nvidia
/

Llama-3.1-Nemotron-70B-Reward

Model card Files Files and versions Community

zhilinw commited on Sep 28

Commit

abd3678

•

1 Parent(s): 1bd9327

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -63,6 +63,7 @@ You can use the model with [NeMo Aligner](https://github.com/NVIDIA/NeMo-Aligner
 ```python
 python /opt/NeMo-Aligner/examples/nlp/gpt/serve_reward_model.py \
       rm_model_file=Llama-3.1-Nemotron-70B-Reward \
       trainer.num_nodes=1 \

 ```python
+HF_HOME=<YOUR_HF_HOME_CONTAINING_TOKEN_WITH_LLAMA31_70B_ACCESS> \
 python /opt/NeMo-Aligner/examples/nlp/gpt/serve_reward_model.py \
       rm_model_file=Llama-3.1-Nemotron-70B-Reward \
       trainer.num_nodes=1 \