meta-llama / llama-models

Utilities intended for use with Llama models.
Other
4.88k stars 838 forks source link

Failed to download the Llama-2-13b-chat #215

Closed vinilvadakkepurakkal closed 1 week ago

vinilvadakkepurakkal commented 1 week ago

(llama2) C:\Users\vinilv>llama model download --source meta --model-id Llama-2-13b-chat Please provide the signed URL for model Llama-2-13b-chat you received via email after visiting https://www.llama.com/llama-downloads/ (e.g., https://llama3-1.llamameta.net/*?Policy...): https://download.llamameta.net/*?Policy=eyJTdGF0ZW1lbnQiOlt7InVuaXF1ZV9oYXNoIjoid3F4OWk5cGJwejd2dzQyMXM5NGtrbjBzIiwiUmVzb3VyY2UiOiJodHRwczpcL1wvZG93bmxvYWQubGxhbWFtZXRhLm5ldFwvKiIsIkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTczMTI5NjgyNn19fV19&Signature=e%7Ejb4MWOSFJFti2ifc0c-ERN47IAOwtebku1Z%7EstnAxrRq2UUTFToCossmtbfAJQnMz7jeYuF5pbPeEJP1nFcjus46QrnnaOPI2HlwXfavrjSiF-bFdu38o0snbrRW7UpFK8UossjCeofUyXFQL43YymaPCdsehOZoDDWdg1ISG1nsnakSLtl2rOJt3FrWjEwi5XS6zS6c%7EeajqSSzPTueaobCDDfqf7-%7EenNCfoNi90Iwr18Vp%7ExzUxVSbSdhTqmHerQORwQ8BJMtWyN1MwSSy0ZENZu8H9s1YX7Vhhf8yOuc8oCFwP7QC0qbFvgMvAUF8NHaAh8-rLkZAXh%7EYhNg__&Key-Pair-Id=K15QRJLYKIFSLZ&Download-Request-ID=1180414533621479 Downloading checklist.chk... Already downloaded C:\Users\vinilv\.llama\checkpoints\Llama-2-13b-chat\checklist.chk, skipping... Downloading tokenizer.model... Traceback (most recent call last): File "C:\Users\vinilv\AppData\Local\anaconda3\envs\llama2\lib\runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "C:\Users\vinilv\AppData\Local\anaconda3\envs\llama2\lib\runpy.py", line 86, in _run_code exec(code, run_globals) File "C:\Users\vinilv\AppData\Local\anaconda3\envs\llama2\Scripts\llama.exe__main.py", line 7, in sys.exit(main()) File "C:\Users\vinilv\AppData\Local\anaconda3\envs\llama2\lib\site-packages\llama_stack\cli\llama.py", line 44, in main parser.run(args) File "C:\Users\vinilv\AppData\Local\anaconda3\envs\llama2\lib\site-packages\llama_stack\cli\llama.py", line 38, in run args.func(args) File "C:\Users\vinilv\AppData\Local\anaconda3\envs\llama2\lib\site-packages\llama_stack\cli\download.py", line 177, in run_download_cmd _meta_download(model, meta_url, info) File "C:\Users\vinilv\AppData\Local\anaconda3\envs\llama2\lib\site-packages\llama_stack\cli\download.py", line 136, in _meta_download asyncio.run(downloader.download()) File "C:\Users\vinilv\AppData\Local\anaconda3\envs\llama2\lib\asyncio\runners.py", line 44, in run return loop.run_until_complete(main) File "C:\Users\vinilv\AppData\Local\anaconda3\envs\llama2\lib\asyncio\base_events.py", line 649, in run_until_complete return future.result() File "C:\Users\vinilv\AppData\Local\anaconda3\envs\llama2\lib\site-packages\llama_stack\cli\download.py", line 266, in download await self.get_file_info(client) File "C:\Users\vinilv\AppData\Local\anaconda3\envs\llama2\lib\site-packages\llama_stack\cli\download.py", line 255, in get_file_info response.raise_for_status() File "C:\Users\vinilv\AppData\Local\anaconda3\envs\llama2\lib\site-packages\httpx_models.py", line 761, in raise_for_status raise HTTPStatusError(message, request=request, response=self) httpx.HTTPStatusError: Client error '403 Forbidden' for url 'https://download.llamameta.net/llama-2-13b-chat/tokenizer.model?Policy=eyJTdGF0ZW1lbnQiOlt7InVuaXF1ZV9oYXNoIjoid3F4OWk5cGJwejd2dzQyMXM5NGtrbjBzIiwiUmVzb3VyY2UiOiJodHRwczpcL1wvZG93bmxvYWQubGxhbWFtZXRhLm5ldFwvKiIsIkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTczMTI5NjgyNn19fV19&Signature=e%7Ejb4MWOSFJFti2ifc0c-ERN47IAOwtebku1Z%7EstnAxrRq2UUTFToCossmtbfAJQnMz7jeYuF5pbPeEJP1nFcjus46QrnnaOPI2HlwXfavrjSiF-bFdu38o0snbrRW7UpFK8UossjCeofUyXFQL43YymaPCdsehOZoDDWdg1ISG1nsnakSLtl2rOJt3FrWjEwi5XS6zS6c%7EeajqSSzPTueaobCDDfqf7-%7EenNCfoNi90Iwr18Vp%7ExzUxVSbSdhTqmHerQORwQ8BJMtWyN1MwSSy0ZENZu8H9s1YX7Vhhf8yOuc8oCFwP7QC0qbFvgMvAUF8NHaAh8-rLkZAXh%7EYhNg&Key-Pair-Id=K15QRJLYKIFSLZ&Download-Request-ID=1180414533621479' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/403

(llama2) C:\Users\vinilv>

adamtcdev commented 1 week ago

Try to download the model using Hugging Face. https://huggingface.co/meta-llama/Llama-2-13b-chat https://huggingface.co/meta-llama/Llama-2-13b-chat-hf

varunfb commented 1 week ago

Your URL might have expired depending. Can you try the following

  1. pip install llama-stack -U
  2. Re-registering at https://www.llama.com/llama-downloads and download using the latest URL
  3. Make sure you are using the right model-id. You can view the list of models available for download using llama model list

Outside of this, encourage using the latest models from Llama 3, 3.1 and 3.2 versions

varunfb commented 1 week ago

Please re-open the issue if it is not working.

ypwang61 commented 4 days ago

I also have this problem even with the most current url. Have you fix this problem?