PKU-Alignment
/

beaver-7b-v2.0

Reinforcement Learning

reinforcement-learning-from-human-feedback

Model card Files Files and versions Community

XuehaiPan commited on May 9

Commit

05adcfb

•

1 Parent(s): 26c2a71

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -45,7 +45,7 @@ Compared with its predecessor [Alpaca](https://github.com/tatsu-lab/stanford_alp
 - Using the [PKU-Alignment/safe-rlhf](https://github.com/PKU-Alignment/safe-rlhf#interactive-cli-demo) GitHub repository.
 ```console
-$ python3 -m safe-rlhf.serve.cli --max_length 512 --model_name_or_path PKU-Alignment/alpaca-7b-reproduced PKU-Alignment/beaver-7b-v1.0 PKU-Alignment/beaver-7b-v2.0 PKU-Alignment/beaver-7b-v3.0
 Loading model...
 Model loaded. HINT: Type "Ctrl + C" or "Ctrl + D" to exit. Type "/clear" to clear dialogue history. Type "/help" to see help message.

 - Using the [PKU-Alignment/safe-rlhf](https://github.com/PKU-Alignment/safe-rlhf#interactive-cli-demo) GitHub repository.
 ```console
+$ python3 -m safe_rlhf.serve.cli --max_length 512 --model_name_or_path PKU-Alignment/alpaca-7b-reproduced PKU-Alignment/beaver-7b-v1.0 PKU-Alignment/beaver-7b-v2.0 PKU-Alignment/beaver-7b-v3.0
 Loading model...
 Model loaded. HINT: Type "Ctrl + C" or "Ctrl + D" to exit. Type "/clear" to clear dialogue history. Type "/help" to see help message.