "model-00001-of-00002.safetensors: 3%|▎ | 157M/5.00G [00:01<00:35, 135MB/s]\u001b[A\n",
273
+ "model-00001-of-00002.safetensors: 4%|▎ | 178M/5.00G [00:01<00:35, 136MB/s]\u001b[A\n",
274
+ "model-00001-of-00002.safetensors: 4%|▍ | 199M/5.00G [00:01<00:35, 135MB/s]\u001b[A\n",
275
+ "model-00001-of-00002.safetensors: 4%|▍ | 220M/5.00G [00:01<00:35, 136MB/s]\u001b[A\n",
276
+ "model-00001-of-00002.safetensors: 5%|▍ | 241M/5.00G [00:01<00:34, 136MB/s]\u001b[A\n",
277
+ "model-00001-of-00002.safetensors: 5%|▌ | 262M/5.00G [00:01<00:34, 135MB/s]\u001b[A\n",
278
+ "model-00001-of-00002.safetensors: 6%|▌ | 283M/5.00G [00:02<00:37, 124MB/s]\u001b[A\n",
279
+ "model-00001-of-00002.safetensors: 6%|▌ | 304M/5.00G [00:02<00:37, 127MB/s]\u001b[A\n",
280
+ "model-00001-of-00002.safetensors: 7%|▋ | 325M/5.00G [00:02<00:36, 129MB/s]\u001b[A\n",
281
+ "model-00001-of-00002.safetensors: 7%|▋ | 346M/5.00G [00:02<00:35, 133MB/s]\u001b[A\n",
282
+ "model-00001-of-00002.safetensors: 7%|▋ | 367M/5.00G [00:02<00:34, 135MB/s]\u001b[A\n",
283
+ "model-00001-of-00002.safetensors: 8%|▊ | 388M/5.00G [00:02<00:33, 139MB/s]\u001b[A\n",
284
+ "model-00001-of-00002.safetensors: 8%|▊ | 409M/5.00G [00:03<00:32, 141MB/s]\u001b[A\n",
285
+ "model-00001-of-00002.safetensors: 9%|▊ | 430M/5.00G [00:03<00:32, 139MB/s]\u001b[A\n",
286
+ "model-00001-of-00002.safetensors: 9%|▉ | 451M/5.00G [00:03<00:32, 138MB/s]\u001b[A\n",
287
+ "model-00001-of-00002.safetensors: 9%|▉ | 472M/5.00G [00:03<00:33, 136MB/s]\u001b[A\n",
288
+ "model-00001-of-00002.safetensors: 10%|▉ | 493M/5.00G [00:03<00:32, 138MB/s]\u001b[A\n",
289
+ "model-00001-of-00002.safetensors: 10%|█ | 514M/5.00G [00:03<00:31, 140MB/s]\u001b[A\n",
290
+ "model-00001-of-00002.safetensors: 11%|█ | 535M/5.00G [00:03<00:31, 140MB/s]\u001b[A\n",
291
+ "model-00001-of-00002.safetensors: 11%|█ | 556M/5.00G [00:04<00:31, 140MB/s]\u001b[A\n",
292
+ "model-00001-of-00002.safetensors: 12%|█▏ | 577M/5.00G [00:04<00:31, 138MB/s]\u001b[A\n",
293
+ "model-00001-of-00002.safetensors: 12%|█▏ | 598M/5.00G [00:04<00:31, 137MB/s]\u001b[A\n",
294
+ "model-00001-of-00002.safetensors: 12%|█▏ | 619M/5.00G [00:04<00:31, 139MB/s]\u001b[A\n",
295
+ "model-00001-of-00002.safetensors: 13%|█▎ | 640M/5.00G [00:04<00:32, 136MB/s]\u001b[A\n",
296
+ "model-00001-of-00002.safetensors: 13%|█▎ | 661M/5.00G [00:04<00:31, 139MB/s]\u001b[A\n",
297
+ "model-00001-of-00002.safetensors: 14%|█▎ | 682M/5.00G [00:05<00:31, 138MB/s]\u001b[A\n",
298
+ "model-00001-of-00002.safetensors: 14%|█▍ | 703M/5.00G [00:05<00:32, 131MB/s]\u001b[A\n",
299
+ "model-00001-of-00002.safetensors: 14%|█▍ | 724M/5.00G [00:05<00:32, 132MB/s]\u001b[A\n",
300
+ "model-00001-of-00002.safetensors: 15%|█▍ | 744M/5.00G [00:05<00:31, 135MB/s]\u001b[A\n",
301
+ "model-00001-of-00002.safetensors: 15%|█▌ | 765M/5.00G [00:05<00:31, 136MB/s]\u001b[A\n",
302
+ "model-00001-of-00002.safetensors: 16%|█▌ | 786M/5.00G [00:05<00:31, 133MB/s]\u001b[A\n",
303
+ "model-00001-of-00002.safetensors: 16%|█▌ | 807M/5.00G [00:05<00:31, 135MB/s]\u001b[A\n",
304
+ "model-00001-of-00002.safetensors: 17%|█▋ | 828M/5.00G [00:06<00:30, 138MB/s]\u001b[A\n",
305
+ "model-00001-of-00002.safetensors: 17%|█▋ | 849M/5.00G [00:06<00:31, 133MB/s]\u001b[A\n",
306
+ "model-00001-of-00002.safetensors: 17%|█▋ | 870M/5.00G [00:06<00:30, 136MB/s]\u001b[A\n",
307
+ "model-00001-of-00002.safetensors: 18%|█▊ | 891M/5.00G [00:06<00:29, 138MB/s]\u001b[A\n",
308
+ "model-00001-of-00002.safetensors: 18%|█▊ | 912M/5.00G [00:06<00:29, 139MB/s]\u001b[A\n",
309
+ "model-00001-of-00002.safetensors: 19%|█▊ | 933M/5.00G [00:06<00:28, 141MB/s]\u001b[A\n",
310
+ "model-00001-of-00002.safetensors: 19%|█▉ | 954M/5.00G [00:07<00:28, 140MB/s]\u001b[A\n",
311
+ "model-00001-of-00002.safetensors: 20%|█▉ | 975M/5.00G [00:07<00:29, 136MB/s]\u001b[A\n",
312
+ "model-00001-of-00002.safetensors: 20%|█▉ | 996M/5.00G [00:07<00:29, 136MB/s]\u001b[A\n",
313
+ "model-00001-of-00002.safetensors: 20%|██ | 1.02G/5.00G [00:07<00:28, 139MB/s]\u001b[A\n",
314
+ "model-00001-of-00002.safetensors: 21%|██ | 1.04G/5.00G [00:07<00:29, 134MB/s]\u001b[A\n",
315
+ "model-00001-of-00002.safetensors: 21%|██ | 1.06G/5.00G [00:07<00:29, 135MB/s]\u001b[A\n",
316
+ "model-00001-of-00002.safetensors: 22%|██▏ | 1.08G/5.00G [00:07<00:29, 135MB/s]\u001b[A\n",
317
+ "model-00001-of-00002.safetensors: 22%|██▏ | 1.10G/5.00G [00:08<00:29, 132MB/s]\u001b[A\n",
318
+ "model-00001-of-00002.safetensors: 22%|██▏ | 1.12G/5.00G [00:08<00:30, 129MB/s]\u001b[A\n",
319
+ "model-00001-of-00002.safetensors: 23%|██▎ | 1.14G/5.00G [00:08<00:29, 133MB/s]\u001b[A\n",
320
+ "model-00001-of-00002.safetensors: 23%|██▎ | 1.16G/5.00G [00:08<00:29, 131MB/s]\u001b[A\n",
321
+ "model-00001-of-00002.safetensors: 24%|██▎ | 1.18G/5.00G [00:08<00:28, 133MB/s]\u001b[A\n",
322
+ "model-00001-of-00002.safetensors: 24%|██▍ | 1.21G/5.00G [00:08<00:27, 136MB/s]\u001b[A\n",
323
+ "model-00001-of-00002.safetensors: 25%|██▍ | 1.23G/5.00G [00:09<00:27, 137MB/s]\u001b[A\n",
324
+ "model-00001-of-00002.safetensors: 25%|██▍ | 1.25G/5.00G [00:09<00:27, 136MB/s]\u001b[A\n",
325
+ "model-00001-of-00002.safetensors: 25%|██▌ | 1.27G/5.00G [00:09<00:27, 136MB/s]\u001b[A\n",
326
+ "model-00001-of-00002.safetensors: 26%|██▌ | 1.29G/5.00G [00:09<00:26, 138MB/s]\u001b[A\n",
327
+ "model-00001-of-00002.safetensors: 26%|██▌ | 1.31G/5.00G [00:09<00:27, 136MB/s]\u001b[A\n",
328
+ "model-00001-of-00002.safetensors: 27%|██▋ | 1.33G/5.00G [00:09<00:26, 137MB/s]\u001b[A\n",
329
+ "model-00001-of-00002.safetensors: 27%|██▋ | 1.35G/5.00G [00:09<00:26, 135MB/s]\u001b[A\n",
330
+ "model-00001-of-00002.safetensors: 27%|██▋ | 1.37G/5.00G [00:10<00:26, 135MB/s]\u001b[A\n",
331
+ "model-00001-of-00002.safetensors: 28%|██▊ | 1.39G/5.00G [00:10<00:29, 124MB/s]\u001b[A\n",
332
+ "model-00001-of-00002.safetensors: 28%|██▊ | 1.42G/5.00G [00:10<00:28, 124MB/s]\u001b[A\n",
333
+ "model-00001-of-00002.safetensors: 29%|██▉ | 1.44G/5.00G [00:10<00:27, 130MB/s]\u001b[A\n",
334
+ "model-00001-of-00002.safetensors: 29%|██▉ | 1.46G/5.00G [00:10<00:26, 133MB/s]\u001b[A\n",
335
+ "model-00001-of-00002.safetensors: 30%|██▉ | 1.48G/5.00G [00:10<00:26, 134MB/s]\u001b[A\n",
336
+ "model-00001-of-00002.safetensors: 30%|███ | 1.50G/5.00G [00:11<00:25, 136MB/s]\u001b[A\n",
337
+ "model-00001-of-00002.safetensors: 30%|███ | 1.52G/5.00G [00:11<00:25, 138MB/s]\u001b[A\n",
338
+ "model-00001-of-00002.safetensors: 31%|███ | 1.54G/5.00G [00:11<00:25, 135MB/s]\u001b[A\n",
339
+ "model-00001-of-00002.safetensors: 31%|███▏ | 1.56G/5.00G [00:11<00:25, 137MB/s]\u001b[A\n",
340
+ "model-00001-of-00002.safetensors: 32%|███▏ | 1.58G/5.00G [00:11<00:24, 141MB/s]\u001b[A\n",
341
+ "model-00001-of-00002.safetensors: 32%|███▏ | 1.60G/5.00G [00:11<00:23, 142MB/s]\u001b[A\n",
342
+ "model-00001-of-00002.safetensors: 33%|███▎ | 1.63G/5.00G [00:11<00:23, 142MB/s]\u001b[A\n",
343
+ "model-00001-of-00002.safetensors: 33%|███▎ | 1.65G/5.00G [00:12<00:34, 97.8MB/s]\u001b[A\n",
344
+ "model-00001-of-00002.safetensors: 33%|███▎ | 1.67G/5.00G [00:12<00:31, 107MB/s] \u001b[A\n",
