Text Generation
Transformers
Safetensors
PyTorch
nvidia
conversational

What inference setting for coding?

#25
by akierum - opened

Why always there are no parameters given?

Temperature?
Top K
Repeat
Min P
Top P

Hello Nvidia you think we are idiots?

It says in the model card...

We recommend setting temperature to 0.6, top_p to 0.95 for reasoning True and greedy search for reasoning False, and increase max_new_tokens to 1024 or higher for reasoning True.

The other values should probably left to their default value, or experiment with some commonly used values.

Sign up or log in to comment