Add cerebras/btlm-3b-8k-base

[natke]

Name of the feature In general, the feature you want added should be supported by HuggingFace's transformers library:

• If requesting a model, it must be listed here.
• If requesting a pipeline, it must be listed here.
  • If requesting a task, it must be listed here.

Add the https://huggingface.co/cerebras/btlm-3b-8k-base model to transformers.js

Reason for request Why is it important that we add this feature? What is your intended use case? Remember, we are more likely to add support for models/pipelines/tasks that are popular (e.g., many downloads), or contain functionality that does not exist (e.g., new input type).

Provides 7B model performance in a 3B model (according to the model card)

Additional context Add any other context or screenshots about the feature request here.

[xenova]

Hi there 👋 Thanks for the request!

Unfortunately, the architecture is not yet supported by (1) Transformers without trust_remote_code=True or (2) Optimum which is the library we use to convert to ONNX.

Please make feature requests to those library first, and then we will add support here! 🤗