MacBook Pro (15 英寸，2018) 运行 ChatGLM3-6B 大模型

已于 2024-02-04 13:04:22 修改
阅读量740 收藏 7
点赞数 7
分类专栏： # AI 用户指南 文章标签： 人工智能
于 2024-02-03 20:38:03 首次发布
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/xieshaohu/article/details/136015330
版权

接上篇 在 Mac 上加速 PyTorch 训练，准备完 MPS 环境之后，开始在本地体验 ChatGLM3-6B 模型。

一、下载本仓库：

(base) markvivv@MBP dev % git clone https://github.com/THUDM/ChatGLM3

Cloning into 'ChatGLM3'...
remote: Enumerating objects: 1053, done.
remote: Counting objects: 100% (634/634), done.
remote: Compressing objects: 100% (240/240), done.
remote: Total 1053 (delta 461), reused 466 (delta 393), pack-reused 419
Receiving objects: 100% (1053/1053), 17.22 MiB | 983.00 KiB/s, done.
Resolving deltas: 100% (608/608), done.

(base) markvivv@MBP dev % cd ChatGLM3

二、然后使用 pip 安装依赖：

(base) markvivv@MBP ChatGLM3 % pip install -r requirements.txt
Collecting protobuf>=4.25.2 (from -r requirements.txt (line 3))
  Downloading protobuf-4.25.2-cp37-abi3-macosx_10_9_universal2.whl.metadata (541 bytes)
Collecting transformers>=4.37.1 (from -r requirements.txt (line 4))
  Downloading transformers-4.37.2-py3-none-any.whl.metadata (129 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 129.4/129.4 kB 183.4 kB/s eta 0:00:00
Collecting tokenizers>=0.15.0 (from -r requirements.txt (line 5))
  Downloading tokenizers-0.15.1-cp311-cp311-macosx_10_12_x86_64.whl.metadata (6.7 kB)
Collecting cpm_kernels>=1.0.11 (from -r requirements.txt (line 6))
  Downloading cpm_kernels-1.0.11-py3-none-any.whl (416 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 416.6/416.6 kB 764.4 kB/s eta 0:00:00
Requirement already satisfied: torch>=2.1.0 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from -r requirements.txt (line 7)) (2.3.0.dev20240129)
Collecting gradio>=4.16.0 (from -r requirements.txt (line 8))
  Downloading gradio-4.16.0-py3-none-any.whl.metadata (15 kB)
Collecting sentencepiece>=0.1.99 (from -r requirements.txt (line 9))
  Downloading sentencepiece-0.1.99-cp311-cp311-macosx_10_9_x86_64.whl (1.2 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.2/1.2 MB 749.3 kB/s eta 0:00:00
Collecting sentence_transformers>=2.2.2 (from -r requirements.txt (line 10))
  Downloading sentence_transformers-2.3.1-py3-none-any.whl.metadata (11 kB)
Collecting accelerate>=0.26.1 (from -r requirements.txt (line 11))
  Downloading accelerate-0.26.1-py3-none-any.whl.metadata (18 kB)
Collecting streamlit>=1.30.0 (from -r requirements.txt (line 12))
  Downloading streamlit-1.30.0-py2.py3-none-any.whl.metadata (8.2 kB)
Collecting fastapi>=0.109.0 (from -r requirements.txt (line 13))
  Downloading fastapi-0.109.0-py3-none-any.whl.metadata (24 kB)
Collecting loguru~=0.7.2 (from -r requirements.txt (line 14))
  Downloading loguru-0.7.2-py3-none-any.whl.metadata (23 kB)
Collecting mdtex2html>=1.3.0 (from -r requirements.txt (line 15))
  Downloading mdtex2html-1.3.0-py3-none-any.whl.metadata (4.1 kB)
Collecting latex2mathml>=3.77.0 (from -r requirements.txt (line 16))
  Downloading latex2mathml-3.77.0-py3-none-any.whl.metadata (14 kB)
Collecting openai>=1.10.0 (from -r requirements.txt (line 20))
  Downloading openai-1.10.0-py3-none-any.whl.metadata (18 kB)
Collecting zhipuai>=2.0.1 (from -r requirements.txt (line 21))
  Downloading zhipuai-2.0.1-py3-none-any.whl.metadata (2.7 kB)
Collecting pydantic>=2.5.3 (from -r requirements.txt (line 23))
  Downloading pydantic-2.6.0-py3-none-any.whl.metadata (81 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 81.8/81.8 kB 86.5 kB/s eta 0:00:00
Collecting sse-starlette>=2.0.0 (from -r requirements.txt (line 24))
  Downloading sse_starlette-2.0.0-py3-none-any.whl.metadata (5.4 kB)
Collecting uvicorn>=0.27.0 (from -r requirements.txt (line 25))
  Downloading uvicorn-0.27.0.post1-py3-none-any.whl.metadata (6.4 kB)
Collecting timm>=0.9.12 (from -r requirements.txt (line 26))
  Downloading timm-0.9.12-py3-none-any.whl.metadata (60 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 60.6/60.6 kB 139.8 kB/s eta 0:00:00
Collecting tiktoken>=0.5.2 (from -r requirements.txt (line 27))
  Downloading tiktoken-0.5.2-cp311-cp311-macosx_10_9_x86_64.whl.metadata (6.6 kB)
Collecting langchain>=0.1.4 (from -r requirements.txt (line 31))
  Downloading langchain-0.1.4-py3-none-any.whl.metadata (13 kB)
Collecting langchainhub>=0.1.14 (from -r requirements.txt (line 32))
  Downloading langchainhub-0.1.14-py3-none-any.whl.metadata (478 bytes)
Collecting arxiv>=2.1.0 (from -r requirements.txt (line 33))
  Downloading arxiv-2.1.0-py3-none-any.whl.metadata (6.1 kB)
Requirement already satisfied: filelock in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from transformers>=4.37.1->-r requirements.txt (line 4)) (3.13.1)
Collecting huggingface-hub<1.0,>=0.19.3 (from transformers>=4.37.1->-r requirements.txt (line 4))
  Downloading huggingface_hub-0.20.3-py3-none-any.whl.metadata (12 kB)
Requirement already satisfied: numpy>=1.17 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from transformers>=4.37.1->-r requirements.txt (line 4)) (1.26.3)
Requirement already satisfied: packaging>=20.0 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from transformers>=4.37.1->-r requirements.txt (line 4)) (23.1)
Requirement already satisfied: pyyaml>=5.1 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from transformers>=4.37.1->-r requirements.txt (line 4)) (6.0.1)
Collecting regex!=2019.12.17 (from transformers>=4.37.1->-r requirements.txt (line 4))
  Downloading regex-2023.12.25-cp311-cp311-macosx_10_9_x86_64.whl.metadata (40 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 40.9/40.9 kB 53.9 kB/s eta 0:00:00
Requirement already satisfied: requests in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from transformers>=4.37.1->-r requirements.txt (line 4)) (2.31.0)
Collecting safetensors>=0.4.1 (from transformers>=4.37.1->-r requirements.txt (line 4))
  Downloading safetensors-0.4.2-cp311-cp311-macosx_10_12_x86_64.whl.metadata (3.8 kB)
Requirement already satisfied: tqdm>=4.27 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from transformers>=4.37.1->-r requirements.txt (line 4)) (4.65.0)
Requirement already satisfied: typing-extensions>=4.8.0 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from torch>=2.1.0->-r requirements.txt (line 7)) (4.9.0)
Requirement already satisfied: sympy in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from torch>=2.1.0->-r requirements.txt (line 7)) (1.12)
Requirement already satisfied: networkx in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from torch>=2.1.0->-r requirements.txt (line 7)) (3.1)
