nvidia
/

Llama-3.1-Nemotron-70B-Reward-HF

Model card Files Files and versions Community

Resources

View closed (0)

Why the hf-format model does not have rm head, since the original format model does have.

#7 opened about 1 month ago by

conversion script used

#6 opened 2 months ago by

the batch inference result

#5 opened 3 months ago by

Question on tokenizer chat template and readout

#4 opened 3 months ago by

smd

#3 opened 4 months ago by

Vllm

#2 opened 4 months ago by

Add proper library tag

#1 opened 4 months ago by