345
+ "model-00001-of-00002.safetensors: 34%|███▍ | 1.69G/5.00G [00:12<00:28, 114MB/s]\u001b[A\n",
346
+ "model-00001-of-00002.safetensors: 34%|███▍ | 1.71G/5.00G [00:12<00:27, 120MB/s]\u001b[A\n",
347
+ "model-00001-of-00002.safetensors: 35%|███▍ | 1.73G/5.00G [00:12<00:26, 124MB/s]\u001b[A\n",
348
+ "model-00001-of-00002.safetensors: 35%|███▌ | 1.75G/5.00G [00:13<00:26, 125MB/s]\u001b[A\n",
349
+ "model-00001-of-00002.safetensors: 35%|███▌ | 1.77G/5.00G [00:13<00:25, 127MB/s]\u001b[A\n",
350
+ "model-00001-of-00002.safetensors: 36%|███▌ | 1.79G/5.00G [00:13<00:25, 126MB/s]\u001b[A\n",
351
+ "model-00001-of-00002.safetensors: 36%|███▋ | 1.81G/5.00G [00:13<00:25, 124MB/s]\u001b[A\n",
352
+ "model-00001-of-00002.safetensors: 37%|███▋ | 1.84G/5.00G [00:13<00:24, 128MB/s]\u001b[A\n",
353
+ "model-00001-of-00002.safetensors: 37%|███▋ | 1.86G/5.00G [00:13<00:24, 129MB/s]\u001b[A\n",
354
+ "model-00001-of-00002.safetensors: 38%|███▊ | 1.88G/5.00G [00:14<00:23, 132MB/s]\u001b[A\n",
355
+ "model-00001-of-00002.safetensors: 38%|███▊ | 1.90G/5.00G [00:14<00:22, 135MB/s]\u001b[A\n",
356
+ "model-00001-of-00002.safetensors: 38%|███▊ | 1.92G/5.00G [00:14<00:23, 134MB/s]\u001b[A\n",
357
+ "model-00001-of-00002.safetensors: 39%|███▉ | 1.94G/5.00G [00:14<00:22, 135MB/s]\u001b[A\n",
358
+ "model-00001-of-00002.safetensors: 39%|███▉ | 1.96G/5.00G [00:14<00:22, 136MB/s]\u001b[A\n",
359
+ "model-00001-of-00002.safetensors: 40%|███▉ | 1.98G/5.00G [00:14<00:22, 132MB/s]\u001b[A\n",
360
+ "model-00001-of-00002.safetensors: 40%|████ | 2.00G/5.00G [00:15<00:22, 134MB/s]\u001b[A\n",
361
+ "model-00001-of-00002.safetensors: 41%|████ | 2.02G/5.00G [00:15<00:22, 132MB/s]\u001b[A\n",
362
+ "model-00001-of-00002.safetensors: 41%|████ | 2.04G/5.00G [00:15<00:22, 133MB/s]\u001b[A\n",
363
+ "model-00001-of-00002.safetensors: 41%|████▏ | 2.07G/5.00G [00:15<00:22, 133MB/s]\u001b[A\n",
364
+ "model-00001-of-00002.safetensors: 42%|████▏ | 2.09G/5.00G [00:15<00:22, 130MB/s]\u001b[A\n",
365
+ "model-00001-of-00002.safetensors: 42%|████▏ | 2.11G/5.00G [00:15<00:21, 132MB/s]\u001b[A\n",
366
+ "model-00001-of-00002.safetensors: 43%|████▎ | 2.13G/5.00G [00:15<00:21, 135MB/s]\u001b[A\n",
367
+ "model-00001-of-00002.safetensors: 43%|████▎ | 2.15G/5.00G [00:16<00:20, 136MB/s]\u001b[A\n",
368
+ "model-00001-of-00002.safetensors: 43%|████▎ | 2.17G/5.00G [00:16<00:20, 138MB/s]\u001b[A\n",
369
+ "model-00001-of-00002.safetensors: 44%|████▍ | 2.19G/5.00G [00:16<00:20, 137MB/s]\u001b[A\n",
370
+ "model-00001-of-00002.safetensors: 44%|████▍ | 2.21G/5.00G [00:16<00:20, 134MB/s]\u001b[A\n",
371
+ "model-00001-of-00002.safetensors: 45%|████▍ | 2.23G/5.00G [00:16<00:20, 135MB/s]\u001b[A\n",
372
+ "model-00001-of-00002.safetensors: 45%|████▌ | 2.25G/5.00G [00:16<00:19, 138MB/s]\u001b[A\n",
373
+ "model-00001-of-00002.safetensors: 46%|████▌ | 2.28G/5.00G [00:17<00:19, 139MB/s]\u001b[A\n",
374
+ "model-00001-of-00002.safetensors: 46%|████▌ | 2.30G/5.00G [00:17<00:19, 139MB/s]\u001b[A\n",
375
+ "model-00001-of-00002.safetensors: 46%|████▋ | 2.32G/5.00G [00:17<00:19, 137MB/s]\u001b[A\n",
376
+ "model-00001-of-00002.safetensors: 47%|████▋ | 2.34G/5.00G [00:17<00:20, 131MB/s]\u001b[A\n",
377
+ "model-00001-of-00002.safetensors: 47%|████▋ | 2.36G/5.00G [00:17<00:19, 134MB/s]\u001b[A\n",
378
+ "model-00001-of-00002.safetensors: 48%|████▊ | 2.38G/5.00G [00:17<00:20, 130MB/s]\u001b[A\n",
379
+ "model-00001-of-00002.safetensors: 48%|████▊ | 2.40G/5.00G [00:18<00:20, 128MB/s]\u001b[A\n",
380
+ "model-00001-of-00002.safetensors: 48%|████▊ | 2.42G/5.00G [00:18<00:19, 129MB/s]\u001b[A\n",
381
+ "model-00001-of-00002.safetensors: 49%|████▉ | 2.44G/5.00G [00:18<00:19, 128MB/s]\u001b[A\n",
382
+ "model-00001-of-00002.safetensors: 49%|████▉ | 2.46G/5.00G [00:18<00:19, 131MB/s]\u001b[A\n",
383
+ "model-00001-of-00002.safetensors: 50%|████▉ | 2.49G/5.00G [00:18<00:18, 133MB/s]\u001b[A\n",
384
+ "model-00001-of-00002.safetensors: 50%|█████ | 2.51G/5.00G [00:18<00:18, 131MB/s]\u001b[A\n",
385
+ "model-00001-of-00002.safetensors: 51%|█████ | 2.53G/5.00G [00:18<00:18, 135MB/s]\u001b[A\n",
386
+ "model-00001-of-00002.safetensors: 51%|█████ | 2.55G/5.00G [00:19<00:17, 136MB/s]\u001b[A\n",
387
+ "model-00001-of-00002.safetensors: 51%|█████▏ | 2.57G/5.00G [00:19<00:18, 134MB/s]\u001b[A\n",
388
+ "model-00001-of-00002.safetensors: 52%|█████▏ | 2.59G/5.00G [00:19<00:17, 135MB/s]\u001b[A\n",
389
+ "model-00001-of-00002.safetensors: 52%|█████▏ | 2.61G/5.00G [00:19<00:20, 116MB/s]\u001b[A\n",
390
+ "model-00001-of-00002.safetensors: 53%|█████▎ | 2.63G/5.00G [00:19<00:20, 117MB/s]\u001b[A\n",
391
+ "model-00001-of-00002.safetensors: 53%|█████▎ | 2.65G/5.00G [00:19<00:19, 122MB/s]\u001b[A\n",
392
+ "model-00001-of-00002.safetensors: 54%|█████▎ | 2.67G/5.00G [00:20<00:18, 127MB/s]\u001b[A\n",
393
+ "model-00001-of-00002.safetensors: 54%|█████▍ | 2.69G/5.00G [00:20<00:18, 126MB/s]\u001b[A\n",
394
+ "model-00001-of-00002.safetensors: 54%|█████▍ | 2.72G/5.00G [00:20<00:17, 129MB/s]\u001b[A\n",
395
+ "model-00001-of-00002.safetensors: 55%|█████▍ | 2.74G/5.00G [00:20<00:20, 109MB/s]\u001b[A\n",
396
+ "model-00001-of-00002.safetensors: 55%|█████▌ | 2.76G/5.00G [00:20<00:19, 113MB/s]\u001b[A\n",
397
+ "model-00001-of-00002.safetensors: 56%|█████▌ | 2.78G/5.00G [00:21<00:18, 120MB/s]\u001b[A\n",
398
+ "model-00001-of-00002.safetensors: 56%|█████▌ | 2.80G/5.00G [00:21<00:17, 124MB/s]\u001b[A\n",
399
+ "model-00001-of-00002.safetensors: 56%|█████▋ | 2.82G/5.00G [00:21<00:17, 128MB/s]\u001b[A\n",
400
+ "model-00001-of-00002.safetensors: 57%|█████▋ | 2.84G/5.00G [00:21<00:16, 127MB/s]\u001b[A\n",
401
+ "model-00001-of-00002.safetensors: 57%|█████▋ | 2.86G/5.00G [00:21<00:21, 97.7MB/s]\u001b[A\n",
402
+ "model-00001-of-00002.safetensors: 58%|█████▊ | 2.88G/5.00G [00:22<00:19, 107MB/s] \u001b[A\n",
403
+ "model-00001-of-00002.safetensors: 58%|█████▊ | 2.90G/5.00G [00:22<00:18, 116MB/s]\u001b[A\n",
404
+ "model-00001-of-00002.safetensors: 59%|█████▊ | 2.93G/5.00G [00:22<00:16, 122MB/s]\u001b[A\n",
405
+ "model-00001-of-00002.safetensors: 59%|█████▉ | 2.95G/5.00G [00:22<00:16, 122MB/s]\u001b[A\n",
406
+ "model-00001-of-00002.safetensors: 59%|█████▉ | 2.97G/5.00G [00:22<00:16, 120MB/s]\u001b[A\n",
407
+ "model-00001-of-00002.safetensors: 60%|█████▉ | 2.99G/5.00G [00:22<00:16, 125MB/s]\u001b[A\n",
408
+ "model-00001-of-00002.safetensors: 60%|██████ | 3.01G/5.00G [00:22<00:15, 126MB/s]\u001b[A\n",
409
+ "model-00001-of-00002.safetensors: 61%|██████ | 3.03G/5.00G [00:23<00:15, 128MB/s]\u001b[A\n",
410
+ "model-00001-of-00002.safetensors: 61%|██████ | 3.05G/5.00G [00:23<00:14, 130MB/s]\u001b[A\n",
411
+ "model-00001-of-00002.safetensors: 62%|██████▏ | 3.07G/5.00G [00:23<00:14, 129MB/s]\u001b[A\n",
412
+ "model-00001-of-00002.safetensors: 62%|██████▏ | 3.09G/5.00G [00:23<00:15, 126MB/s]\u001b[A\n",
413
+ "model-00001-of-00002.safetensors: 62%|██████▏ | 3.11G/5.00G [00:23<00:14, 131MB/s]\u001b[A\n",
414