Requirement already satisfied: jinja2 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from torch>=2.1.0->-r requirements.txt (line 7)) (3.1.2)
Collecting fsspec (from torch>=2.1.0->-r requirements.txt (line 7))
  Downloading fsspec-2023.12.2-py3-none-any.whl.metadata (6.8 kB)
Collecting aiofiles<24.0,>=22.0 (from gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading aiofiles-23.2.1-py3-none-any.whl.metadata (9.7 kB)
Collecting altair<6.0,>=4.2.0 (from gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading altair-5.2.0-py3-none-any.whl.metadata (8.7 kB)
Collecting ffmpy (from gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading ffmpy-0.3.1.tar.gz (5.5 kB)
  Preparing metadata (setup.py) ... done
Collecting gradio-client==0.8.1 (from gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading gradio_client-0.8.1-py3-none-any.whl.metadata (7.1 kB)
Collecting httpx (from gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading httpx-0.26.0-py3-none-any.whl.metadata (7.6 kB)
Collecting importlib-resources<7.0,>=1.3 (from gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading importlib_resources-6.1.1-py3-none-any.whl.metadata (4.1 kB)
Requirement already satisfied: markupsafe~=2.0 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from gradio>=4.16.0->-r requirements.txt (line 8)) (2.1.3)
Collecting matplotlib~=3.0 (from gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading matplotlib-3.8.2-cp311-cp311-macosx_10_12_x86_64.whl.metadata (5.8 kB)
Collecting orjson~=3.0 (from gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading orjson-3.9.12-cp311-cp311-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl.metadata (49 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 49.4/49.4 kB 181.3 kB/s eta 0:00:00
Collecting pandas<3.0,>=1.0 (from gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading pandas-2.2.0-cp311-cp311-macosx_10_9_x86_64.whl.metadata (19 kB)
Requirement already satisfied: pillow<11.0,>=8.0 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from gradio>=4.16.0->-r requirements.txt (line 8)) (9.3.0)
Collecting pydub (from gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)
Collecting python-multipart (from gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading python_multipart-0.0.6-py3-none-any.whl (45 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 45.7/45.7 kB 316.1 kB/s eta 0:00:00
Collecting ruff>=0.1.7 (from gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading ruff-0.1.15-py3-none-macosx_10_12_x86_64.whl.metadata (22 kB)
Collecting semantic-version~=2.0 (from gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)
Collecting tomlkit==0.12.0 (from gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading tomlkit-0.12.0-py3-none-any.whl.metadata (2.7 kB)
Collecting typer<1.0,>=0.9 (from typer[all]<1.0,>=0.9->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading typer-0.9.0-py3-none-any.whl (45 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 45.9/45.9 kB 285.8 kB/s eta 0:00:00
Collecting websockets<12.0,>=10.0 (from gradio-client==0.8.1->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading websockets-11.0.3-cp311-cp311-macosx_10_9_x86_64.whl (120 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 121.0/121.0 kB 227.9 kB/s eta 0:00:00
Collecting scikit-learn (from sentence_transformers>=2.2.2->-r requirements.txt (line 10))
  Downloading scikit_learn-1.4.0-1-cp311-cp311-macosx_10_9_x86_64.whl.metadata (11 kB)
Collecting scipy (from sentence_transformers>=2.2.2->-r requirements.txt (line 10))
  Downloading scipy-1.12.0-cp311-cp311-macosx_10_9_x86_64.whl.metadata (60 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 60.4/60.4 kB 638.2 kB/s eta 0:00:00
Collecting nltk (from sentence_transformers>=2.2.2->-r requirements.txt (line 10))
  Downloading nltk-3.8.1-py3-none-any.whl (1.5 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.5/1.5 MB 640.4 kB/s eta 0:00:00
Collecting psutil (from accelerate>=0.26.1->-r requirements.txt (line 11))
  Downloading psutil-5.9.8-cp36-abi3-macosx_10_9_x86_64.whl.metadata (21 kB)
Collecting blinker<2,>=1.0.0 (from streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading blinker-1.7.0-py3-none-any.whl.metadata (1.9 kB)
Collecting cachetools<6,>=4.0 (from streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading cachetools-5.3.2-py3-none-any.whl.metadata (5.2 kB)
Collecting click<9,>=7.0 (from streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading click-8.1.7-py3-none-any.whl.metadata (3.0 kB)
Collecting importlib-metadata<8,>=1.4 (from streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading importlib_metadata-7.0.1-py3-none-any.whl.metadata (4.9 kB)
Collecting pyarrow>=6.0 (from streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading pyarrow-15.0.0-cp311-cp311-macosx_10_15_x86_64.whl.metadata (3.0 kB)
Collecting python-dateutil<3,>=2.7.3 (from streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading python_dateutil-2.8.2-py2.py3-none-any.whl (247 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 247.7/247.7 kB 1.0 MB/s eta 0:00:00
Collecting rich<14,>=10.14.0 (from streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading rich-13.7.0-py3-none-any.whl.metadata (18 kB)
Collecting tenacity<9,>=8.1.0 (from streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading tenacity-8.2.3-py3-none-any.whl.metadata (1.0 kB)
Collecting toml<2,>=0.10.1 (from streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading toml-0.10.2-py2.py3-none-any.whl (16 kB)
Collecting tzlocal<6,>=1.1 (from streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading tzlocal-5.2-py3-none-any.whl.metadata (7.8 kB)
Collecting validators<1,>=0.2 (from streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading validators-0.22.0-py3-none-any.whl.metadata (4.7 kB)
Collecting gitpython!=3.1.19,<4,>=3.0.7 (from streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading GitPython-3.1.41-py3-none-any.whl.metadata (14 kB)
Collecting pydeck<1,>=0.8.0b4 (from streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading pydeck-0.8.1b0-py2.py3-none-any.whl (4.8 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4.8/4.8 MB 1.8 MB/s eta 0:00:00
Collecting tornado<7,>=6.0.3 (from streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading tornado-6.4-cp38-abi3-macosx_10_9_x86_64.whl.metadata (2.5 kB)
Collecting starlette<0.36.0,>=0.35.0 (from fastapi>=0.109.0->-r requirements.txt (line 13))
