Hugging Face 的应用

git lfs install#模型会下载到本地目录，并不在hugging face的标准管理目录里，可能会导致后续Transformers库重新下载git clone https://huggingface.co/google/owlv2-base-patch16-ensemble

python -m pip install huggingface_hub# 需要开启代理huggingface-cli login

python -m pip install huggingface_hub[hf_transfer]
#缺点：目前还不支持代理，导致下载大文件可能有时候更慢。export HF_HUB_ENABLE_HF_TRANSFER=1
huggingface-cli download gpt2 config.json

(base) hogwarts: llama seveniruby$ huggingface-cli -husage: huggingface-cli <command> [<args>]
positional arguments:  {env,login,whoami,logout,repo,upload,download,lfs-enable-largefiles,lfs-multipart-upload,scan-cache,delete-cache}                        huggingface-cli command helpers    env                 Print information about the environment.    login               Log in using a token from huggingface.co/settings/tokens    whoami              Find out which huggingface.co account you are logged in as.    logout              Log out    repo                {create, ls-files} Commands to interact with your huggingface.co repos.    upload              Upload a file or a folder to a repo on the Hub    download            Download files from the Hub    lfs-enable-largefiles                        Configure your repository to enable upload of files > 5GB.    lfs-multipart-upload                        Command will get called by git-lfs, do not call it directly.    scan-cache          Scan cache directory.    delete-cache        Delete revisions from the cache directory.
options:  -h, --help            show this help message and exit

huggingface-cli loginhuggingface-cli download gpt2huggingface-cli download gpt2 config.jsonhuggingface-cli download gpt2 --revision main

from huggingface_hub import hf_hub_downloadhf_hub_download(repo_id="google/pegasus-xsum", filename="config.json")
from huggingface_hub import hf_hub_downloadhf_hub_download(    repo_id="google/pegasus-xsum",    filename="config.json",    revision="4d33b01d79672f27f001f6abade33f22d993b151")

#文件快照./snapshots./snapshots/187d69aae616814bc1386bdfe38e256518d17637./snapshots/187d69aae616814bc1386bdfe38e256518d17637/added_tokens.json./snapshots/187d69aae616814bc1386bdfe38e256518d17637/tokenizer_config.json./snapshots/187d69aae616814bc1386bdfe38e256518d17637/special_tokens_map.json./snapshots/187d69aae616814bc1386bdfe38e256518d17637/config.json./snapshots/187d69aae616814bc1386bdfe38e256518d17637/README.md./snapshots/187d69aae616814bc1386bdfe38e256518d17637/merges.txt./snapshots/187d69aae616814bc1386bdfe38e256518d17637/.gitattributes./snapshots/187d69aae616814bc1386bdfe38e256518d17637/pytorch_model.bin./snapshots/187d69aae616814bc1386bdfe38e256518d17637/vocab.json./snapshots/187d69aae616814bc1386bdfe38e256518d17637/preprocessor_config.json#真正的文件缓存./blobs./blobs/76e821f1b6f0a9709293c3b6b51ed90980b3166b./blobs/69feda8b53b1c9e2a85ae756bf58c120c3c1b4b4a4d97d4876578c1809a63d76./blobs/39808ac074d69141c0b2f065d16f56dfa5194cac./blobs/1c4c373d81adc0c63bb3368a89f4a92574395c2c./blobs/b24bfd579e8682df31c7794a3e1c3ef6a9a22a7a./blobs/5ff4ac542d5e800dd3aadbdcda354868b5f24ddd./blobs/a6344aac8c09253b3b630fb776ae94478aa0275b./blobs/dfc1049705d082052a81e7d18bde6d11fc137a0d./blobs/ee790e862e5a47398da080893272d3c2b76cf0e5./blobs/469be27c5c010538f845f518c4f5e8574c78f7c8
#分支，指定分支有助于解决重复下载问题./refs./refs/main

pip install transformers datasetspip install torchpip install tensorflow
#测试python -c "from transformers import pipeline; print(pipeline('sentiment-analysis')('we love you'))"
pipeline api 使用pipe = pipeline("text-classification")pipe("This restaurant is awesome")
#输出[{'label': 'POSITIVE', 'score': 0.9998743534088135}]

pipe = pipeline(model="FacebookAI/roberta-large-mnli")pipe("This restaurant is awesome")
#输出[{'label': 'NEUTRAL', 'score': 0.7313136458396912}]

def test_zero_shot_object_detector():    with open('coco_sample.png', mode='rb') as f:        image = Image.open(f)        object_detector = pipeline('object-detection', revision='main')
        predictions = object_detector(image)        print(json.dumps(predictions, indent=2, ensure_ascii=False))
#输出[  {    "score": 0.9982201457023621,    "label": "remote",    "box": {      "xmin": 40,      "ymin": 70,      "xmax": 175,      "ymax": 117    }  },  {    "score": 0.9960021376609802,    "label": "remote",    "box": {      "xmin": 333,      "ymin": 72,      "xmax": 368,      "ymax": 187    }  },  {    "score": 0.9954745173454285,    "label": "couch",    "box": {      "xmin": 0,      "ymin": 1,      "xmax": 639,      "ymax": 473    }  },  {    "score": 0.9988006353378296,    "label": "cat",    "box": {      "xmin": 13,      "ymin": 52,      "xmax": 314,      "ymax": 470    }  },  {    "score": 0.9986783862113953,    "label": "cat",    "box": {      "xmin": 345,      "ymin": 23,      "xmax": 640,      "ymax": 368    }  }]

model=tiiuae/falcon-7b-instructvolume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.4 --model-id $model
model=teknium/OpenHermes-2.5-Mistral-7Bvolume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.4 --model-id $model

curl 127.0.0.1:8080/generate \    -X POST \    -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":20}}' \    -H 'Content-Type: application/json'

import requests
headers = {    "Content-Type": "application/json",}
data = {    'inputs': 'What is Deep Learning?',    'parameters': {        'max_new_tokens': 20,    },}
response = requests.post('http://127.0.0.1:8080/generate', headers=headers, json=data)print(response.json())# {'generated_text': '\n\nDeep Learning is a subset of Machine Learning that is concern