Everytime when I try to downloat meta-llama/Llama-2-7b-chat-hf model i get error

[Chovanec]

Describe the bug

Everytime when I try to downloat meta-llama/Llama-2-7b-chat-hf model i get this error:

Is there an existing issue for this?

• [X] I have searched the existing issues

Reproduction

try to install meta-llama/Llama-2-7b-chat-hf

Screenshot

Logs

Traceback (most recent call last):

File "C:\text-generation-webui-main\modules\ui_model_menu.py", line 244, in download_model_wrapper


links, sha256, is_lora, is_llamacpp = downloader.get_download_links_from_huggingface(model, branch, text_only=False, specific_file=specific_file)

                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\text-generation-webui-main\download-model.py", line 74, in get_download_links_from_huggingface


r.raise_for_status()
File "C:\text-generation-webui-main\installer_files\env\Lib\site-packages\requests\models.py", line 1021, in raise_for_status


raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/api/models/meta-llama/Llama-2-7b-chat-hf/tree/main

System Info

win11, rtx 2060 nvidia

[sandyis]

@Chovanec

use a different model like https://huggingface.co/NousResearch/Nous-Hermes-llama-2-7b which is not gated and optimised OR

• you need to first register with Facebook to get link for download https://ai.meta.com/resources/models-and-libraries/llama-downloads/
• make sure you have a account in hugging face with same email id
• then go to hugging face https://huggingface.co/meta-llama/Llama-2-7b-hf
• make sure you see
• 

[sandyis]

Or you can get this model https://huggingface.co/TheBloke/Llama-2-7B-Chat-GPTQ us this in download field TheBloke/Llama-2-7b-Chat-GPTQ:gptq-4bit-32g-actorder_True

[ivanbaldo]

To download that model, we need to specify the HuggingFace Token to Text Generation WebUI, but it doesn't have that option in the UI nor in the command line. The solution I found is to set the HF_TOKEN environment variable before running the server. It would be nice if someday some of these features could be added to Text Generation WebUI:

• be able to specify the token on the web UI.
• to automatically use the token from the $HOME/.cache/huggingface/token file.
• be compatible with $HOME/.cache/huggingface/ so that all of the already downloaded models from there get added to the list automatically and if a new model is downloaded then it gets saved/cached there with the format compatible with the HF Transformers model downloader/loaders. Thanks!!!

[github-actions[bot]]

This issue has been closed due to inactivity for 2 months. If you believe it is still relevant, please leave a comment below. You can tag a developer in your comment.