  Downloading starlette-0.35.1-py3-none-any.whl.metadata (5.8 kB)
Collecting markdown (from mdtex2html>=1.3.0->-r requirements.txt (line 15))
  Downloading Markdown-3.5.2-py3-none-any.whl.metadata (7.0 kB)
Collecting anyio<5,>=3.5.0 (from openai>=1.10.0->-r requirements.txt (line 20))
  Downloading anyio-4.2.0-py3-none-any.whl.metadata (4.6 kB)
Requirement already satisfied: distro<2,>=1.7.0 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from openai>=1.10.0->-r requirements.txt (line 20)) (1.8.0)
Collecting sniffio (from openai>=1.10.0->-r requirements.txt (line 20))
  Downloading sniffio-1.3.0-py3-none-any.whl (10 kB)
Collecting pyjwt~=2.8.0 (from zhipuai>=2.0.1->-r requirements.txt (line 21))
  Downloading PyJWT-2.8.0-py3-none-any.whl.metadata (4.2 kB)
Collecting annotated-types>=0.4.0 (from pydantic>=2.5.3->-r requirements.txt (line 23))
  Downloading annotated_types-0.6.0-py3-none-any.whl.metadata (12 kB)
Collecting pydantic-core==2.16.1 (from pydantic>=2.5.3->-r requirements.txt (line 23))
  Downloading pydantic_core-2.16.1-cp311-cp311-macosx_10_12_x86_64.whl.metadata (6.5 kB)
Collecting h11>=0.8 (from uvicorn>=0.27.0->-r requirements.txt (line 25))
  Downloading h11-0.14.0-py3-none-any.whl (58 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 58.3/58.3 kB 135.9 kB/s eta 0:00:00
Requirement already satisfied: torchvision in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from timm>=0.9.12->-r requirements.txt (line 26)) (0.18.0.dev20240129)
Collecting SQLAlchemy<3,>=1.4 (from langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading SQLAlchemy-2.0.25-cp311-cp311-macosx_10_9_x86_64.whl.metadata (9.6 kB)
Collecting aiohttp<4.0.0,>=3.8.3 (from langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading aiohttp-3.9.3-cp311-cp311-macosx_10_9_x86_64.whl.metadata (7.4 kB)
Collecting dataclasses-json<0.7,>=0.5.7 (from langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading dataclasses_json-0.6.3-py3-none-any.whl.metadata (25 kB)
Collecting jsonpatch<2.0,>=1.33 (from langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading jsonpatch-1.33-py2.py3-none-any.whl.metadata (3.0 kB)
Collecting langchain-community<0.1,>=0.0.14 (from langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading langchain_community-0.0.16-py3-none-any.whl.metadata (7.8 kB)
Collecting langchain-core<0.2,>=0.1.16 (from langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading langchain_core-0.1.17-py3-none-any.whl.metadata (6.0 kB)
Collecting langsmith<0.1,>=0.0.83 (from langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading langsmith-0.0.85-py3-none-any.whl.metadata (10 kB)
Collecting types-requests<3.0.0.0,>=2.31.0.2 (from langchainhub>=0.1.14->-r requirements.txt (line 32))
  Downloading types_requests-2.31.0.20240125-py3-none-any.whl.metadata (1.8 kB)
Collecting feedparser==6.0.10 (from arxiv>=2.1.0->-r requirements.txt (line 33))
  Downloading feedparser-6.0.10-py3-none-any.whl (81 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 81.1/81.1 kB 243.9 kB/s eta 0:00:00
Collecting sgmllib3k (from feedparser==6.0.10->arxiv>=2.1.0->-r requirements.txt (line 33))
  Downloading sgmllib3k-1.0.0.tar.gz (5.8 kB)
  Preparing metadata (setup.py) ... done
Requirement already satisfied: charset-normalizer<4,>=2 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from requests->transformers>=4.37.1->-r requirements.txt (line 4)) (2.0.4)
Requirement already satisfied: idna<4,>=2.5 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from requests->transformers>=4.37.1->-r requirements.txt (line 4)) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from requests->transformers>=4.37.1->-r requirements.txt (line 4)) (1.26.18)
Requirement already satisfied: certifi>=2017.4.17 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from requests->transformers>=4.37.1->-r requirements.txt (line 4)) (2023.11.17)
Collecting aiosignal>=1.1.2 (from aiohttp<4.0.0,>=3.8.3->langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)
Collecting attrs>=17.3.0 (from aiohttp<4.0.0,>=3.8.3->langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading attrs-23.2.0-py3-none-any.whl.metadata (9.5 kB)
Collecting frozenlist>=1.1.1 (from aiohttp<4.0.0,>=3.8.3->langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading frozenlist-1.4.1-cp311-cp311-macosx_10_9_x86_64.whl.metadata (12 kB)
Collecting multidict<7.0,>=4.5 (from aiohttp<4.0.0,>=3.8.3->langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading multidict-6.0.4-cp311-cp311-macosx_10_9_x86_64.whl (29 kB)
Collecting yarl<2.0,>=1.0 (from aiohttp<4.0.0,>=3.8.3->langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading yarl-1.9.4-cp311-cp311-macosx_10_9_x86_64.whl.metadata (31 kB)
Collecting jsonschema>=3.0 (from altair<6.0,>=4.2.0->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading jsonschema-4.21.1-py3-none-any.whl.metadata (7.8 kB)
Collecting toolz (from altair<6.0,>=4.2.0->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading toolz-0.12.1-py3-none-any.whl.metadata (5.1 kB)
Collecting marshmallow<4.0.0,>=3.18.0 (from dataclasses-json<0.7,>=0.5.7->langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading marshmallow-3.20.2-py3-none-any.whl.metadata (7.5 kB)
Collecting typing-inspect<1,>=0.4.0 (from dataclasses-json<0.7,>=0.5.7->langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading typing_inspect-0.9.0-py3-none-any.whl.metadata (1.5 kB)
Collecting gitdb<5,>=4.0.1 (from gitpython!=3.1.19,<4,>=3.0.7->streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading gitdb-4.0.11-py3-none-any.whl.metadata (1.2 kB)
Collecting httpcore==1.* (from httpx->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading httpcore-1.0.2-py3-none-any.whl.metadata (20 kB)
Collecting zipp>=0.5 (from importlib-metadata<8,>=1.4->streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading zipp-3.17.0-py3-none-any.whl.metadata (3.7 kB)
Requirement already satisfied: jsonpointer>=1.9 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from jsonpatch<2.0,>=1.33->langchain>=0.1.4->-r requirements.txt (line 31)) (2.1)
Collecting packaging>=20.0 (from transformers>=4.37.1->-r requirements.txt (line 4))
  Downloading packaging-23.2-py3-none-any.whl.metadata (3.2 kB)
Collecting contourpy>=1.0.1 (from matplotlib~=3.0->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading contourpy-1.2.0-cp311-cp311-macosx_10_9_x86_64.whl.metadata (5.8 kB)
Collecting cycler>=0.10 (from matplotlib~=3.0->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading cycler-0.12.1-py3-none-any.whl.metadata (3.8 kB)
