Johnno1011

Results 7 comments of Johnno1011

Hi! The LLM has to worry about generating the JSON as well as the fields in the schema, I think that's the issue. Grammar works 99% of the time really...

Ah I see what I was not doing right now, thanks for sharing this example and so quickly too! It looks like this is for distributed and tensor parallelism in...

You could still use the openai.chat.completions.create but reset the chat history each time? For example: ``` def generate(prompt: str) -> ChatCompletion: messages = [ { "role": "system", "content": "You are...

I was able to resolve this by adding "model_type": "XLMRobertaModel" to the config.json of the downloaded model. Not a long term solution, but also not caused by TEI - the...

Hey guys, seen the PRs related to this that were in the recent release. It doesn't look like this has fixed the issue for me. I'm using HuggingFaceEndpoint wrapped up...

Also experienced the same with this model, whether using grammar or just attempting to use the function_calling functionality