Anindyadeep

I see, but internally hf module internally uses AutoModel module to instantiate weights. So can you explain me why we require to use already loaded model to dspy instead of...

can you please share the full code for the loading process and your approach? Would appreciate this.

Hey @pawanGithub10 I have started to raise a PR by seeing the issue that you faced. Here are some of the cases of loading models would look like: ```python from...

That is awesome, also @marella I have one last question after which we can close this issue, can we convert a hugging face model to ggml through CTransformers. What I...

Yeah and thanks for clarifying and we can close this issue. Thanks

Sure, let me check that out

@gforsyth , Can you please provide me more details or the link of that (in the documentation) where I can refer to, about registering a function with the backend and...

Thanks @OmriLevyTau, but yes this feature would be super useful.

> @Anindyadeep can you check if they support llama2/mistral? Otherwise let's close the issue Yes we need to put this in medium priority, since it is an engine

> @Anindyadeep can you update the issue with "check flash attention v2 support"? Done