+ "model-00001-of-00002.safetensors: 63%|██████▎ | 3.14G/5.00G [00:23<00:14, 125MB/s]\u001b[A\n",
415
+ "model-00001-of-00002.safetensors: 63%|██████▎ | 3.16G/5.00G [00:24<00:14, 128MB/s]\u001b[A\n",
416
+ "model-00001-of-00002.safetensors: 64%|██████▎ | 3.18G/5.00G [00:24<00:13, 131MB/s]\u001b[A\n",
417
+ "model-00001-of-00002.safetensors: 64%|██████▍ | 3.20G/5.00G [00:24<00:13, 130MB/s]\u001b[A\n",
418
+ "model-00001-of-00002.safetensors: 64%|██████▍ | 3.22G/5.00G [00:24<00:13, 130MB/s]\u001b[A\n",
419
+ "model-00001-of-00002.safetensors: 65%|██████▍ | 3.24G/5.00G [00:24<00:13, 132MB/s]\u001b[A\n",
420
+ "model-00001-of-00002.safetensors: 65%|██████▌ | 3.26G/5.00G [00:24<00:13, 129MB/s]\u001b[A\n",
421
+ "model-00001-of-00002.safetensors: 66%|██████▌ | 3.28G/5.00G [00:25<00:12, 132MB/s]\u001b[A\n",
422
+ "model-00001-of-00002.safetensors: 66%|██████▌ | 3.30G/5.00G [00:25<00:12, 133MB/s]\u001b[A\n",
423
+ "model-00001-of-00002.safetensors: 67%|██████▋ | 3.32G/5.00G [00:25<00:12, 130MB/s]\u001b[A\n",
424
+ "model-00001-of-00002.safetensors: 67%|██████▋ | 3.34G/5.00G [00:25<00:12, 130MB/s]\u001b[A\n",
425
+ "model-00001-of-00002.safetensors: 67%|██████▋ | 3.37G/5.00G [00:25<00:12, 132MB/s]\u001b[A\n",
426
+ "model-00001-of-00002.safetensors: 68%|██████▊ | 3.39G/5.00G [00:25<00:12, 130MB/s]\u001b[A\n",
427
+ "model-00001-of-00002.safetensors: 68%|██████▊ | 3.41G/5.00G [00:26<00:12, 132MB/s]\u001b[A\n",
428
+ "model-00001-of-00002.safetensors: 69%|██████▊ | 3.43G/5.00G [00:26<00:11, 133MB/s]\u001b[A\n",
429
+ "model-00001-of-00002.safetensors: 69%|██████▉ | 3.45G/5.00G [00:26<00:11, 132MB/s]\u001b[A\n",
430
+ "model-00001-of-00002.safetensors: 69%|██████▉ | 3.47G/5.00G [00:26<00:11, 132MB/s]\u001b[A\n",
431
+ "model-00001-of-00002.safetensors: 70%|██████▉ | 3.49G/5.00G [00:26<00:11, 130MB/s]\u001b[A\n",
432
+ "model-00001-of-00002.safetensors: 70%|███████ | 3.51G/5.00G [00:26<00:11, 129MB/s]\u001b[A\n",
433
+ "model-00001-of-00002.safetensors: 71%|███████ | 3.53G/5.00G [00:26<00:11, 131MB/s]\u001b[A\n",
434
+ "model-00001-of-00002.safetensors: 71%|███████ | 3.55G/5.00G [00:27<00:10, 135MB/s]\u001b[A\n",
435
+ "model-00001-of-00002.safetensors: 72%|███████▏ | 3.58G/5.00G [00:27<00:10, 133MB/s]\u001b[A\n",
436
+ "model-00001-of-00002.safetensors: 72%|███████▏ | 3.60G/5.00G [00:27<00:10, 132MB/s]\u001b[A\n",
437
+ "model-00001-of-00002.safetensors: 72%|███████▏ | 3.62G/5.00G [00:27<00:10, 130MB/s]\u001b[A\n",
438
+ "model-00001-of-00002.safetensors: 73%|███████▎ | 3.64G/5.00G [00:27<00:10, 124MB/s]\u001b[A\n",
439
+ "model-00001-of-00002.safetensors: 73%|███████▎ | 3.66G/5.00G [00:27<00:11, 121MB/s]\u001b[A\n",
440
+ "model-00001-of-00002.safetensors: 74%|███████▎ | 3.68G/5.00G [00:28<00:10, 125MB/s]\u001b[A\n",
441
+ "model-00001-of-00002.safetensors: 74%|███████▍ | 3.70G/5.00G [00:28<00:09, 130MB/s]\u001b[A\n",
442
+ "model-00001-of-00002.safetensors: 75%|███████▍ | 3.72G/5.00G [00:28<00:09, 133MB/s]\u001b[A\n",
443
+ "model-00001-of-00002.safetensors: 75%|███████▍ | 3.74G/5.00G [00:28<00:10, 125MB/s]\u001b[A\n",
444
+ "model-00001-of-00002.safetensors: 75%|███████▌ | 3.76G/5.00G [00:28<00:09, 125MB/s]\u001b[A\n",
445
+ "model-00001-of-00002.safetensors: 76%|███████▌ | 3.79G/5.00G [00:28<00:09, 126MB/s]\u001b[A\n",
446
+ "model-00001-of-00002.safetensors: 76%|███████▌ | 3.81G/5.00G [00:29<00:09, 122MB/s]\u001b[A\n",
447
+ "model-00001-of-00002.safetensors: 77%|███████▋ | 3.83G/5.00G [00:29<00:09, 130MB/s]\u001b[A\n",
448
+ "model-00001-of-00002.safetensors: 77%|███████▋ | 3.85G/5.00G [00:29<00:08, 132MB/s]\u001b[A\n",
449
+ "model-00001-of-00002.safetensors: 77%|███████▋ | 3.87G/5.00G [00:29<00:12, 88.9MB/s]\u001b[A\n",
450
+ "model-00001-of-00002.safetensors: 78%|███████▊ | 3.89G/5.00G [00:30<00:11, 98.1MB/s]\u001b[A\n",
451
+ "model-00001-of-00002.safetensors: 78%|███████▊ | 3.91G/5.00G [00:30<00:10, 105MB/s] \u001b[A\n",
452
+ "model-00001-of-00002.safetensors: 79%|███████▊ | 3.93G/5.00G [00:30<00:09, 112MB/s]\u001b[A\n",
453
+ "model-00001-of-00002.safetensors: 79%|███████▉ | 3.95G/5.00G [00:30<00:08, 119MB/s]\u001b[A\n",
454
+ "model-00001-of-00002.safetensors: 80%|███████▉ | 3.97G/5.00G [00:30<00:08, 122MB/s]\u001b[A\n",
455
+ "model-00001-of-00002.safetensors: 80%|███████▉ | 4.00G/5.00G [00:30<00:08, 115MB/s]\u001b[A\n",
456
+ "model-00001-of-00002.safetensors: 80%|████████ | 4.02G/5.00G [00:31<00:08, 114MB/s]\u001b[A\n",
457
+ "model-00001-of-00002.safetensors: 81%|████████ | 4.04G/5.00G [00:31<00:08, 116MB/s]\u001b[A\n",
458
+ "model-00001-of-00002.safetensors: 81%|████████ | 4.06G/5.00G [00:31<00:08, 117MB/s]\u001b[A\n",
459
+ "model-00001-of-00002.safetensors: 82%|████████▏ | 4.08G/5.00G [00:31<00:07, 120MB/s]\u001b[A\n",
460
+ "model-00001-of-00002.safetensors: 82%|████████▏ | 4.10G/5.00G [00:31<00:07, 122MB/s]\u001b[A\n",
461
+ "model-00001-of-00002.safetensors: 82%|████████▏ | 4.12G/5.00G [00:31<00:07, 118MB/s]\u001b[A\n",
462
+ "model-00001-of-00002.safetensors: 83%|████████▎ | 4.14G/5.00G [00:32<00:07, 119MB/s]\u001b[A\n",
463
+ "model-00001-of-00002.safetensors: 83%|████████▎ | 4.16G/5.00G [00:32<00:06, 120MB/s]\u001b[A\n",
464
+ "model-00001-of-00002.safetensors: 84%|████████▍ | 4.18G/5.00G [00:32<00:06, 119MB/s]\u001b[A\n",
465
+ "model-00001-of-00002.safetensors: 84%|████████▍ | 4.20G/5.00G [00:32<00:06, 121MB/s]\u001b[A\n",
466
+ "model-00001-of-00002.safetensors: 85%|████████▍ | 4.23G/5.00G [00:32<00:06, 122MB/s]\u001b[A\n",
467
+ "model-00001-of-00002.safetensors: 85%|████████▌ | 4.25G/5.00G [00:32<00:06, 123MB/s]\u001b[A\n",
468
+ "model-00001-of-00002.safetensors: 85%|████████▌ | 4.27G/5.00G [00:33<00:05, 129MB/s]\u001b[A\n",
469
+ "model-00001-of-00002.safetensors: 86%|████████▌ | 4.29G/5.00G [00:33<00:05, 132MB/s]\u001b[A\n",
470
+ "model-00001-of-00002.safetensors: 86%|████████▋ | 4.31G/5.00G [00:33<00:05, 131MB/s]\u001b[A\n",
471
+ "model-00001-of-00002.safetensors: 87%|████████▋ | 4.33G/5.00G [00:33<00:04, 135MB/s]\u001b[A\n",
472
+ "model-00001-of-00002.safetensors: 87%|████████▋ | 4.35G/5.00G [00:33<00:04, 134MB/s]\u001b[A\n",
473
+ "model-00001-of-00002.safetensors: 88%|████████▊ | 4.37G/5.00G [00:33<00:05, 125MB/s]\u001b[A\n",
474
+ "model-00001-of-00002.safetensors: 88%|████████▊ | 4.39G/5.00G [00:34<00:04, 128MB/s]\u001b[A\n",
475
+ "model-00001-of-00002.safetensors: 88%|████████▊ | 4.41G/5.00G [00:34<00:04, 130MB/s]\u001b[A\n",
476
+ "model-00001-of-00002.safetensors: 89%|████████▉ | 4.44G/5.00G [00:34<00:04, 129MB/s]\u001b[A\n",
477
+ "model-00001-of-00002.safetensors: 89%|████████▉ | 4.46G/5.00G [00:34<00:04, 132MB/s]\u001b[A\n",
478
+ "model-00001-of-00002.safetensors: 90%|████████▉ | 4.48G/5.00G [00:34<00:03, 136MB/s]\u001b[A\n",
479
+ "model-00001-of-00002.safetensors: 90%|█████████ | 4.50G/5.00G [00:34<00:03, 135MB/s]\u001b[A\n",
480
+ "model-00001-of-00002.safetensors: 90%|█████████ | 4.52G/5.00G [00:34<00:03, 138MB/s]\u001b[A\n",
481
+ "model-00001-of-00002.safetensors: 91%|█████████ | 4.54G/5.00G [00:35<00:03, 140MB/s]\u001b[A\n",
482
