I trying to apply a Chatbot with speech recognition and speech replay.
I successfully used the models of NeMo models for it, like ASM and TTS, but cant find a way to integrate to it LLama 7b model.
I ran the Llama model with hugging face (transformers package).
I want to convert it to run it with NeMo too and make all the models run on GPU from one package.
will appreciate any help 😁