I was working on this tutorial NeMo/tutorials/llm/function_calling/nemo2-chat-sft-function-calling.ipynb at main · NVIDIA/NeMo · GitHub . After finetuning the model I managed to successfully evaluate with api.generate function. However, when I tried to generate response with huggingface formatted model, model does not generate anything. I can convert my other finetuned models into huggingface and deploy them without an error but I couldn’t manage to make this work.
1 Like
Hi @yusufkurt , I wonder what NeMo Docker image are you using here ?
I would suggest to use the latest release container for doing the finetuning: nvcr.io/nvidia/nemo:25.07
thanks @aot . I managed to make it work by switching from peft to sft in nemo:25.07.00 .
1 Like
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.