Upload inference.ipynb

inference.ipynb

@@ -0,0 +1,131 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "953dfc98",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from awq import AutoAWQForCausalLM\n",
+    "from transformers import AutoTokenizer, AutoProcessor, TextStreamer\n",
+    "from PIL import Image\n",
+    "import requests\n",
+    "import torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c667ce7b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "quant_path = './llava-v1.6-34b-awq'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6adbf36e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Replacing layers...: 100%|██████████| 60/60 [00:06<00:00,  9.86it/s]\n",
+      "Fusing layers...: 100%|██████████| 60/60 [00:00<00:00, 166.86it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "model = AutoAWQForCausalLM.from_quantized(quant_path, safetensors=True, device_map=\"auto\")\n",
+    "processor = AutoProcessor.from_pretrained(quant_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "d8ab8031",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "url = \"https://github.com/haotian-liu/LLaVA/blob/1a91fc274d7c35a9b50b3cb29c4247ae5837ce39/images/llava_v1_5_radar.jpg?raw=true\"\n",
+    "image = Image.open(requests.get(url, stream=True).raw)\n",
+    "prompt = \"<|im_start|>system\\nAnswer the questions.<|im_end|><|im_start|>user\\n<image>\\nWhat is shown in this image?<|im_end|><|im_start|>assistant\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "350d6426",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "inputs = processor(prompt, image, return_tensors='pt').to(0, torch.float16)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "24c9ac90",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "streamer = TextStreamer(processor)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "74e964aa",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<|im_start|> system\n",
+      "Answer the questions.<|im_end|><|im_start|> user\n",
+      "<image> \n",
+      "What is shown in this image?<|im_end|><|im_start|> assistant\n",
+      "The image shows a radar chart with various data points. The chart is a polar plot with concentric "
+     ]
+    }
+   ],
+   "source": [
+    "generation_output = model.generate(**inputs,max_new_tokens=1024, streamer = streamer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4ae4ca43",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}