+ "model-00001-of-00002.safetensors: 91%|█████████▏| 4.56G/5.00G [00:35<00:03, 136MB/s]\u001b[A\n",
483
+ "model-00001-of-00002.safetensors: 92%|█████████▏| 4.58G/5.00G [00:35<00:03, 137MB/s]\u001b[A\n",
484
+ "model-00001-of-00002.safetensors: 92%|█████████▏| 4.60G/5.00G [00:35<00:02, 138MB/s]\u001b[A\n",
485
+ "model-00001-of-00002.safetensors: 93%|█████████▎| 4.62G/5.00G [00:35<00:02, 135MB/s]\u001b[A\n",
486
+ "model-00001-of-00002.safetensors: 93%|█████████▎| 4.65G/5.00G [00:35<00:02, 137MB/s]\u001b[A\n",
487
+ "model-00001-of-00002.safetensors: 93%|█████████▎| 4.67G/5.00G [00:36<00:02, 137MB/s]\u001b[A\n",
488
+ "model-00001-of-00002.safetensors: 94%|█████████▍| 4.69G/5.00G [00:36<00:02, 135MB/s]\u001b[A\n",
489
+ "model-00001-of-00002.safetensors: 94%|█████████▍| 4.71G/5.00G [00:36<00:02, 136MB/s]\u001b[A\n",
490
+ "model-00001-of-00002.safetensors: 95%|█████████▍| 4.73G/5.00G [00:36<00:01, 134MB/s]\u001b[A\n",
491
+ "model-00001-of-00002.safetensors: 95%|█████████▌| 4.75G/5.00G [00:36<00:01, 130MB/s]\u001b[A\n",
492
+ "model-00001-of-00002.safetensors: 96%|█████████▌| 4.77G/5.00G [00:36<00:01, 131MB/s]\u001b[A\n",
493
+ "model-00001-of-00002.safetensors: 96%|█████████▌| 4.79G/5.00G [00:37<00:01, 132MB/s]\u001b[A\n",
494
+ "model-00001-of-00002.safetensors: 96%|█████████▋| 4.81G/5.00G [00:37<00:01, 132MB/s]\u001b[A\n",
495
+ "model-00001-of-00002.safetensors: 97%|█████████▋| 4.83G/5.00G [00:37<00:01, 136MB/s]\u001b[A\n",
496
+ "model-00001-of-00002.safetensors: 97%|█████████▋| 4.85G/5.00G [00:37<00:01, 138MB/s]\u001b[A\n",
497
+ "model-00001-of-00002.safetensors: 98%|█████████▊| 4.88G/5.00G [00:37<00:00, 135MB/s]\u001b[A\n",
498
+ "model-00001-of-00002.safetensors: 98%|█████████▊| 4.90G/5.00G [00:37<00:00, 138MB/s]\u001b[A\n",
499
+ "model-00001-of-00002.safetensors: 98%|█████████▊| 4.92G/5.00G [00:37<00:00, 139MB/s]\u001b[A\n",
500
+ "model-00001-of-00002.safetensors: 99%|█████████▉| 4.94G/5.00G [00:38<00:00, 140MB/s]\u001b[A\n",
501
+ "model-00001-of-00002.safetensors: 99%|█████████▉| 4.96G/5.00G [00:38<00:00, 142MB/s]\u001b[A\n",
502
+ "model-00001-of-00002.safetensors: 100%|█████████▉| 4.98G/5.00G [00:38<00:00, 137MB/s]\u001b[A\n",
503
+ "model-00001-of-00002.safetensors: 100%|██████████| 5.00G/5.00G [00:38<00:00, 130MB/s]\u001b[A\n",
504
+ "Downloading shards: 50%|█████ | 1/2 [00:38<00:38, 38.64s/it]\n",
505
+ "model-00002-of-00002.safetensors: 0%| | 0.00/564M [00:00<?, ?B/s]\u001b[A\n",
506
+ "model-00002-of-00002.safetensors: 4%|▎ | 21.0M/564M [00:00<00:03, 150MB/s]\u001b[A\n",
507
+ "model-00002-of-00002.safetensors: 7%|▋ | 41.9M/564M [00:00<00:03, 143MB/s]\u001b[A\n",
508
+ "model-00002-of-00002.safetensors: 11%|█ | 62.9M/564M [00:00<00:03, 126MB/s]\u001b[A\n",
509
+ "model-00002-of-00002.safetensors: 15%|█▍ | 83.9M/564M [00:00<00:03, 130MB/s]\u001b[A\n",
510
+ "model-00002-of-00002.safetensors: 19%|█▊ | 105M/564M [00:00<00:03, 129MB/s] \u001b[A\n",
511
+ "model-00002-of-00002.safetensors: 22%|██▏ | 126M/564M [00:00<00:03, 133MB/s]\u001b[A\n",
512
+ "model-00002-of-00002.safetensors: 26%|██▌ | 147M/564M [00:01<00:03, 134MB/s]\u001b[A\n",
513
+ "model-00002-of-00002.safetensors: 30%|██▉ | 168M/564M [00:01<00:02, 135MB/s]\u001b[A\n",
514
+ "model-00002-of-00002.safetensors: 33%|███▎ | 189M/564M [00:01<00:02, 128MB/s]\u001b[A\n",
515
+ "model-00002-of-00002.safetensors: 37%|███▋ | 210M/564M [00:01<00:02, 131MB/s]\u001b[A\n",
516
+ "model-00002-of-00002.safetensors: 41%|████ | 231M/564M [00:01<00:02, 131MB/s]\u001b[A\n",
517
+ "model-00002-of-00002.safetensors: 45%|████▍ | 252M/564M [00:01<00:02, 131MB/s]\u001b[A\n",
518
+ "model-00002-of-00002.safetensors: 48%|████▊ | 273M/564M [00:02<00:02, 133MB/s]\u001b[A\n",
519
+ "model-00002-of-00002.safetensors: 52%|█████▏ | 294M/564M [00:02<00:02, 133MB/s]\u001b[A\n",
520
+ "model-00002-of-00002.safetensors: 56%|█████▌ | 315M/564M [00:02<00:01, 136MB/s]\u001b[A\n",
521
+ "model-00002-of-00002.safetensors: 60%|█████▉ | 336M/564M [00:02<00:01, 135MB/s]\u001b[A\n",
522
+ "model-00002-of-00002.safetensors: 63%|██████▎ | 357M/564M [00:02<00:01, 134MB/s]\u001b[A\n",
523
+ "model-00002-of-00002.safetensors: 67%|██████▋ | 377M/564M [00:02<00:01, 134MB/s]\u001b[A\n",
524
+ "model-00002-of-00002.safetensors: 71%|███████ | 398M/564M [00:02<00:01, 137MB/s]\u001b[A\n",
525
+ "model-00002-of-00002.safetensors: 74%|███████▍ | 419M/564M [00:03<00:01, 136MB/s]\u001b[A\n",
526
+ "model-00002-of-00002.safetensors: 78%|███████▊ | 440M/564M [00:03<00:00, 136MB/s]\u001b[A\n",
527
+ "model-00002-of-00002.safetensors: 82%|████████▏ | 461M/564M [00:03<00:01, 95.4MB/s]\u001b[A\n",
528
+ "model-00002-of-00002.safetensors: 86%|████████▌ | 482M/564M [00:03<00:00, 103MB/s] \u001b[A\n",
529
+ "model-00002-of-00002.safetensors: 89%|████████▉ | 503M/564M [00:04<00:00, 109MB/s]\u001b[A\n",
530
+ "model-00002-of-00002.safetensors: 93%|█████████▎| 524M/564M [00:04<00:00, 116MB/s]\u001b[A\n",
531
+ "model-00002-of-00002.safetensors: 97%|█████████▋| 545M/564M [00:04<00:00, 120MB/s]\u001b[A\n",
532
+ "model-00002-of-00002.safetensors: 100%|██████████| 564M/564M [00:04<00:00, 126MB/s]\u001b[A\n",
533
+ "Downloading shards: 100%|██████████| 2/2 [00:43<00:00, 21.61s/it]\n",
534
+ "Loading checkpoint shards: 100%|██████████| 2/2 [00:08<00:00, 4.06s/it]\n",
535
+ "generation_config.json: 100%|██████████| 124/124 [00:00<00:00, 278kB/s]\n"
536
+ ]
537
+ }
538
+ ],
539
+ "source": [
540
+ "bnb_config = BitsAndBytesConfig(\n",
541
+ " load_in_4bit=True,\n",
542
+ " bnb_4bit_use_double_quant=True,\n",
543
+ " bnb_4bit_quant_type=\"nf4\",\n",
544
+ " bnb_4bit_compute_dtype=torch.float16\n",
545
+ ")\n",
546
+ "\n",
547
+ "model = AutoModelForCausalLM.from_pretrained(\n",
548
+ " \"microsoft/phi-2\",\n",
549
+ " device_map={\"\":0},\n",
550
+ " trust_remote_code=True,\n",
551
+ " quantization_config=bnb_config\n",
552
+ ")"
553
+ ]
554
+ },
555
+ {
556
+ "cell_type": "code",
557
+ "execution_count": 5,
558
+ "id": "e15aa794-e17c-4b09-a64a-c60377259218",
559
+ "metadata": {},
560
+ "outputs": [
561
+ {
562
+ "name": "stdout",
563
+ "output_type": "stream",
564
+ "text": [
565
+ "PhiForCausalLM(\n",
566
+ " (model): PhiModel(\n",
567
+ " (embed_tokens): Embedding(51200, 2560)\n",
568
+ " (embed_dropout): Dropout(p=0.0, inplace=False)\n",
569
+ " (layers): ModuleList(\n",
570
+ " (0-31): 32 x PhiDecoderLayer(\n",
571
+ " (self_attn): PhiAttention(\n",
572
+ " (q_proj): Linear4bit(in_features=2560, out_features=2560, bias=True)\n",
573
+ " (k_proj): Linear4bit(in_features=2560, out_features=2560, bias=True)\n",
574
+ " (v_proj): Linear4bit(in_features=2560, out_features=2560, bias=True)\n",
575
+ " (dense): Linear4bit(in_features=2560, out_features=2560, bias=True)\n",
576
+ " (rotary_emb): PhiRotaryEmbedding()\n",
577
+ " )\n",
578
+ " (mlp): PhiMLP(\n",
579
+ " (activation_fn): NewGELUActivation()\n",
580
+ " (fc1): Linear4bit(in_features=2560, out_features=10240, bias=True)\n",
581
+ " (fc2): Linear4bit(in_features=10240, out_features=2560, bias=True)\n",
582
+ " )\n",
583