Collecting fonttools>=4.22.0 (from matplotlib~=3.0->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading fonttools-4.47.2-cp311-cp311-macosx_10_9_x86_64.whl.metadata (157 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 157.6/157.6 kB 109.2 kB/s eta 0:00:00
Collecting kiwisolver>=1.3.1 (from matplotlib~=3.0->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading kiwisolver-1.4.5-cp311-cp311-macosx_10_9_x86_64.whl.metadata (6.4 kB)
Collecting pyparsing>=2.3.1 (from matplotlib~=3.0->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading pyparsing-3.1.1-py3-none-any.whl.metadata (5.1 kB)
Collecting pytz>=2020.1 (from pandas<3.0,>=1.0->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading pytz-2023.4-py2.py3-none-any.whl.metadata (22 kB)
Collecting tzdata>=2022.7 (from pandas<3.0,>=1.0->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading tzdata-2023.4-py2.py3-none-any.whl.metadata (1.4 kB)
Collecting six>=1.5 (from python-dateutil<3,>=2.7.3->streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading six-1.16.0-py2.py3-none-any.whl (11 kB)
Collecting markdown-it-py>=2.2.0 (from rich<14,>=10.14.0->streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading markdown_it_py-3.0.0-py3-none-any.whl.metadata (6.9 kB)
Collecting pygments<3.0.0,>=2.13.0 (from rich<14,>=10.14.0->streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading pygments-2.17.2-py3-none-any.whl.metadata (2.6 kB)
Collecting greenlet!=0.4.17 (from SQLAlchemy<3,>=1.4->langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading greenlet-3.0.3.tar.gz (182 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 182.0/182.0 kB 303.3 kB/s eta 0:00:00
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
  Installing backend dependencies ... done
  Preparing metadata (pyproject.toml) ... done
Collecting colorama<0.5.0,>=0.4.3 (from typer[all]<1.0,>=0.9->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)
Collecting shellingham<2.0.0,>=1.3.0 (from typer[all]<1.0,>=0.9->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading shellingham-1.5.4-py2.py3-none-any.whl.metadata (3.5 kB)
Collecting urllib3<3,>=1.21.1 (from requests->transformers>=4.37.1->-r requirements.txt (line 4))
  Downloading urllib3-2.2.0-py3-none-any.whl.metadata (6.4 kB)
Collecting joblib (from nltk->sentence_transformers>=2.2.2->-r requirements.txt (line 10))
  Downloading joblib-1.3.2-py3-none-any.whl.metadata (5.4 kB)
Collecting threadpoolctl>=2.0.0 (from scikit-learn->sentence_transformers>=2.2.2->-r requirements.txt (line 10))
  Downloading threadpoolctl-3.2.0-py3-none-any.whl.metadata (10.0 kB)
Requirement already satisfied: mpmath>=0.19 in /Users/markvivv/dev/miniconda3/lib/python3.11/site-packages (from sympy->torch>=2.1.0->-r requirements.txt (line 7)) (1.2.1)
Collecting smmap<6,>=3.0.1 (from gitdb<5,>=4.0.1->gitpython!=3.1.19,<4,>=3.0.7->streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading smmap-5.0.1-py3-none-any.whl.metadata (4.3 kB)
Collecting jsonschema-specifications>=2023.03.6 (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading jsonschema_specifications-2023.12.1-py3-none-any.whl.metadata (3.0 kB)
Collecting referencing>=0.28.4 (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading referencing-0.33.0-py3-none-any.whl.metadata (2.7 kB)
Collecting rpds-py>=0.7.1 (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio>=4.16.0->-r requirements.txt (line 8))
  Downloading rpds_py-0.17.1-cp311-cp311-macosx_10_12_x86_64.whl.metadata (4.1 kB)
Collecting mdurl~=0.1 (from markdown-it-py>=2.2.0->rich<14,>=10.14.0->streamlit>=1.30.0->-r requirements.txt (line 12))
  Downloading mdurl-0.1.2-py3-none-any.whl (10.0 kB)
Collecting mypy-extensions>=0.3.0 (from typing-inspect<1,>=0.4.0->dataclasses-json<0.7,>=0.5.7->langchain>=0.1.4->-r requirements.txt (line 31))
  Downloading mypy_extensions-1.0.0-py3-none-any.whl (4.7 kB)
Downloading protobuf-4.25.2-cp37-abi3-macosx_10_9_universal2.whl (394 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 394.2/394.2 kB 489.0 kB/s eta 0:00:00
Downloading transformers-4.37.2-py3-none-any.whl (8.4 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 8.4/8.4 MB 1.1 MB/s eta 0:00:00
Downloading tokenizers-0.15.1-cp311-cp311-macosx_10_12_x86_64.whl (2.6 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.6/2.6 MB 710.7 kB/s eta 0:00:00
Downloading gradio-4.16.0-py3-none-any.whl (16.7 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 16.7/16.7 MB 2.0 MB/s eta 0:00:00
Downloading gradio_client-0.8.1-py3-none-any.whl (305 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 305.2/305.2 kB 1.1 MB/s eta 0:00:00
Downloading tomlkit-0.12.0-py3-none-any.whl (37 kB)
Downloading sentence_transformers-2.3.1-py3-none-any.whl (132 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 132.8/132.8 kB 1.8 MB/s eta 0:00:00
Downloading accelerate-0.26.1-py3-none-any.whl (270 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 270.9/270.9 kB 1.5 MB/s eta 0:00:00
Downloading streamlit-1.30.0-py2.py3-none-any.whl (8.4 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 8.4/8.4 MB 1.8 MB/s eta 0:00:00
Downloading fastapi-0.109.0-py3-none-any.whl (92 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 92.0/92.0 kB 1.3 MB/s eta 0:00:00
Downloading loguru-0.7.2-py3-none-any.whl (62 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 62.5/62.5 kB 1.1 MB/s eta 0:00:00
Downloading mdtex2html-1.3.0-py3-none-any.whl (13 kB)
Downloading latex2mathml-3.77.0-py3-none-any.whl (73 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 73.7/73.7 kB 1.2 MB/s eta 0:00:00
Downloading openai-1.10.0-py3-none-any.whl (225 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 225.1/225.1 kB 1.6 MB/s eta 0:00:00
Downloading zhipuai-2.0.1-py3-none-any.whl (26 kB)
Downloading pydantic-2.6.0-py3-none-any.whl (394 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 394.2/394.2 kB 3.1 MB/s eta 0:00:00
Downloading pydantic_core-2.16.1-cp311-cp311-macosx_10_12_x86_64.whl (1.9 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.9/1.9 MB 1.2 MB/s eta 0:00:00
Downloading sse_starlette-2.0.0-py3-none-any.whl (9.0 kB)
Downloading uvicorn-0.27.0.post1-py3-none-any.whl (60 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 60.7/60.7 kB 1.3 MB/s eta 0:00:00
Downloading timm-0.9.12-py3-none-any.whl (2.2 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.2/2.2 MB 1.5 MB/s eta 0:00:00
Downloading tiktoken-0.5.2-cp311-cp311-macosx_10_9_x86_64.whl (1.0 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.0/1.0 MB 965.3 kB/s eta 0:00:00
