00079-Hugging Face 杂项

前言

Hugging Face 的官网地址为：https://huggingface.co/ 。

镜像网站: https://hf-mirror.com/

操作系统：Windows 10 专业版

参考文档

1. Save a model
2. Cache setup
3. Fetch models and tokenizers to use offline
4. 全网最好解决中国hugggingface.co无法访问问题

模型缓存位置

transformers

source link: https://huggingface.co/docs/transformers/installation#cache-setup

1. 编辑 ~/.bashrc:

vim ~/.bashrc

2. 在文件中添加如下内容：

export HUGGINGFACE_HUB_CACHE=/data/.cache/huggingface/hub

3. 保存退出后，运行以下命令使设置生效：

source ~/.bashrc

modelscope

source link: https://modelscope.cn/docs/%E6%A8%A1%E5%9E%8B%E7%9A%84%E4%B8%8B%E8%BD%BD

1. 编辑 ~/.bashrc:

vim ~/.bashrc

2. 在文件中添加如下内容：

export MODELSCOPE_CACHE=/data/.cache/modelscope

3. 保存退出后，运行以下命令使设置生效：

source ~/.bashrc

镜像网站

源教程地址: https://blog.csdn.net/mar1111s/article/details/137179180 .

设置环境变量方法如下:

import os
os.environ["HF_ENDPOINT"] = "https://hf-mirror.com"

---

Linux 运行下面的命令或者将其写入 ~/.bashrc。

1. 编辑 ~/.bashrc:

vim ~/.bashrc

2. 在文件中添加如下内容：

export HF_ENDPOINT=https://hf-mirror.com

3. 保存退出后，运行以下命令使设置生效：

source ~/.bashrc

下载模型

"""
link1: https://huggingface.co/meta-llama/Llama-3.2-1B
link2: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
link3: https://modelscope.cn/models/LLM-Research/Llama-3.2-1B-Instruct
"""

import torch
from transformers import pipeline
from modelscope import snapshot_download

model_dir = snapshot_download('LLM-Research/Llama-3.2-1B-Instruct')

pipe = pipeline(
    "text-generation",
    model=model_dir,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

terminators = [
    pipe.tokenizer.eos_token_id,
    pipe.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipe(
    messages,
    max_new_tokens=256,
    eos_token_id=terminators,
)

print(outputs[0]["generated_text"][-1]["content"])

print(f"{'*'*42}")

print(pipe("The key to life is", max_new_tokens=100, eos_token_id=terminators))

保存模型

源教程地址: https://huggingface.co/docs/transformers/quicktour#save-a-model .

Once your model is fine-tuned, you can save it with its tokenizer using PreTrainedModel.save_pretrained():

pt_save_directory = "./pt_save_pretrained"
tokenizer.save_pretrained(pt_save_directory)
pt_model.save_pretrained(pt_save_directory)

When you are ready to use the model again, reload it with PreTrainedModel.from_pretrained():

pt_model = AutoModelForSequenceClassification.from_pretrained("./pt_save_pretrained")

Github Issues

‘_datasets_server’ from ‘datasets.utils’

source link: https://github.com/modelscope/modelscope/issues/836

安装 datasets:

$ pip install datasets==2.18.0

更多内容

缓存设置

源教程地址: https://huggingface.co/docs/transformers/installation#cache-setup .

Pretrained models are downloaded and locally cached at: ~/.cache/huggingface/hub. This is the default directory given by the shell environment variable TRANSFORMERS_CACHE. On Windows, the default directory is given by C:\Users\username\.cache\huggingface\hub. You can change the shell environment variables shown below - in order of priority - to specify a different cache directory:

1. Shell environment variable (default): HUGGINGFACE_HUB_CACHE or TRANSFORMERS_CACHE.
2. Shell environment variable: HF_HOME.
3. Shell environment variable: XDG_CACHE_HOME + /huggingface.

离线使用

源教程地址: https://huggingface.co/docs/transformers/installation#fetch-models-and-tokenizers-to-use-offline .

Another option for using 🤗 Transformers offline is to download the files ahead of time, and then point to their local path when you need to use them offline. There are three ways to do this:

• Download a file through the user interface on the Model Hub by clicking on the ↓ icon.

• Use the PreTrainedModel.from_pretrained() and PreTrainedModel.save_pretrained() workflow:

  1. Download your files ahead of time with PreTrainedModel.from_pretrained():

     from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
     
     tokenizer = AutoTokenizer.from_pretrained("bigscience/T0_3B")
     model = AutoModelForSeq2SeqLM.from_pretrained("bigscience/T0_3B")

  2. Save your files to a specified directory with PreTrainedModel.save_pretrained():

     tokenizer.save_pretrained("./your/path/bigscience_t0")
     model.save_pretrained("./your/path/bigscience_t0")

  3. Now when you’re offline, reload your files with PreTrainedModel.from_pretrained() from the specified directory:

     tokenizer = AutoTokenizer.from_pretrained("./your/path/bigscience_t0")
     model = AutoModel.from_pretrained("./your/path/bigscience_t0")

• Programmatically download files with the huggingface_hub library:

  1. Install the huggingface_hub library in your virtual environment:

     python -m pip install huggingface_hub

  2. Use the hf_hub_download function to download a file to a specific path. For example, the following command downloads the config.json file from the T0 model to your desired path:

     from huggingface_hub import hf_hub_download
     
     hf_hub_download(repo_id="bigscience/T0_3B", filename="config.json", cache_dir="./your/path/bigscience_t0")

Once your file is downloaded and locally cached, specify it’s local path to load and use it:

from transformers import AutoConfig

config = AutoConfig.from_pretrained("./your/path/bigscience_t0/config.json")

See the How to download files from the Hub section for more details on downloading files stored on the Hub.

结语

第七十九篇博文写完，开心！！！！

今天，也是充满希望的一天。