+ " (input_layernorm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True)\n",
584
+ " (resid_dropout): Dropout(p=0.1, inplace=False)\n",
585
+ " )\n",
586
+ " )\n",
587
+ " (final_layernorm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True)\n",
588
+ " )\n",
589
+ " (lm_head): Linear(in_features=2560, out_features=51200, bias=True)\n",
590
+ ")\n"
591
+ ]
592
+ }
593
+ ],
594
+ "source": [
595
+ "print(model)"
596
+ ]
597
+ },
598
+ {
599
+ "cell_type": "code",
600
+ "execution_count": 6,
601
+ "id": "18d5599f-992d-4d8e-a90c-4d43774be473",
602
+ "metadata": {},
603
+ "outputs": [
604
+ {
605
+ "name": "stdout",
606
+ "output_type": "stream",
607
+ "text": [
608
+ "trainable params: 17,039,360 || all params: 2,796,723,200 || trainable%: 0.6092615815537269\n"
609
+ ]
610
+ }
611
+ ],
612
+ "source": [
613
+ "config = LoraConfig(\n",
614
+ " r=16,\n",
615
+ " lora_alpha=16,\n",
616
+ " target_modules=[\"dense\", \"fc2\",\"q_proj\",\"k_proj\",\"v_proj\"],\n",
617
+ " lora_dropout=0.05,\n",
618
+ " bias=\"none\",\n",
619
+ " task_type=\"CAUSAL_LM\"\n",
620
+ ")\n",
621
+ "\n",
622
+ "model = get_peft_model(model, config)\n",
623
+ "model.print_trainable_parameters()"
624
+ ]
625
+ },
626
+ {
627
+ "cell_type": "code",
628
+ "execution_count": 7,
629
+ "id": "baeee903-3dce-48b2-93c3-7a697d8c6daf",
630
+ "metadata": {},
631
+ "outputs": [],
632
+ "source": [
633
+ "def tokenize(sample):\n",
634
+ " model_inps = tokenizer(sample[\"text\"], padding=True, truncation=True, max_length=512)\n",
635
+ " return model_inps"
636
+ ]
637
+ },
638
+ {
639
+ "cell_type": "code",
640
+ "execution_count": 8,
641
+ "id": "28a9b24a-a822-4fcb-96b3-d77b7ea30a5f",
642
+ "metadata": {},
643
+ "outputs": [
644
+ {
645
+ "name": "stdout",
646
+ "output_type": "stream",
647
+ "text": [
648
+ "Collecting scikit-learn\n",
649
+ " Downloading scikit_learn-1.4.0-1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (11 kB)\n",
650
+ "Requirement already satisfied: numpy<2.0,>=1.19.5 in /usr/local/lib/python3.11/site-packages (from scikit-learn) (1.26.4)\n",
651
+ "Requirement already satisfied: scipy>=1.6.0 in /usr/local/lib/python3.11/site-packages (from scikit-learn) (1.12.0)\n",
652
+ "Collecting joblib>=1.2.0 (from scikit-learn)\n",
653
+ " Downloading joblib-1.3.2-py3-none-any.whl.metadata (5.4 kB)\n",
654
+ "Collecting threadpoolctl>=2.0.0 (from scikit-learn)\n",
655
+ " Downloading threadpoolctl-3.2.0-py3-none-any.whl.metadata (10.0 kB)\n",
656
+ "Downloading scikit_learn-1.4.0-1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.1 MB)\n",
657
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.1/12.1 MB\u001b[0m \u001b[31m62.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
658
+ "\u001b[?25hDownloading joblib-1.3.2-py3-none-any.whl (302 kB)\n",
659
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m302.2/302.2 kB\u001b[0m \u001b[31m279.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
660
+ "\u001b[?25hDownloading threadpoolctl-3.2.0-py3-none-any.whl (15 kB)\n",
661
+ "Installing collected packages: threadpoolctl, joblib, scikit-learn\n",
662
+ "Successfully installed joblib-1.3.2 scikit-learn-1.4.0 threadpoolctl-3.2.0\n"
663
+ ]
664
+ }
665
+ ],
666
+ "source": [
667
+ "!pip install scikit-learn"
668
+ ]
669
+ },
670
+ {
671
+ "cell_type": "code",
672
+ "execution_count": 9,
673
+ "id": "1ee7fd2a-38e4-4f23-a978-0bdeeda64d8b",
674
+ "metadata": {},
675
+ "outputs": [],
676
+ "source": [
677
+ "import pandas as pd\n",
678
+ "\n",
679
+ "from sklearn.model_selection import train_test_split\n",
680
+ "dataset_name='data.csv'\n",
681
+ "df = pd.read_csv(dataset_name)\n",
682
+ "train, test = train_test_split(df, test_size=0.2)"
683
+ ]
684
+ },
685
+ {
686
+ "cell_type": "code",
687
+ "execution_count": 10,
688
+ "id": "e84c29e2-843e-42c2-8c0f-324d392e671c",
689
+ "metadata": {},
690
+ "outputs": [
691
+ {
692
+ "name": "stderr",
693
+ "output_type": "stream",
694
+ "text": [
695
+ "Tokenizing data: 100%|██████████| 13129/13129 [00:04<00:00, 2739.65 examples/s]\n"
696
+ ]
697
+ },
698
+ {
699
+ "data": {
700
+ "text/plain": [
701
+ "Dataset({\n",
702
+ " features: ['input_ids', 'attention_mask'],\n",
703
+ " num_rows: 13129\n",
704
+ "})"
705
+ ]
706
+ },
707
+ "execution_count": 10,
708
+ "metadata": {},
709
+ "output_type": "execute_result"
710
+ }
711
+ ],
712
+ "source": [
713
+ "data_df = train\n",
714
+ "data_df[\"text\"] = data_df[[\"user\", \"assistant\"]].apply(lambda x: \"question: \" + str(x[\"user\"]) + \" answer: \" + str(x[\"assistant\"]), axis=1)\n",
715
+ "data = Dataset.from_pandas(data_df)\n",
716
+ "tokenized_data = data.map(tokenize, batched=True, desc=\"Tokenizing data\", remove_columns=data.column_names)\n",
717
+ "tokenized_data"
718
+ ]
719
+ },
720
+ {
721
+ "cell_type": "code",
722
+ "execution_count": 16,
723
+ "id": "ac968254-5338-49df-950d-222b82647407",
724
+ "metadata": {},
725
+ "outputs": [],
726
+ "source": [
727
+ "training_arguments = TrainingArguments(\n",
728
+ " output_dir=\".\",\n",
729
+ " per_device_train_batch_size=4,\n",
730
+ " gradient_accumulation_steps=1,\n",
731
+ " learning_rate=2e-4,\n",
732
+ " lr_scheduler_type=\"cosine\",\n",
733
+ " save_strategy=\"epoch\",\n",
734
+ " logging_steps=100,\n",
735
+ " max_steps=1100,\n",
736
+ " num_train_epochs=2,\n",
737
+ " push_to_hub=True\n",
738
+ " )"
739
+ ]
740
+ },
741
+ {
742
+ "cell_type": "code",
743
+ "execution_count": 12,
744
+ "id": "729df2d0-0890-4ac4-adf3-c167a6e9669d",
745
+ "metadata": {},
746
+ "outputs": [
747
+ {
748
+ "name": "stderr",
749
+ "output_type": "stream",
750
+ "text": [
751
+ "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
752
+ "To disable this warning, you can either:\n",
753
+ "\t- Avoid using `tokenizers` before the fork if possible\n",
754
+ "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
755
+ ]
756
+ },
757
+ {
758
+ "name": "stdout",
759
+ "output_type": "stream",
760
+ "text": [
761
+ "Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.11/site-packages (0.20.3)\n",
762
+ "Requirement already satisfied: filelock in /usr/local/lib/python3.11/site-packages (from huggingface_hub) (3.13.1)\n",
763
+ "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.11/site-packages (from huggingface_hub) (2023.10.0)\n",
764
+ "Requirement already satisfied: requests in /usr/local/lib/python3.11/site-packages (from huggingface_hub) (2.31.0)\n",
765
+ "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.11/site-packages (from huggingface_hub) (4.66.1)\n",
766
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/site-packages (from huggingface_hub) (6.0.1)\n",
767
+ "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/site-packages (from huggingface_hub) (4.9.0)\n",
768
+ "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.11/site-packages (from huggingface_hub) (23.2)\n",
769
+ "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/site-packages (from requests->huggingface_hub) (2.1.1)\n",
770
