Sentencetransformers URL

[mforell]

LocalAI version:

quay.io/go-skynet/local-ai:master-cublas-cuda11-ffmpeg

Describe the bug

Trying to use backend: sentencetransformers.

The yaml we use:

- url: OUR_LINK_TO_THE_GALLERY/base.yaml
  name: text-embedding-all-miniLM-L6
  license: mit
  urls:
    - https://huggingface.co/skeskinen/ggml
  tags:
    - license:mit
    - region:us
  overrides:
    parameters:
        model: all-MiniLM-L12-v2/ggml-model-q4_0.bin
    embeddings: true
    backend: sentencetransformers
  files:
    - filename: all-MiniLM-L6-v2/ggml-model-q4_0.bin
      sha256: ""
      uri: https://huggingface.co/skeskinen/ggml/resolve/main/all-MiniLM-L6-v2/ggml-model-q4_0.bin

When we try to access the model, we get the Error Not Found for url: https://huggingface.co/api/models/all-MiniLM-L12-v2/ggml-model-q4_0.bin.\ I t appears that a point is added to the url param and the model cannot be found.

The generated yaml file looks like:

backend: sentencetransformers
context_size: 1024
embeddings: true
name: text-embedding-all-miniLM-L6
parameters:
  model: "all-MiniLM-L12-v2/ggml-model-q4_0.bin"

The complete response with the error:
Response:

{
	"error": {
		"code": 500,
		"message": "could not load model (no success): Unexpected err=RepositoryNotFoundError('401 Client Error. (Request ID: Root=1-6565b896-57b5d77f3f3e5fe4797ea763;3d39a4f7-c62a-42f4-b473-7866a02c0bb2)\\n\\nRepository Not Found for url: https://huggingface.co/api/models/all-MiniLM-L12-v2/ggml-model-q4_0.bin.\\nPlease make sure you specified the correct `repo_id` and `repo_type`.\\nIf you are trying to access a private or gated repo, make sure you are authenticated.\\nInvalid username or password.'), type(err)=<class 'huggingface_hub.utils._errors.RepositoryNotFoundError'>",
		"type": ""
	}
}

To Reproduce

Use the attached yamls.
Expected behavior

The point should not be added to the url param when making a request.
Logs

Additional context

[localai-bot]

⚠️⚠️⚠️⚠️⚠️

Hi! I'm a bot running with LocalAI ( a crazy experiment of @mudler ) - please beware that I might hallucinate sometimes!

but.... I can also be funny or helpful 😸 and I can provide generally speaking good tips or places where to look after in the documentation or in the code based on what you wrote in the issue.

Don't engage in conversation with me,
I don't support (yet) replying!

⚠️⚠️⚠️⚠️⚠️

ERROR: The prompt size exceeds the context window size and cannot be processed.

Sources:

• https://github.com/go-skynet/LocalAI/tree/master/examples/autoGPT/README.md
• https://github.com/go-skynet/LocalAI/tree/master/docs/content/features/embeddings.md
• https://localai.io/features/embeddings/index.html

[mudler]

did you tried following https://localai.io/features/embeddings/index.html ? you need to specify a huggingface repository id, not a local file

[mforell]

Thank you very much. That has solved my problem. And thank you very much for your great work, much appreciated