{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "6363d4dd-5c18-4652-b682-bf54a468aae5", "metadata": {}, "outputs": [], "source": [ "import torch\n", "from safetensors import safe_open\n", "from safetensors.torch import save_file\n", "\n", "# 加载 safetensors 文件\n", "model_path = \"model.safetensors\"\n", "with safe_open(model_path, framework=\"pt\", device=\"cpu\") as f:\n", " state_dict = {key: f.get_tensor(key) for key in f.keys()}\n", "\n", "# 将 BF16 转换为 FP16\n", "fp16_state_dict = {key: value.to(torch.float16) for key, value in state_dict.items()}\n", "\n", "# 保存为新的 safetensors 文件\n", "output_path = \"model_fp16.safetensors\"\n", "save_file(fp16_state_dict, output_path)" ] }, { "cell_type": "code", "execution_count": 4, "id": "9aa60eaa-883a-465e-958a-3280e0439f66", "metadata": {}, "outputs": [ { "ename": "PackageNotFoundError", "evalue": "No package metadata was found for auto-gptq", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mStopIteration\u001b[0m Traceback (most recent call last)", "File \u001b[0;32m~/miniconda3/lib/python3.12/importlib/metadata/__init__.py:397\u001b[0m, in \u001b[0;36mDistribution.from_name\u001b[0;34m(cls, name)\u001b[0m\n\u001b[1;32m 396\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 397\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mnext\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdiscover\u001b[49m\u001b[43m(\u001b[49m\u001b[43mname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mname\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 398\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m:\n", "\u001b[0;31mStopIteration\u001b[0m: ", "\nDuring handling of the above exception, another exception occurred:\n", "\u001b[0;31mPackageNotFoundError\u001b[0m Traceback (most recent call last)", "Cell \u001b[0;32mIn[4], line 7\u001b[0m\n\u001b[1;32m 4\u001b[0m model_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m./\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 6\u001b[0m \u001b[38;5;66;03m# 加载模型，显式指定 torch_dtype\u001b[39;00m\n\u001b[0;32m----> 7\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[43mAutoModelForCausalLM\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 8\u001b[0m \u001b[43m \u001b[49m\u001b[43mmodel_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 9\u001b[0m \u001b[43m \u001b[49m\u001b[43mtorch_dtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfloat16\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# 或 torch.float16，与权重一致\u001b[39;49;00m\n\u001b[1;32m 10\u001b[0m \u001b[43m \u001b[49m\u001b[43mdevice_map\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mauto\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# 可选，自动分配设备\u001b[39;49;00m\n\u001b[1;32m 11\u001b[0m \u001b[43m)\u001b[49m\n\u001b[1;32m 13\u001b[0m \u001b[38;5;66;03m# 加载分词器\u001b[39;00m\n\u001b[1;32m 14\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m AutoTokenizer\u001b[38;5;241m.\u001b[39mfrom_pretrained(model_path)\n", "File \u001b[0;32m~/miniconda3/lib/python3.12/site-packages/transformers/models/auto/auto_factory.py:564\u001b[0m, in \u001b[0;36m_BaseAutoModelClass.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, *model_args, **kwargs)\u001b[0m\n\u001b[1;32m 562\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mtype\u001b[39m(config) \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_model_mapping\u001b[38;5;241m.\u001b[39mkeys():\n\u001b[1;32m 563\u001b[0m model_class \u001b[38;5;241m=\u001b[39m _get_model_class(config, \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_model_mapping)\n\u001b[0;32m--> 564\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mmodel_class\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 565\u001b[0m \u001b[43m \u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_args\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\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[43mhub_kwargs\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\n\u001b[1;32m 566\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 567\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 568\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUnrecognized configuration class \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mconfig\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m for this kind of AutoModel: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 569\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mModel type should be one of \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m, \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(c\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mfor\u001b[39;00m\u001b[38;5;250m \u001b[39mc\u001b[38;5;250m \u001b[39m\u001b[38;5;129;01min\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_model_mapping\u001b[38;5;241m.\u001b[39mkeys())\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 570\u001b[0m )\n", "File \u001b[0;32m~/miniconda3/lib/python3.12/site-packages/transformers/modeling_utils.py:3669\u001b[0m, in \u001b[0;36mPreTrainedModel.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, weights_only, *model_args, **kwargs)\u001b[0m\n\u001b[1;32m 3666\u001b[0m hf_quantizer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 3668\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m hf_quantizer \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 3669\u001b[0m \u001b[43mhf_quantizer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mvalidate_environment\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 3670\u001b[0m \u001b[43m \u001b[49m\u001b[43mtorch_dtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtorch_dtype\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3671\u001b[0m \u001b[43m \u001b[49m\u001b[43mfrom_tf\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfrom_tf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3672\u001b[0m \u001b[43m \u001b[49m\u001b[43mfrom_flax\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfrom_flax\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3673\u001b[0m \u001b[43m \u001b[49m\u001b[43mdevice_map\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdevice_map\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3674\u001b[0m \u001b[43m \u001b[49m\u001b[43mweights_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mweights_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3675\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 3676\u001b[0m torch_dtype \u001b[38;5;241m=\u001b[39m hf_quantizer\u001b[38;5;241m.\u001b[39mupdate_torch_dtype(torch_dtype)\n\u001b[1;32m 3677\u001b[0m device_map \u001b[38;5;241m=\u001b[39m hf_quantizer\u001b[38;5;241m.\u001b[39mupdate_device_map(device_map)\n", "File \u001b[0;32m~/miniconda3/lib/python3.12/site-packages/transformers/quantizers/quantizer_gptq.py:52\u001b[0m, in \u001b[0;36mGptqHfQuantizer.validate_environment\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 51\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mvalidate_environment\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[0;32m---> 52\u001b[0m gptq_supports_cpu \u001b[38;5;241m=\u001b[39m version\u001b[38;5;241m.\u001b[39mparse(\u001b[43mimportlib\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmetadata\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mversion\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mauto-gptq\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m) \u001b[38;5;241m>\u001b[39m version\u001b[38;5;241m.\u001b[39mparse(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m0.4.2\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 53\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m gptq_supports_cpu \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mcuda\u001b[38;5;241m.\u001b[39mis_available():\n\u001b[1;32m 54\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mGPU is required to quantize or run quantize model.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n", "File \u001b[0;32m~/miniconda3/lib/python3.12/importlib/metadata/__init__.py:889\u001b[0m, in \u001b[0;36mversion\u001b[0;34m(distribution_name)\u001b[0m\n\u001b[1;32m 882\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mversion\u001b[39m(distribution_name):\n\u001b[1;32m 883\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Get the version string for the named package.