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/site-packages (from requests->huggingface_hub) (3.6)\n",
771
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/site-packages (from requests->huggingface_hub) (2.2.0)\n",
772
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/site-packages (from requests->huggingface_hub) (2024.2.2)\n"
773
+ ]
774
+ }
775
+ ],
776
+ "source": [
777
+ "!pip install huggingface_hub"
778
+ ]
779
+ },
780
+ {
781
+ "cell_type": "code",
782
+ "execution_count": 13,
783
+ "id": "525f81a4-eb92-466e-bb9c-cd63122231ab",
784
+ "metadata": {},
785
+ "outputs": [
786
+ {
787
+ "name": "stderr",
788
+ "output_type": "stream",
789
+ "text": [
790
+ "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
791
+ "To disable this warning, you can either:\n",
792
+ "\t- Avoid using `tokenizers` before the fork if possible\n",
793
+ "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
794
+ ]
795
+ },
796
+ {
797
+ "name": "stdout",
798
+ "output_type": "stream",
799
+ "text": [
800
+ "Requirement already satisfied: jupyterlab in /usr/local/lib/python3.11/site-packages (4.1.0)\n",
801
+ "Collecting jupyterlab-git\n",
802
+ " Downloading jupyterlab_git-0.50.0-py3-none-any.whl.metadata (31 kB)\n",
803
+ "Requirement already satisfied: async-lru>=1.0.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (2.0.4)\n",
804
+ "Requirement already satisfied: httpx>=0.25.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (0.26.0)\n",
805
+ "Requirement already satisfied: ipykernel in /usr/local/lib/python3.11/site-packages (from jupyterlab) (6.29.1)\n",
806
+ "Requirement already satisfied: jinja2>=3.0.3 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (3.1.3)\n",
807
+ "Requirement already satisfied: jupyter-core in /usr/local/lib/python3.11/site-packages (from jupyterlab) (5.7.1)\n",
808
+ "Requirement already satisfied: jupyter-lsp>=2.0.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (2.2.2)\n",
809
+ "Requirement already satisfied: jupyter-server<3,>=2.4.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (2.12.5)\n",
810
+ "Requirement already satisfied: jupyterlab-server<3,>=2.19.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (2.25.2)\n",
811
+ "Requirement already satisfied: notebook-shim>=0.2 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (0.2.3)\n",
812
+ "Requirement already satisfied: packaging in /usr/local/lib/python3.11/site-packages (from jupyterlab) (23.2)\n",
813
+ "Requirement already satisfied: tornado>=6.2.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (6.4)\n",
814
+ "Requirement already satisfied: traitlets in /usr/local/lib/python3.11/site-packages (from jupyterlab) (5.14.1)\n",
815
+ "Collecting nbdime~=4.0.1 (from jupyterlab-git)\n",
816
+ " Downloading nbdime-4.0.1-py3-none-any.whl.metadata (9.5 kB)\n",
817
+ "Requirement already satisfied: nbformat in /usr/local/lib/python3.11/site-packages (from jupyterlab-git) (5.9.2)\n",
818
+ "Requirement already satisfied: pexpect in /usr/local/lib/python3.11/site-packages (from jupyterlab-git) (4.9.0)\n",
819
+ "Requirement already satisfied: anyio in /usr/local/lib/python3.11/site-packages (from httpx>=0.25.0->jupyterlab) (4.2.0)\n",
820
+ "Requirement already satisfied: certifi in /usr/local/lib/python3.11/site-packages (from httpx>=0.25.0->jupyterlab) (2024.2.2)\n",
821
+ "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.11/site-packages (from httpx>=0.25.0->jupyterlab) (1.0.2)\n",
822
+ "Requirement already satisfied: idna in /usr/local/lib/python3.11/site-packages (from httpx>=0.25.0->jupyterlab) (3.6)\n",
823
+ "Requirement already satisfied: sniffio in /usr/local/lib/python3.11/site-packages (from httpx>=0.25.0->jupyterlab) (1.3.0)\n",
824
+ "Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.11/site-packages (from httpcore==1.*->httpx>=0.25.0->jupyterlab) (0.14.0)\n",
825
+ "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/site-packages (from jinja2>=3.0.3->jupyterlab) (2.1.5)\n",
826
+ "Requirement already satisfied: argon2-cffi in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (23.1.0)\n",
827
+ "Requirement already satisfied: jupyter-client>=7.4.4 in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (8.6.0)\n",
828
+ "Requirement already satisfied: jupyter-events>=0.9.0 in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (0.9.0)\n",
829
+ "Requirement already satisfied: jupyter-server-terminals in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (0.5.2)\n",
830
+ "Requirement already satisfied: nbconvert>=6.4.4 in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (7.15.0)\n",
831
+ "Requirement already satisfied: overrides in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (7.7.0)\n",
832
+ "Requirement already satisfied: prometheus-client in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (0.19.0)\n",
833
+ "Requirement already satisfied: pyzmq>=24 in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (25.1.2)\n",
834
+ "Requirement already satisfied: send2trash>=1.8.2 in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (1.8.2)\n",
835
+ "Requirement already satisfied: terminado>=0.8.3 in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (0.18.0)\n",
836
+ "Requirement already satisfied: websocket-client in /usr/local/lib/python3.11/site-packages (from jupyter-server<3,>=2.4.0->jupyterlab) (1.7.0)\n",
837
+ "Requirement already satisfied: platformdirs>=2.5 in /usr/local/lib/python3.11/site-packages (from jupyter-core->jupyterlab) (4.2.0)\n",
838
+ "Requirement already satisfied: babel>=2.10 in /usr/local/lib/python3.11/site-packages (from jupyterlab-server<3,>=2.19.0->jupyterlab) (2.14.0)\n",
839
+ "Requirement already satisfied: json5>=0.9.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab-server<3,>=2.19.0->jupyterlab) (0.9.14)\n",
840
+ "Requirement already satisfied: jsonschema>=4.18.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab-server<3,>=2.19.0->jupyterlab) (4.21.1)\n",
841
+ "Requirement already satisfied: requests>=2.31 in /usr/local/lib/python3.11/site-packages (from jupyterlab-server<3,>=2.19.0->jupyterlab) (2.31.0)\n",
842
+ "Collecting colorama (from nbdime~=4.0.1->jupyterlab-git)\n",
843
+ " Downloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)\n",
844
+ "Collecting gitpython!=2.1.4,!=2.1.5,!=2.1.6 (from nbdime~=4.0.1->jupyterlab-git)\n",
845
+ " Downloading GitPython-3.1.41-py3-none-any.whl.metadata (14 kB)\n",
846
+ "Collecting jupyter-server-mathjax>=0.2.2 (from nbdime~=4.0.1->jupyterlab-git)\n",
847
+ " Downloading jupyter_server_mathjax-0.2.6-py3-none-any.whl (3.1 MB)\n",
848
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m18.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
849
+ "\u001b[?25hRequirement already satisfied: pygments in /usr/local/lib/python3.11/site-packages (from nbdime~=4.0.1->jupyterlab-git) (2.17.2)\n",
850
+ "Requirement already satisfied: fastjsonschema in /usr/local/lib/python3.11/site-packages (from nbformat->jupyterlab-git) (2.19.1)\n",
851