Downloading langchain-0.1.4-py3-none-any.whl (803 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 803.6/803.6 kB 1.9 MB/s eta 0:00:00
Downloading langchainhub-0.1.14-py3-none-any.whl (3.4 kB)
Downloading arxiv-2.1.0-py3-none-any.whl (11 kB)
Downloading aiofiles-23.2.1-py3-none-any.whl (15 kB)
Downloading aiohttp-3.9.3-cp311-cp311-macosx_10_9_x86_64.whl (398 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 398.5/398.5 kB 1.9 MB/s eta 0:00:00
Downloading altair-5.2.0-py3-none-any.whl (996 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 996.9/996.9 kB 1.4 MB/s eta 0:00:00
Downloading annotated_types-0.6.0-py3-none-any.whl (12 kB)
Downloading anyio-4.2.0-py3-none-any.whl (85 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 85.5/85.5 kB 1.3 MB/s eta 0:00:00
Downloading blinker-1.7.0-py3-none-any.whl (13 kB)
Downloading cachetools-5.3.2-py3-none-any.whl (9.3 kB)
Downloading click-8.1.7-py3-none-any.whl (97 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 97.9/97.9 kB 205.8 kB/s eta 0:00:00
Downloading dataclasses_json-0.6.3-py3-none-any.whl (28 kB)
Downloading GitPython-3.1.41-py3-none-any.whl (196 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 196.4/196.4 kB 1.4 MB/s eta 0:00:00
Downloading httpx-0.26.0-py3-none-any.whl (75 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 75.9/75.9 kB 1.2 MB/s eta 0:00:00
Downloading httpcore-1.0.2-py3-none-any.whl (76 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 76.9/76.9 kB 1.1 MB/s eta 0:00:00
Downloading huggingface_hub-0.20.3-py3-none-any.whl (330 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 330.1/330.1 kB 385.8 kB/s eta 0:00:00
Downloading fsspec-2023.12.2-py3-none-any.whl (168 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 169.0/169.0 kB 996.0 kB/s eta 0:00:00
Downloading importlib_metadata-7.0.1-py3-none-any.whl (23 kB)
Downloading importlib_resources-6.1.1-py3-none-any.whl (33 kB)
Downloading jsonpatch-1.33-py2.py3-none-any.whl (12 kB)
Downloading langchain_community-0.0.16-py3-none-any.whl (1.6 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.6/1.6 MB 1.6 MB/s eta 0:00:00
Downloading langchain_core-0.1.17-py3-none-any.whl (235 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 235.9/235.9 kB 1.8 MB/s eta 0:00:00
Downloading langsmith-0.0.85-py3-none-any.whl (54 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 54.0/54.0 kB 735.7 kB/s eta 0:00:00
Downloading matplotlib-3.8.2-cp311-cp311-macosx_10_12_x86_64.whl (7.6 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7.6/7.6 MB 1.5 MB/s eta 0:00:00
Downloading orjson-3.9.12-cp311-cp311-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl (250 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 250.6/250.6 kB 2.2 MB/s eta 0:00:00
Downloading packaging-23.2-py3-none-any.whl (53 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 53.0/53.0 kB 1.1 MB/s eta 0:00:00
Downloading pandas-2.2.0-cp311-cp311-macosx_10_9_x86_64.whl (12.5 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 12.5/12.5 MB 1.8 MB/s eta 0:00:00
Downloading pyarrow-15.0.0-cp311-cp311-macosx_10_15_x86_64.whl (27.2 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 27.2/27.2 MB 1.1 MB/s eta 0:00:00
Downloading PyJWT-2.8.0-py3-none-any.whl (22 kB)
Downloading regex-2023.12.25-cp311-cp311-macosx_10_9_x86_64.whl (296 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 296.5/296.5 kB 2.0 MB/s eta 0:00:00
Downloading rich-13.7.0-py3-none-any.whl (240 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 240.6/240.6 kB 957.1 kB/s eta 0:00:00
Downloading ruff-0.1.15-py3-none-macosx_10_12_x86_64.whl (7.3 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7.3/7.3 MB 1.7 MB/s eta 0:00:00
Downloading safetensors-0.4.2-cp311-cp311-macosx_10_12_x86_64.whl (426 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 426.3/426.3 kB 1.5 MB/s eta 0:00:00
Downloading SQLAlchemy-2.0.25-cp311-cp311-macosx_10_9_x86_64.whl (2.1 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.1/2.1 MB 1.3 MB/s eta 0:00:00
Downloading starlette-0.35.1-py3-none-any.whl (71 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 71.1/71.1 kB 2.2 MB/s eta 0:00:00
Downloading tenacity-8.2.3-py3-none-any.whl (24 kB)
Downloading tornado-6.4-cp38-abi3-macosx_10_9_x86_64.whl (431 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 431.1/431.1 kB 1.4 MB/s eta 0:00:00
Downloading types_requests-2.31.0.20240125-py3-none-any.whl (14 kB)
Downloading tzlocal-5.2-py3-none-any.whl (17 kB)
Downloading validators-0.22.0-py3-none-any.whl (26 kB)
Downloading Markdown-3.5.2-py3-none-any.whl (103 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 103.9/103.9 kB 1.3 MB/s eta 0:00:00
Downloading psutil-5.9.8-cp36-abi3-macosx_10_9_x86_64.whl (248 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 248.7/248.7 kB 1.3 MB/s eta 0:00:00
Downloading scikit_learn-1.4.0-1-cp311-cp311-macosx_10_9_x86_64.whl (11.5 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 11.5/11.5 MB 1.5 MB/s eta 0:00:00
Downloading scipy-1.12.0-cp311-cp311-macosx_10_9_x86_64.whl (38.9 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 38.9/38.9 MB 1.9 MB/s eta 0:00:00
Downloading attrs-23.2.0-py3-none-any.whl (60 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 60.8/60.8 kB 992.9 kB/s eta 0:00:00
Downloading contourpy-1.2.0-cp311-cp311-macosx_10_9_x86_64.whl (258 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 258.2/258.2 kB 1.3 MB/s eta 0:00:00
Downloading cycler-0.12.1-py3-none-any.whl (8.3 kB)
Downloading fonttools-4.47.2-cp311-cp311-macosx_10_9_x86_64.whl (2.3 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.3/2.3 MB 2.0 MB/s eta 0:00:00
Downloading frozenlist-1.4.1-cp311-cp311-macosx_10_9_x86_64.whl (55 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 55.3/55.3 kB 1.0 MB/s eta 0:00:00
Downloading gitdb-4.0.11-py3-none-any.whl (62 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 62.7/62.7 kB 1.3 MB/s eta 0:00:00
Downloading joblib-1.3.2-py3-none-any.whl (302 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 302.2/302.2 kB 927.0 kB/s eta 0:00:00
Downloading jsonschema-4.21.1-py3-none-any.whl (85 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 85.5/85.5 kB 1.2 MB/s eta 0:00:00
Downloading kiwisolver-1.4.5-cp311-cp311-macosx_10_9_x86_64.whl (68 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 68.2/68.2 kB 1.4 MB/s eta 0:00:00
Downloading markdown_it_py-3.0.0-py3-none-any.whl (87 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 87.5/87.5 kB 1.6 MB/s eta 0:00:00
