Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

LORAX_USE_GLOBAL_HF_TOKEN is not applied at the first time of calling adapter from huggingface private hub #541

Open
2 of 4 tasks
monologg opened this issue Jul 16, 2024 · 0 comments · May be fixed by #542
Open
2 of 4 tasks

Comments

@monologg
Copy link

System Info

ghcr.io/predibase/lorax:24cb494

Information

  • Docker
  • The CLI directly

Tasks

  • An officially supported command
  • My own modifications

Reproduction

  • I've set HUGGING_FACE_HUB_TOKEN as environment when running docker container
  • Also set LORAX_USE_GLOBAL_HF_TOKEN=1 as environment
  • I'm pulling adapter from huggingface private hub.
curl http://XXXX/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "PRIVATE_HF_HUB_PATH", 
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant who gives detailed informations"
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'

I've got the error below.

{"error":"Request failed during generation: Server error: No valid adapter config file found: tried None and None","error_type":"generation"}%

Reason why this happens

CleanShot 2024-07-16 at 13 01 13@2x

CleanShot 2024-07-16 at 13 01 59@2x

CleanShot 2024-07-16 at 13 02 19@2x

Expected behavior

I should return the result correctly even though I don't send api_token on request

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
1 participant