+ "Requirement already satisfied: comm>=0.1.1 in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (0.2.1)\n",
852
+ "Requirement already satisfied: debugpy>=1.6.5 in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (1.8.0)\n",
853
+ "Requirement already satisfied: ipython>=7.23.1 in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (8.21.0)\n",
854
+ "Requirement already satisfied: matplotlib-inline>=0.1 in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (0.1.6)\n",
855
+ "Requirement already satisfied: nest-asyncio in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (1.6.0)\n",
856
+ "Requirement already satisfied: psutil in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (5.9.8)\n",
857
+ "Requirement already satisfied: ptyprocess>=0.5 in /usr/local/lib/python3.11/site-packages (from pexpect->jupyterlab-git) (0.7.0)\n",
858
+ "Collecting gitdb<5,>=4.0.1 (from gitpython!=2.1.4,!=2.1.5,!=2.1.6->nbdime~=4.0.1->jupyterlab-git)\n",
859
+ " Downloading gitdb-4.0.11-py3-none-any.whl.metadata (1.2 kB)\n",
860
+ "Requirement already satisfied: decorator in /usr/local/lib/python3.11/site-packages (from ipython>=7.23.1->ipykernel->jupyterlab) (5.1.1)\n",
861
+ "Requirement already satisfied: jedi>=0.16 in /usr/local/lib/python3.11/site-packages (from ipython>=7.23.1->ipykernel->jupyterlab) (0.19.1)\n",
862
+ "Requirement already satisfied: prompt-toolkit<3.1.0,>=3.0.41 in /usr/local/lib/python3.11/site-packages (from ipython>=7.23.1->ipykernel->jupyterlab) (3.0.43)\n",
863
+ "Requirement already satisfied: stack-data in /usr/local/lib/python3.11/site-packages (from ipython>=7.23.1->ipykernel->jupyterlab) (0.6.3)\n",
864
+ "Requirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.11/site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.19.0->jupyterlab) (23.2.0)\n",
865
+ "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.11/site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.19.0->jupyterlab) (2023.12.1)\n",
866
+ "Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.11/site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.19.0->jupyterlab) (0.33.0)\n",
867
+ "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.11/site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.19.0->jupyterlab) (0.17.1)\n",
868
+ "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/site-packages (from jupyter-client>=7.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (2.8.2)\n",
869
+ "Requirement already satisfied: python-json-logger>=2.0.4 in /usr/local/lib/python3.11/site-packages (from jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (2.0.7)\n",
870
+ "Requirement already satisfied: pyyaml>=5.3 in /usr/local/lib/python3.11/site-packages (from jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (6.0.1)\n",
871
+ "Requirement already satisfied: rfc3339-validator in /usr/local/lib/python3.11/site-packages (from jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (0.1.4)\n",
872
+ "Requirement already satisfied: rfc3986-validator>=0.1.1 in /usr/local/lib/python3.11/site-packages (from jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (0.1.1)\n",
873
+ "Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (4.12.3)\n",
874
+ "Requirement already satisfied: bleach!=5.0.0 in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (6.1.0)\n",
875
+ "Requirement already satisfied: defusedxml in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (0.7.1)\n",
876
+ "Requirement already satisfied: jupyterlab-pygments in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (0.3.0)\n",
877
+ "Requirement already satisfied: mistune<4,>=2.0.3 in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (3.0.2)\n",
878
+ "Requirement already satisfied: nbclient>=0.5.0 in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (0.9.0)\n",
879
+ "Requirement already satisfied: pandocfilters>=1.4.1 in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (1.5.1)\n",
880
+ "Requirement already satisfied: tinycss2 in /usr/local/lib/python3.11/site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (1.2.1)\n",
881
+ "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/site-packages (from requests>=2.31->jupyterlab-server<3,>=2.19.0->jupyterlab) (2.1.1)\n",
882
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/site-packages (from requests>=2.31->jupyterlab-server<3,>=2.19.0->jupyterlab) (2.2.0)\n",
883
+ "Requirement already satisfied: argon2-cffi-bindings in /usr/local/lib/python3.11/site-packages (from argon2-cffi->jupyter-server<3,>=2.4.0->jupyterlab) (21.2.0)\n",
884
+ "Requirement already satisfied: six>=1.9.0 in /usr/local/lib/python3.11/site-packages (from bleach!=5.0.0->nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (1.16.0)\n",
885
+ "Requirement already satisfied: webencodings in /usr/local/lib/python3.11/site-packages (from bleach!=5.0.0->nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (0.5.1)\n",
886
+ "Collecting smmap<6,>=3.0.1 (from gitdb<5,>=4.0.1->gitpython!=2.1.4,!=2.1.5,!=2.1.6->nbdime~=4.0.1->jupyterlab-git)\n",
887
+ " Downloading smmap-5.0.1-py3-none-any.whl.metadata (4.3 kB)\n",
888
+ "Requirement already satisfied: parso<0.9.0,>=0.8.3 in /usr/local/lib/python3.11/site-packages (from jedi>=0.16->ipython>=7.23.1->ipykernel->jupyterlab) (0.8.3)\n",
889
+ "Requirement already satisfied: fqdn in /usr/local/lib/python3.11/site-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (1.5.1)\n",
890
+ "Requirement already satisfied: isoduration in /usr/local/lib/python3.11/site-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (20.11.0)\n",
891
+ "Requirement already satisfied: jsonpointer>1.13 in /usr/local/lib/python3.11/site-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (2.4)\n",
892
+ "Requirement already satisfied: uri-template in /usr/local/lib/python3.11/site-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (1.3.0)\n",
893
+ "Requirement already satisfied: webcolors>=1.11 in /usr/local/lib/python3.11/site-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (1.13)\n",
894
+ "Requirement already satisfied: wcwidth in /usr/local/lib/python3.11/site-packages (from prompt-toolkit<3.1.0,>=3.0.41->ipython>=7.23.1->ipykernel->jupyterlab) (0.2.13)\n",
895
+ "Requirement already satisfied: cffi>=1.0.1 in /usr/local/lib/python3.11/site-packages (from argon2-cffi-bindings->argon2-cffi->jupyter-server<3,>=2.4.0->jupyterlab) (1.16.0)\n",
896
+ "Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.11/site-packages (from beautifulsoup4->nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (2.5)\n",
897
+ "Requirement already satisfied: executing>=1.2.0 in /usr/local/lib/python3.11/site-packages (from stack-data->ipython>=7.23.1->ipykernel->jupyterlab) (2.0.1)\n",
898
+ "Requirement already satisfied: asttokens>=2.1.0 in /usr/local/lib/python3.11/site-packages (from stack-data->ipython>=7.23.1->ipykernel->jupyterlab) (2.4.1)\n",
899
+ "Requirement already satisfied: pure-eval in /usr/local/lib/python3.11/site-packages (from stack-data->ipython>=7.23.1->ipykernel->jupyterlab) (0.2.2)\n",
