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

break change for v1.2.1 #241

Open
1 of 4 tasks
lloydzhou opened this issue Apr 16, 2024 · 1 comment
Open
1 of 4 tasks

break change for v1.2.1 #241

lloydzhou opened this issue Apr 16, 2024 · 1 comment

Comments

@lloydzhou
Copy link

System Info

{
  "model_id":"thenlper/gte-small-zh",
  "model_sha":null,
  "model_dtype":"float32",
  "model_type":{
    "embedding": {
      "pooling":"cls"
    }
  },
  "max_concurrent_requests":512,
  "max_input_length":512,
  "max_batch_tokens":16384,
  "max_batch_requests":null,
  "max_client_batch_size":32,
  "auto_truncate":true,
  "tokenization_workers":1,
  "version":"1.2.1",
  "sha":"8927093ddda438fee975bd43898beb88f24417eb",
  "docker_label":"sha-8927093"
}

Information

  • Docker
  • The CLI directly

Tasks

  • An officially supported command
  • My own modifications

Reproduction

  1. must set env "HF_MODEL_ID"
  2. change default port from 80 to 8080

https://github.com/huggingface/text-embeddings-inference/blob/v1.2.1/sagemaker-entrypoint.sh

Expected behavior

when i upgrage from ghcr.io/huggingface/text-embeddings-inference:cpu-1.2 to ghcr.io/huggingface/text-embeddings-inference:cpu-1.2.1 my service can not start.

i want to keep the default config.

@OlivierDehaene
Copy link
Member

This should not have hapened and is fixed on v1.2.2.
The dockerfile was wrongly updated.

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

No branches or pull requests

2 participants