mistralai

/

Mistral-7B-v0.3

like 271

I am a newbie too and I still cannot download some models, even though it shows "You have been granted access to this model" on some of the repos. Anyway, I got access to some of the models in these steps:
(1) signing in your hugging face account in the terminal.
(2) In the account settings - access tokens - Repositories permissions, select those models I want to download.

#xuzhe118
this seemed to work for me,
Appreciate the reply !

(1) signing in your hugging face account in the terminal.
huggingface-cli login
Enter your token

Home page to get authorization

(base) qihao@qihao-B760M-DS3H:~/Ai$ huggingface-cli login

    _|    _|  _|    _|    _|_|_|    _|_|_|  _|_|_|  _|      _|    _|_|_|      _|_|_|_|    _|_|      _|_|_|  _|_|_|_|
    _|    _|  _|    _|  _|        _|          _|    _|_|    _|  _|            _|        _|    _|  _|        _|
    _|_|_|_|  _|    _|  _|  _|_|  _|  _|_|    _|    _|  _|  _|  _|  _|_|      _|_|_|    _|_|_|_|  _|        _|_|_|
    _|    _|  _|    _|  _|    _|  _|    _|    _|    _|    _|_|  _|    _|      _|        _|    _|  _|        _|
    _|    _|    _|_|      _|_|_|    _|_|_|  _|_|_|  _|      _|    _|_|_|      _|        _|    _|    _|_|_|  _|_|_|_|

    To login, `huggingface_hub` requires a token generated from https://huggingface.co/settings/tokens .
Enter your token (input will not be visible):
Add token as git credential? (Y/n) y

app.py

from huggingface_hub import snapshot_download
from pathlib import Path

mistral_models_path = Path.home().joinpath('mistral_models', '7B-v0.3')
mistral_models_path.mkdir(parents=True, exist_ok=True)

snapshot_download(repo_id="mistralai/Mistral-7B-v0.3", use_auth_token=True,
                  allow_patterns=["params.json", "consolidated.safetensors", "tokenizer.model.v3"],
                  local_dir=mistral_models_path)

 python app.py

params.json: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 202/202 [00:00<00:00, 616kB/s]
tokenizer.model.v3: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 587k/587k [00:00<00:00, 2.59MB/s]
tokenizer.model.v3: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 587k/587k [00:00<00:00, 2.60MB/s]
consolidated.safetensors:  24%|████████████████████████████████▎                                                                                                     | 3.49G/14.5G [22:17<1:10:29, 2.60MB/s]