900
+ "Requirement already satisfied: pycparser in /usr/local/lib/python3.11/site-packages (from cffi>=1.0.1->argon2-cffi-bindings->argon2-cffi->jupyter-server<3,>=2.4.0->jupyterlab) (2.21)\n",
901
+ "Requirement already satisfied: arrow>=0.15.0 in /usr/local/lib/python3.11/site-packages (from isoduration->jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (1.3.0)\n",
902
+ "Requirement already satisfied: types-python-dateutil>=2.8.10 in /usr/local/lib/python3.11/site-packages (from arrow>=0.15.0->isoduration->jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (2.8.19.20240106)\n",
903
+ "Downloading jupyterlab_git-0.50.0-py3-none-any.whl (1.2 MB)\n",
904
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m80.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
905
+ "\u001b[?25hDownloading nbdime-4.0.1-py3-none-any.whl (5.9 MB)\n",
906
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.9/5.9 MB\u001b[0m \u001b[31m43.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
907
+ "\u001b[?25hDownloading GitPython-3.1.41-py3-none-any.whl (196 kB)\n",
908
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.4/196.4 kB\u001b[0m \u001b[31m43.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
909
+ "\u001b[?25hDownloading gitdb-4.0.11-py3-none-any.whl (62 kB)\n",
910
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.7/62.7 kB\u001b[0m \u001b[31m132.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
911
+ "\u001b[?25hDownloading smmap-5.0.1-py3-none-any.whl (24 kB)\n",
912
+ "Installing collected packages: smmap, colorama, gitdb, gitpython, jupyter-server-mathjax, nbdime, jupyterlab-git\n",
913
+ "Successfully installed colorama-0.4.6 gitdb-4.0.11 gitpython-3.1.41 jupyter-server-mathjax-0.2.6 jupyterlab-git-0.50.0 nbdime-4.0.1 smmap-5.0.1\n",
914
+ "Note: you may need to restart the kernel to use updated packages.\n"
915
+ ]
916
+ }
917
+ ],
918
+ "source": [
919
+ "pip install --upgrade jupyterlab jupyterlab-git"
920
+ ]
921
+ },
922
+ {
923
+ "cell_type": "code",
924
+ "execution_count": 17,
925
+ "id": "05d58512-a9e2-4319-88bf-9331c6a0584c",
926
+ "metadata": {},
927
+ "outputs": [
928
+ {
929
+ "name": "stdout",
930
+ "output_type": "stream",
931
+ "text": [
932
+ "\n",
933
+ " _| _| _| _| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _|_|_|_| _|_| _|_|_| _|_|_|_|\n",
934
+ " _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|\n",
935
+ " _|_|_|_| _| _| _| _|_| _| _|_| _| _| _| _| _| _|_| _|_|_| _|_|_|_| _| _|_|_|\n",
936
+ " _| _| _| _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|\n",
937
+ " _| _| _|_| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _| _| _| _|_|_| _|_|_|_|\n",
938
+ "\n",
939
+ " A token is already saved on your machine. Run `huggingface-cli whoami` to get more information or `huggingface-cli logout` if you want to log out.\n",
940
+ " Setting a new token will erase the existing one.\n",
941
+ " To login, `huggingface_hub` requires a token generated from https://huggingface.co/settings/tokens .\n"
942
+ ]
943
+ },
944
+ {
945
+ "name": "stdin",
946
+ "output_type": "stream",
947
+ "text": [
948
+ "Token: ········\n",
949
+ "Add token as git credential? (Y/n) n\n"
950
+ ]
951
+ },
952
+ {
953
+ "name": "stdout",
954
+ "output_type": "stream",
955
+ "text": [
956
+ "Token is valid (permission: write).\n",
957
+ "Your token has been saved to /root/.cache/huggingface/token\n",
958
+ "Login successful\n"
959
+ ]
960
+ }
961
+ ],
962
+ "source": [
963
+ "from huggingface_hub import interpreter_login\n",
964
+ "interpreter_login()"
965
+ ]
966
+ },
967
+ {
968
+ "cell_type": "code",
969
+ "execution_count": null,
970
+ "id": "3bf553b6-b26c-49c3-9407-74c8d53a395e",
971
+ "metadata": {},
972
+ "outputs": [
973
+ {
974
+ "name": "stderr",
975
+ "output_type": "stream",
976
+ "text": [
977
+ "Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.\n"
978
+ ]
979
+ },
980
+ {
981
+ "data": {
982
+ "text/html": [
983
+ "\n",
984
+ " <div>\n",
985
+ " \n",
986
+ " <progress value='865' max='1100' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
987
+ " [ 865/1100 06:23 < 01:44, 2.25 it/s, Epoch 0.26/1]\n",
988
+ " </div>\n",
989
+ " <table border=\"1\" class=\"dataframe\">\n",
990
+ " <thead>\n",
991
+ " <tr style=\"text-align: left;\">\n",
992
+ " <th>Step</th>\n",
993
+ " <th>Training Loss</th>\n",
994
+ " </tr>\n",
995
+ " </thead>\n",
996
+ " <tbody>\n",
997
+ " <tr>\n",
998
+ " <td>100</td>\n",
999
+ " <td>1.304900</td>\n",
1000
+ " </tr>\n",
1001
+ " <tr>\n",
1002
+ " <td>200</td>\n",
1003
+ " <td>1.187200</td>\n",
1004
+ " </tr>\n",
1005
+ " <tr>\n",
1006
+ " <td>300</td>\n",
1007
+ " <td>1.169100</td>\n",
1008
+ " </tr>\n",
1009
+ " <tr>\n",
1010
+ " <td>400</td>\n",
1011
+ " <td>1.171700</td>\n",
1012
+ " </tr>\n",
1013
+ " <tr>\n",
1014
+ " <td>500</td>\n",
1015
+ " <td>1.143400</td>\n",
1016
+ " </tr>\n",
1017
+ " <tr>\n",
1018
+ " <td>600</td>\n",
1019
+ " <td>1.191400</td>\n",
1020
+ " </tr>\n",
1021
+ " <tr>\n",
1022
+ " <td>700</td>\n",
1023
+ " <td>1.144800</td>\n",
1024
+ " </tr>\n",
1025
+ " <tr>\n",
1026
+ " <td>800</td>\n",
1027
+ " <td>1.152100</td>\n",
1028
+ " </tr>\n",
1029
+ " </tbody>\n",
1030
+ "</table><p>"
1031
+ ],
1032
+ "text/plain": [
1033
+ "<IPython.core.display.HTML object>"
1034
+ ]
1035
+ },
1036
+ "metadata": {},
1037
+ "output_type": "display_data"
1038
+ }
1039
+ ],
1040
+ "source": [
1041
+ "trainer = Trainer(\n",
1042
+ " model=model,\n",
1043
+ " train_dataset=tokenized_data,\n",
1044
+ " args=training_arguments,\n",
1045
+ " data_collator=DataCollatorForLanguageModeling(tokenizer, mlm=False)\n",
1046
+ ")\n",
1047
+ "trainer.train()"
1048
+ ]
1049
+ },
1050
+ {
1051
+ "cell_type": "code",
1052
+ "execution_count": null,
1053
+ "id": "263cc15e-8e9d-4bd8-9708-ec1638bc1165",
1054
+ "metadata": {},
1055
+ "outputs": [],
1056
+ "source": []
1057
+ }
1058
+ ],
1059
+ "metadata": {
1060
+ "kernelspec": {
1061
+ "display_name": "Python 3 (ipykernel)",
1062
+ "language": "python",
1063
+ "name": "python3"
1064
+ },
1065
+ "language_info": {
1066
+ "codemirror_mode": {
1067
+ "name": "ipython",
1068
+ "version": 3
1069
+ },
1070
+ "file_extension": ".py",
1071
+ "mimetype": "text/x-python",
1072
+ "name": "python",
1073
+ "nbconvert_exporter": "python",
1074
+ "pygments_lexer": "ipython3",
1075
+ "version": "3.11.5"
1076
+ }
1077
+ },
1078
+ "nbformat": 4,
1079
+ "nbformat_minor": 5
1080
+ }
adapter_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "k_proj",
24
+ "fc2",
25
+ "dense",
26
+ "q_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_rslora": false
30
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e022b421528495c48133eddad0f9e9bfabc961fbb1c17e027dfba5889b9e3ec9
3
+ size 68199872
data.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8009c48c3edc7e0ffaaa8c6f5c327aa69cd089184a966e6501a941bb82f2cfd
3
+ size 22246553
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:722353eab13d6007491c6de86f62d8c3e6b74e347e9eb1e04a39128a3d3a15ac
3
+ size 4664