Downloading marshmallow-3.20.2-py3-none-any.whl (49 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 49.4/49.4 kB 1.0 MB/s eta 0:00:00
Downloading pygments-2.17.2-py3-none-any.whl (1.2 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.2/1.2 MB 1.5 MB/s eta 0:00:00
Downloading pyparsing-3.1.1-py3-none-any.whl (103 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 103.1/103.1 kB 1.3 MB/s eta 0:00:00
Downloading pytz-2023.4-py2.py3-none-any.whl (506 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 506.5/506.5 kB 1.2 MB/s eta 0:00:00
Downloading shellingham-1.5.4-py2.py3-none-any.whl (9.8 kB)
Downloading threadpoolctl-3.2.0-py3-none-any.whl (15 kB)
Downloading typing_inspect-0.9.0-py3-none-any.whl (8.8 kB)
Downloading tzdata-2023.4-py2.py3-none-any.whl (346 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 346.6/346.6 kB 1.2 MB/s eta 0:00:00
Downloading urllib3-2.2.0-py3-none-any.whl (120 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 120.9/120.9 kB 1.8 MB/s eta 0:00:00
Downloading yarl-1.9.4-cp311-cp311-macosx_10_9_x86_64.whl (83 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 83.2/83.2 kB 443.8 kB/s eta 0:00:00
Downloading zipp-3.17.0-py3-none-any.whl (7.4 kB)
Downloading toolz-0.12.1-py3-none-any.whl (56 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 56.1/56.1 kB 1.2 MB/s eta 0:00:00
Downloading jsonschema_specifications-2023.12.1-py3-none-any.whl (18 kB)
Downloading referencing-0.33.0-py3-none-any.whl (26 kB)
Downloading rpds_py-0.17.1-cp311-cp311-macosx_10_12_x86_64.whl (353 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 354.0/354.0 kB 1.1 MB/s eta 0:00:00
Downloading smmap-5.0.1-py3-none-any.whl (24 kB)
Building wheels for collected packages: ffmpy, greenlet, sgmllib3k
  Building wheel for ffmpy (setup.py) ... done
  Created wheel for ffmpy: filename=ffmpy-0.3.1-py3-none-any.whl size=5579 sha256=2da41c8a484b0216a795b6762618a78078b9ee0dd763cf2e1ca40f51b0b90cb6
  Stored in directory: /Users/markvivv/Library/Caches/pip/wheels/99/3b/84/22ac1eab7a10222ac6bbc3f7e69b04f3980db328978c533a3f
  Building wheel for greenlet (pyproject.toml) ... done
  Created wheel for greenlet: filename=greenlet-3.0.3-cp311-cp311-macosx_10_9_x86_64.whl size=214633 sha256=14b61d6f09dad9bc5af1feda5eb76510c613612680bbc330044443f825ce82b9
  Stored in directory: /Users/markvivv/Library/Caches/pip/wheels/56/08/ca/e0bd72a4cd850a40d2a51ee67fbd2f3efe5332fe5fe00e2c53
  Building wheel for sgmllib3k (setup.py) ... done
  Created wheel for sgmllib3k: filename=sgmllib3k-1.0.0-py3-none-any.whl size=6047 sha256=ae3bad9422d7de25be119b223c83a2476aaeba9aecbc0cbc97e61b8a95ca1fb8
  Stored in directory: /Users/markvivv/Library/Caches/pip/wheels/3b/25/2a/105d6a15df6914f4d15047691c6c28f9052cc1173e40285d03
Successfully built ffmpy greenlet sgmllib3k
Installing collected packages: sgmllib3k, sentencepiece, pytz, pydub, ffmpy, cpm_kernels, zipp, websockets, validators, urllib3, tzlocal, tzdata, tornado, toolz, tomlkit, toml, threadpoolctl, tenacity, sniffio, smmap, six, shellingham, semantic-version, scipy, safetensors, ruff, rpds-py, regex, python-multipart, pyparsing, pyjwt, pygments, pydantic-core, pyarrow, psutil, protobuf, packaging, orjson, mypy-extensions, multidict, mdurl, markdown, loguru, latex2mathml, kiwisolver, jsonpatch, joblib, importlib-resources, h11, greenlet, fsspec, frozenlist, fonttools, feedparser, cycler, contourpy, colorama, click, cachetools, blinker, attrs, annotated-types, aiofiles, yarl, uvicorn, typing-inspect, types-requests, typer, SQLAlchemy, scikit-learn, referencing, python-dateutil, pydeck, pydantic, nltk, mdtex2html, marshmallow, markdown-it-py, importlib-metadata, httpcore, gitdb, anyio, aiosignal, tiktoken, starlette, rich, pandas, matplotlib, langsmith, langchainhub, jsonschema-specifications, huggingface-hub, httpx, gitpython, dataclasses-json, arxiv, aiohttp, zhipuai, tokenizers, timm, sse-starlette, openai, langchain-core, jsonschema, gradio-client, fastapi, accelerate, transformers, langchain-community, altair, streamlit, sentence_transformers, langchain, gradio
  Attempting uninstall: urllib3
    Found existing installation: urllib3 1.26.18
    Uninstalling urllib3-1.26.18:
      Successfully uninstalled urllib3-1.26.18
  Attempting uninstall: packaging
    Found existing installation: packaging 23.1
    Uninstalling packaging-23.1:
      Successfully uninstalled packaging-23.1
  Attempting uninstall: jsonpatch
    Found existing installation: jsonpatch 1.32
    Uninstalling jsonpatch-1.32:
      Successfully uninstalled jsonpatch-1.32
Successfully installed SQLAlchemy-2.0.25 accelerate-0.26.1 aiofiles-23.2.1 aiohttp-3.9.3 aiosignal-1.3.1 altair-5.2.0 annotated-types-0.6.0 anyio-4.2.0 arxiv-2.1.0 attrs-23.2.0 blinker-1.7.0 cachetools-5.3.2 click-8.1.7 colorama-0.4.6 contourpy-1.2.0 cpm_kernels-1.0.11 cycler-0.12.1 dataclasses-json-0.6.3 fastapi-0.109.0 feedparser-6.0.10 ffmpy-0.3.1 fonttools-4.47.2 frozenlist-1.4.1 fsspec-2023.12.2 gitdb-4.0.11 gitpython-3.1.41 gradio-4.16.0 gradio-client-0.8.1 greenlet-3.0.3 h11-0.14.0 httpcore-1.0.2 httpx-0.26.0 huggingface-hub-0.20.3 importlib-metadata-7.0.1 importlib-resources-6.1.1 joblib-1.3.2 jsonpatch-1.33 jsonschema-4.21.1 jsonschema-specifications-2023.12.1 kiwisolver-1.4.5 langchain-0.1.4 langchain-community-0.0.16 langchain-core-0.1.17 langchainhub-0.1.14 langsmith-0.0.85 latex2mathml-3.77.0 loguru-0.7.2 markdown-3.5.2 markdown-it-py-3.0.0 marshmallow-3.20.2 matplotlib-3.8.2 mdtex2html-1.3.0 mdurl-0.1.2 multidict-6.0.4 mypy-extensions-1.0.0 nltk-3.8.1 openai-1.10.0 orjson-3.9.12 packaging-23.2 pandas-2.2.0 protobuf-4.25.2 psutil-5.9.8 pyarrow-15.0.0 pydantic-2.6.0 pydantic-core-2.16.1 pydeck-0.8.1b0 pydub-0.25.1 pygments-2.17.2 pyjwt-2.8.0 pyparsing-3.1.1 python-dateutil-2.8.2 python-multipart-0.0.6 pytz-2023.4 referencing-0.33.0 regex-2023.12.25 rich-13.7.0 rpds-py-0.17.1 ruff-0.1.15 safetensors-0.4.2 scikit-learn-1.4.0 scipy-1.12.0 semantic-version-2.10.0 sentence_transformers-2.3.1 sentencepiece-0.1.99 sgmllib3k-1.0.0 shellingham-1.5.4 six-1.16.0 smmap-5.0.1 sniffio-1.3.0 sse-starlette-2.0.0 starlette-0.35.1 streamlit-1.30.0 tenacity-8.2.3 threadpoolctl-3.2.0 tiktoken-0.5.2 timm-0.9.12 tokenizers-0.15.1 toml-0.10.2 tomlkit-0.12.0 toolz-0.12.1 tornado-6.4 transformers-4.37.2 typer-0.9.0 types-requests-2.31.0.20240125 typing-inspect-0.9.0 tzdata-2023.4 tzlocal-5.2 urllib3-2.2.0 uvicorn-0.27.0.post1 validators-0.22.0 websockets-11.0.3 yarl-1.9.4 zhipuai-2.0.1 zipp-3.17.0