\u001b[39;00m\n\u001b[1;32m 884\u001b[0m \n\u001b[1;32m 885\u001b[0m \u001b[38;5;124;03m :param distribution_name: The name of the distribution package to query.\u001b[39;00m\n\u001b[1;32m 886\u001b[0m \u001b[38;5;124;03m :return: The version string for the package as defined in the package's\u001b[39;00m\n\u001b[1;32m 887\u001b[0m \u001b[38;5;124;03m \"Version\" metadata key.\u001b[39;00m\n\u001b[1;32m 888\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 889\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mdistribution\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdistribution_name\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39mversion\n", "File \u001b[0;32m~/miniconda3/lib/python3.12/importlib/metadata/__init__.py:862\u001b[0m, in \u001b[0;36mdistribution\u001b[0;34m(distribution_name)\u001b[0m\n\u001b[1;32m 856\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdistribution\u001b[39m(distribution_name):\n\u001b[1;32m 857\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Get the ``Distribution`` instance for the named package.\u001b[39;00m\n\u001b[1;32m 858\u001b[0m \n\u001b[1;32m 859\u001b[0m \u001b[38;5;124;03m :param distribution_name: The name of the distribution package as a string.\u001b[39;00m\n\u001b[1;32m 860\u001b[0m \u001b[38;5;124;03m :return: A ``Distribution`` instance (or subclass thereof).\u001b[39;00m\n\u001b[1;32m 861\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 862\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mDistribution\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_name\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdistribution_name\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/miniconda3/lib/python3.12/importlib/metadata/__init__.py:399\u001b[0m, in \u001b[0;36mDistribution.from_name\u001b[0;34m(cls, name)\u001b[0m\n\u001b[1;32m 397\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mnext\u001b[39m(\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39mdiscover(name\u001b[38;5;241m=\u001b[39mname))\n\u001b[1;32m 398\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m:\n\u001b[0;32m--> 399\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m PackageNotFoundError(name)\n", "\u001b[0;31mPackageNotFoundError\u001b[0m: No package metadata was found for auto-gptq" ] } ], "source": [ "\n", "from transformers import AutoModelForCausalLM, AutoTokenizer\n", "\n", "# 模型路径\n", "model_path = \"./\"\n", "\n", "# 加载模型，显式指定 torch_dtype\n", "model = AutoModelForCausalLM.from_pretrained(\n", " model_path,\n", " torch_dtype=torch.float16, # 或 torch.float16，与权重一致\n", " device_map=\"auto\" # 可选，自动分配设备\n", ")\n", "\n", "# 加载分词器\n", "tokenizer = AutoTokenizer.from_pretrained(model_path)\n", "\n", "# 测试模型\n", "input_text = \"Hello, how are you?\"\n", "inputs = tokenizer(input_text, return_tensors=\"pt\")\n", "outputs = model.generate(**inputs)\n", "print(tokenizer.decode(outputs[0], skip_special_tokens=True))" ] }, { "cell_type": "code", "execution_count": 5, "id": "9d15b55d-f5bc-40ad-80e5-81d421bd0592", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Looking in indexes: http://mirrors.aliyun.com/pypi/simple\n", "Collecting auto-gptq\n", " Downloading http://mirrors.aliyun.com/pypi/packages/90/e5/b22697903982284fe284568fb2663a2196694a8eee637f5cf4ccfe435a38/auto_gptq-0.7.1.tar.gz (126 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m126.1/126.1 kB\u001b[0m \u001b[31m1.4 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[?25hDiscarding \u001b[4;34mhttp://mirrors.aliyun.com/pypi/packages/90/e5/b22697903982284fe284568fb2663a2196694a8eee637f5cf4ccfe435a38/auto_gptq-0.7.1.tar.gz#sha256=5c61ad380e9b4c603757c254765e9083a90a820cd0aff1b5d2c6f7fd96c85e80 (from http://mirrors.aliyun.com/pypi/simple/auto-gptq/) (requires-python:>=3.8.0)\u001b[0m: \u001b[33mRequested auto-gptq from http://mirrors.aliyun.com/pypi/packages/90/e5/b22697903982284fe284568fb2663a2196694a8eee637f5cf4ccfe435a38/auto_gptq-0.7.1.tar.gz#sha256=5c61ad380e9b4c603757c254765e9083a90a820cd0aff1b5d2c6f7fd96c85e80 has inconsistent version: expected '0.7.1', but metadata has '0.7.1+cu1241'\u001b[0m\n", " Downloading http://mirrors.aliyun.com/pypi/packages/34/71/c3e73cf17681f6ff4754ef8f4cb8b67af3def230fc8711eac1250bbd78d5/auto_gptq-0.7.0.tar.gz (124 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m124.6/124.6 kB\u001b[0m \u001b[31m2.4 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[?25hDiscarding \u001b[4;34mhttp://mirrors.aliyun.com/pypi/packages/34/71/c3e73cf17681f6ff4754ef8f4cb8b67af3def230fc8711eac1250bbd78d5/auto_gptq-0.7.0.tar.gz#sha256=50a5396fae2db5a19446b3198ef0e86ee520846b881db47bdbf4eb9260eac723 (from http://mirrors.aliyun.com/pypi/simple/auto-gptq/) (requires-python:>=3.8.0)\u001b[0m: \u001b[33mRequested auto-gptq from http://mirrors.aliyun.com/pypi/packages/34/71/c3e73cf17681f6ff4754ef8f4cb8b67af3def230fc8711eac1250bbd78d5/auto_gptq-0.7.0.tar.gz#sha256=50a5396fae2db5a19446b3198ef0e86ee520846b881db47bdbf4eb9260eac723 has inconsistent version: expected '0.7.0', but metadata has '0.7.0+cu1241'\u001b[0m\n", " Downloading http://mirrors.aliyun.com/pypi/packages/49/af/02b66e55dfd9aeb0ece923843043724ed7432ec0c649ea0f3b9fa1dd90c6/auto_gptq-0.6.0.tar.gz (120 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m121.0/121.0 kB\u001b[0m \u001b[31m1.9 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[?25lerror\n", " \u001b[1;31merror\u001b[0m: \u001b[1msubprocess-exited-with-error\u001b[0m\n", " \n", " \u001b[31m×\u001b[0m \u001b[32mpython setup.py egg_info\u001b[0m did not run successfully.\n", " \u001b[31m│\u001b[0m exit code: \u001b[1;36m1\u001b[0m\n", " \u001b[31m╰─>\u001b[0m \u001b[31m[20 lines of output]\u001b[0m\n", " \u001b[31m \u001b[0m python: can't open file '/tmp/pip-install-9tzda5pv/auto-gptq_60a9cac9f2ef4bb89bb1ce3f0d0126b0/./autogptq_extension/qigen/generate.py': [Errno 2] No such file or directory\n", " \u001b[31m \u001b[0m Traceback (most recent call last):\n", " \u001b[31m \u001b[0m File \"/tmp/pip-install-9tzda5pv/auto-gptq_60a9cac9f2ef4bb89bb1ce3f0d0126b0/setup.py\", line 109, in \n", " \u001b[31m \u001b[0m subprocess.check_output([\"python\", \"./autogptq_extension/qigen/generate.py\", \"--module\", \"--search\", \"--p\", str(p)])\n", " \u001b[31m \u001b[0m File \"/root/miniconda3/lib/python3.12/subprocess.py\", line 466, in check_output\n", " \u001b[31m \u001b[0m return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,\n", " \u001b[31m \u001b[0m ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", " \u001b[31m \u001b[0m File \"/root/miniconda3/lib/python3.12/subprocess.py\", line 571, in run\n", " \u001b[31m \u001b[0m raise CalledProcessError(retcode, process.args,\n", " \u001b[31m \u001b[0m subprocess.CalledProcessError: Command '['python', './autogptq_extension/qigen/generate.py', '--module', '--search', '--p', '48']' returned non-zero exit status 2.\n", " \u001b[31m \u001b[0m \n", " \u001b[31m \u001b[0m During handling of the above exception, another exception occurred:\n", " \u001b[31m \u001b[0m \n", " \u001b[31m \u001b[0m Traceback (most recent call last):\n", " \u001b[31m \u001b[0m File \"\", line 2, in \n", " \u001b[31m \u001b[0m File \"\", line 34, in \n", " \u001b[31m \u001b[0m File \"/tmp/pip-install-9tzda5pv/auto-gptq_60a9cac9f2ef4bb89bb1ce3f0d0126b0/setup.py\", line 111, in \n", " \u001b[31m \u001b[0m raise Exception(f\"Generating QiGen kernels failed with the error shown above.\")\n", " \u001b[31m \u001b[0m Exception: Generating QiGen kernels failed with the error shown above.\n", " \u001b[31m \u001b[0m Generating qigen kernels...\n", " \u001b[31m \u001b[0m \u001b[31m[end of output]\u001b[0m\n", " \n", " \u001b[1;35mnote\u001b[0m: This error originates from a subprocess, and is likely not a problem with pip.\n", "\u001b[1;31merror\u001b[0m: \u001b[1mmetadata-generation-failed\u001b[0m\n", "\n", "\u001b[31m×\u001b[0m Encountered error while generating package metadata.\n", "\u001b[31m╰─>\u001b[0m See above for output.\n", "\n", "\u001b[1;35mnote\u001b[0m: This is an issue with the package mentioned above, not pip.\n", "\u001b[1;36mhint\u001b[0m: See above for details.\n", "\u001b[?25h" ] } ], "source": [ "!pip install auto-gptq" ] }, { "cell_type": "code", "execution_count": null, "id": "b8c14f99-2926-433f-8249-58cc123ce73d", "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": "3.12.3" } }, "nbformat": 4, "nbformat_minor": 5 }