三、进入 base_demo，准备启动 streamlit 示例程序

(base) markvivv@MBP ChatGLM3 % cd base_demo

本人笔记本带独立显卡，4G 显存，16G 内存，默认参数可以启动示例程序，但是对大模型提任何问题都会提示如下错误：

RuntimeError: MPS backend out of memory (MPS allocated: 5.44 GB, other allocations: 1.17 GB, max allowed: 6.80 GB). Tried to allocate 428.00 MB on private pool. Use PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0 to disable upper limit for memory allocations (may cause system failure).

按 Ctrl + C 结束正在运行的模型，冒着机器可能突然崩溃的风险，按照提示信息执行命令取消内存限制

(base) markvivv@MBP basic_demo % PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0

内存限制错误提示信息如下：

(base) markvivv@MBP basic_demo % streamlit run web_demo_streamlit.py 

      👋 Welcome to Streamlit!

      If you’d like to receive helpful onboarding emails, news, offers, promotions,
      and the occasional swag, please enter your email address below. Otherwise,
      leave this field blank.

      Email:  

  You can find our privacy policy at https://streamlit.io/privacy-policy

  Summary:
  - This open source library collects usage statistics.
  - We cannot see and do not store information contained inside Streamlit apps,
    such as text, charts, images, etc.
  - Telemetry data is stored in servers in the United States.
  - If you'd like to opt out, add the following to ~/.streamlit/config.toml,
    creating that file if necessary:

    [browser]
    gatherUsageStats = false


  You can now view your Streamlit app in your browser.

  Local URL: http://localhost:8501
  Network URL: http://10.8.0.2:8501

  For better performance, install the Watchdog module:

  $ xcode-select --install
  $ pip install watchdog
            
tokenizer_config.json: 100%|████████████████████████████████████████████████████████████| 518/518 [00:00<00:00, 451kB/s]
tokenization_chatglm.py: 100%|█████████████████████████████████████████████████████| 13.0k/13.0k [00:00<00:00, 37.3MB/s]
A new version of the following files was downloaded from https://huggingface.co/THUDM/chatglm3-6b:
- tokenization_chatglm.py
. 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.
tokenizer.model: 100%|█████████████████████████████████████████████████████████████| 1.02M/1.02M [00:00<00:00, 3.52MB/s]
config.json: 100%|█████████████████████████████████████████████████████████████████| 1.32k/1.32k [00:00<00:00, 4.47MB/s]
configuration_chatglm.py: 100%|████████████████████████████████████████████████████| 2.33k/2.33k [00:00<00:00, 13.2MB/s]
A new version of the following files was downloaded from https://huggingface.co/THUDM/chatglm3-6b:
- configuration_chatglm.py
. 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.
modeling_chatglm.py: 100%|█████████████████████████████████████████████████████████| 55.7k/55.7k [00:00<00:00, 1.00MB/s]
quantization.py: 100%|█████████████████████████████████████████████████████████████| 14.7k/14.7k [00:00<00:00, 51.6MB/s]
A new version of the following files was downloaded from https://huggingface.co/THUDM/chatglm3-6b:
- quantization.py
. 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.
A new version of the following files was downloaded from https://huggingface.co/THUDM/chatglm3-6b:
- modeling_chatglm.py
- quantization.py
. 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.
model.safetensors.index.json: 100%|████████████████████████████████████████████████| 21.2k/21.2k [00:00<00:00, 7.74MB/s]
model-00001-of-00007.safetensors: 100%|████████████████████████████████████████████| 1.83G/1.83G [15:17<00:00, 1.99MB/s]
Downloading shards:  14%|████████▊                                                     | 1/7 [15:17<1:31:44, 917.50s/itError while downloading from https://cdn-lfs-us-1.huggingface.co/repos/01/5a/015a4eda6314fbcdb0aecc00e73f604e0f398b10ef843cf3e7bfcf8d0b9c1d7d/f88d7f69a3940711b87308eb20dd0544df22aff81134fa0d5160d3c859f5d321?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27model-00002-of-00007.safetensors%3B+filename%3D%22model-00002-of-00007.safetensors%22%3B&Expires=1707015811&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcwNzAxNTgxMX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzAxLzVhLzAxNWE0ZWRhNjMxNGZiY2RiMGFlY2MwMGU3M2Y2MDRlMGYzOThiMTBlZjg0M2NmM2U3YmZjZjhkMGI5YzFkN2QvZjg4ZDdmNjlhMzk0MDcxMWI4NzMwOGViMjBkZDA1NDRkZjIyYWZmODExMzRmYTBkNTE2MGQzYzg1OWY1ZDMyMT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=WrIM24-FutGC5aTXW55Ff4g-z5MO8K2NsIFjc7eRvXokY7fdHy4AdMQnVafWlpLWzEFBAosLvPSlR4VpXBUqBR%7EzSJZ7MEMqX6mT32Rj0eX0x8CfTVPUsOFu2T0nM1MNb0B7BYjDirjkjm2LUNnligb9znWwxYlchj6wEVV3I2UHh3IwmLdcUujmXiq9t07ZIzJ3tf39DEgRbjDgufdOHUO-gHQ%7Eb6bGWYhGRjpAog2U6P9CrzGNwIEIz6a6muh-raFzOukyi8Wxz2sys-HNprB5F1nsjahI3YhFLb6M6XyxWCFTCbPtTI8Yi24glkKArXD%7EZnyFcmZnNtGsnplEQg__&Key-Pair-Id=KCD77M1F0VK2B: HTTPSConnectionPool(host='cdn-lfs-us-1.huggingface.co', port=443): Read timed out.
Trying to resume download...
model-00002-of-00007.safetensors: 100%|████████████████████████████████████████████| 1.97G/1.97G [09:01<00:00, 3.21MB/s]
model-00002-of-00007.safetensors:  12%|█████▏                                      | 231M/1.97G [11:06<1:23:42, 346kB/s]
model-00003-of-00007.safetensors: 100%|████████████████████████████████████████████| 1.93G/1.93G [09:47<00:00, 3.28MB/s]
Downloading shards:  43%|███████████████████████████▍                                    | 3/7 [36:13<45:49, 687.47s/it]
model-00004-of-00007.safetensors:  42%|██████████████████▋                          | 755M/1.82G [04:13<05:18, 3.33MB/s]
model-00004-of-00007.safetensors: 100%|████████████████████████████████████████████| 1.82G/1.82G [09:31<00:00, 3.17MB/s]
model-00005-of-00007.safetensors: 100%|████████████████████████████████████████████| 1.97G/1.97G [10:47<00:00, 3.04MB/s]
model-00006-of-00007.safetensors: 100%|████████████████████████████████████████████| 1.93G/1.93G [09:40<00:00, 3.32MB/s]
model-00007-of-00007.safetensors: 100%|████████████████████████████████████████████| 1.05G/1.05G [05:37<00:00, 3.12MB/s]
Downloading shards: 100%|██████████████████████████████████████████████████████████████| 7/7 [1:11:55<00:00, 616.55s/it]
Loading checkpoint shards: 100%|██████████████████████████████████████████████████████████| 7/7 [00:20<00:00,  2.88s/it]
WARNING:root:Some parameters are on the meta device device because they were offloaded to the disk.

正常启动后，会自动使用浏览器打开 http://localhost:8501，然后就可以正常通过浏览器和大模型交互了，受限于硬件水平，响应非常慢。

四、运行情况

交互界面，注意红色内存报警，截图时已结束大模型进程，太慢了
交互界面，注意红色内存报警，截图时已结束大模型进程，太慢了
响应问题时，16G 的内存，使用量超过12G，GPU 功率10W 左右，可能 GPU 显存太小，没用起来
响应问题时，16G 的内存，使用量超过12G，GPU 功率10W 左右，可能 GPU 显存太小，没用起来

markvivv
关注
  • 7
    点赞
  • 踩
  • 7
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论
专栏目录
15年15寸MACBOOKPRO蓝牙驱动
11-06
15年15寸MACBOOKPRO蓝牙驱动亲测有效，提取对应驱动包蓝牙驱动程序！
记录｜M1 Pro mps跑模型LeNet和AlexNet
weixin_45041379的博客
10-09 1060
2022.10.9 记录M1 Pro mps跑模型
在搭载 M1 及 M2 芯片 MacBook 设备上玩 Stable Diffusion 模型
热门推荐
为了不折腾而去折腾的那些事
12-10 1万+
本篇文章，我们聊了如何使用搭载了 Apple Silicon 芯片（M1 和 M2 CPU）的 MacBook 设备上运行 Stable Diffusion 模型。
如何在本地部署chatGLM3
最美dee时光的博客
02-04 1609
ChatGLM3 是智谱AI和清华大学 KEG 实验室联合发布的对话预训练模型。更强大的基础模型。更完整的功能支持。更全面的开源序列。详细介绍参考官方README介绍。basic_demo: 基础demo（cli_demo和web_demo）composite_demo ： 综合demo（聊天、工具和代码解释器）finetune_demo：基础模型微调model：这个事自己创建的，将模型文件放在此目录下openai_api_demo: openapi的api接口demo。
基于MacBook Pro M1芯片运行chatglm2-6b大模型
最美dee时光的博客
01-22 1234
更强大的性能。更长的上下文。更高效的推理。更开放的协议。详细介绍参考官方README介绍。
Apple MacBook Pro A1502 820-4924-A 、820-3536-A 点位图
03-01
Apple MacBook Pro A1502 820-4924-A 、820-3536-A 点位图与点位图查看软件：BoardViewer点位软件
Macbook pro retina 15寸苹果笔记本电脑模型3D图纸.zip
09-14
Macbook pro retina 15寸苹果笔记本电脑模型3D图纸
Macbook pro 电路图 A1502 820-4924-a
02-28
Macbook Pro 电路图 对应主板型号是A1502 820-4924-a
Apple MacBook Pro 15 A1707 电路原理图
11-25
Apple MacBook Pro 15 A1707 电路原理图，
使用 MacBook Pro M1 16G 运行 Llama 2 7B (Apple Silicon 通用方法)
weixin_45063926的博客
11-04 738
这篇文章用于记录我在 MacBook Pro M1 16G 中配置 Llama 2 7B 环境的全流程。这一方法适用于所有 Apple Silicon 系列，为未来运行更大模型的设备提供参考。
【ChatGLM2-6B微调】6GB显存实现ChatGLM2-6B大模型微调！
weixin_45666317的博客
08-15 3256
6GB显存配置实现ChatGLM2-6B大模型微调！使用官方项目包中的P-Tuning V2做微调实践。
注意力机制略解
cqbzcsq的博客
04-29 1160
本文简要地介绍了注意力机制，Q、K、V矩阵的含义，注意力评分函数的计算方式，并提及了Transformer的相关内容
【 书生·浦语大模型实战营】作业（六）：Lagent & AgentLego 智能体应用搭建
最新发布
专注大数据与人工智能技术分享，欢迎私信加群互相学习！
05-03 715
本篇笔记内容主要为 【书生·浦语大模型实战营】作业（六）：Lagent & AgentLego 智能体应用搭建智能体的作业 ，主要对智能体应用理论部分及具体搭建流程详细介绍，并分别进行实战应用及可视化展示，欢迎大家交流学习！
Perfectly Clear Workbench for mac/win：让图像清晰不再是难题
2401_82627223的博客
04-27 680
Perfectly Clear Workbench是一款功能强大、操作简便的图像清晰处理软件。它不仅能够满足专业摄影师的高标准需求，也能让业余爱好者轻松提升作品质量。
Transformers：它们如何转换您的数据？
gongdiwudu的专栏
05-01 812
在快速发展的人工智能和机器学习领域，一项创新因其对我们处理、理解和生成数据的方式产生深远影响而脱颖而出：Transformers。Transformer 彻底改变了自然语言处理 （NLP） 及其他领域，为当今一些最先进的 AI 应用程序提供动力。但究竟什么是变形金刚，它们如何以如此开创性的方式转换数据？本文揭开了 Transformer 模型内部工作的神秘面纱，重点介绍了编码器架构。我们将首先在 Python 中实现 Transformer 编码器，分解其主要组件。然后，我们将可视化 Transfor
macos如何安装Tesseract软件and常规应用及问题处理
LYX_WIN
04-28 421
Homebrew 在 macOS 13 上可能会遇到一些构建失败的情况，因为它是一个预发布版本，不是稳定版本，可能会有一些兼容性问题。3.安装 pytesseract 之后，您还需要安装 Tesseract OCR 的二进制文件。4.安装完成后，您可以使用 pytesseract 库在 Python 中调用 Tesseract OCR 进行文字识别。2.安装完成后，可以在终端或命令提示符中输入以下命令测试 Tesseract 是否安装成功。安装完成后，可以使用 Tesseract 进行文字识别等操作。
su03t语音模块烧录识别不出问题解决方法
weixin_49387645的博客
05-02 1000
su03t语音sdk烧录无法识别问题
神经网络中多层卷积的作用
金石软件
04-27 815
在神经网络中采用多层卷积的目的是为了逐步提取和组合图像的抽象特征，从而更有效地学习数据的表示并执行复杂的任务。不同层的卷积具有不同的作用，从较低层次的特征（例如边缘、纹理）到较高层次的抽象特征（例如物体部件、整体物体）逐渐提取。通过多层卷积，网络能够从原始图像中逐步学习并提取更加抽象和语义丰富的特征，从而实现对输入数据更准确和有效的建模和处理。
ChatGLM2-6B量化
07-28
ChatGLM2-6B量化是指将ChatGLM2-6B模型使用模型量化技术进行压缩和优化，以减少模型的显存占用和部署门槛。在量化后，ChatGLM2-6B模型的显存占用可以进一步降低到10GB（INT8）和6GB（INT4），使得该模型可以在消费级显卡上进行部署。量化后的ChatGLM2-6B模型仍然保持了较长的序列长度，达到32K，支持更长的对话和应用。此外，ChatGLM2-6B模型还通过使用监督微调、反馈自助和人类反馈强化学习等方式，使得模型具备理解人类指令意图的能力，并且输出格式为markdown，方便展示。\[3\] #### 引用[.reference_title] - *1* *3* [ChatGLM2-6B、ChatGLM-6B 模型介绍及训练自己数据集实战](https://blog.csdn.net/dream_home8407/article/details/130099656)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^control_2,239^v3^insert_chatgpt"}} ] [.reference_item] - *2* [macbook安装chatglm2-6b](https://blog.csdn.net/qq_26819733/article/details/131563492)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^control_2,239^v3^insert_chatgpt"}} ] [.reference_item] [ .reference_list ]

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

markvivv

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付：¥1
获取中
扫码支付

您的余额不足，请更换扫码支付或充值

打赏作者

实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值