Hugging Face's logo

PKU-Alignment
/
beaver-7b-v1.0-cost

Reinforcement Learning
Safetensors
English
safe-rlhf
llama
reinforcement-learning-from-human-feedback
beaver
safety
ai-safety
deepspeed
rlhf
alpaca
Model card Files Community
1
RuiyangSun commited on
Commit
c2f25b2
•
1 Parent(s): 32e35c1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -35,6 +35,7 @@ It can play a role in the safe RLHF algorithm, helping the Beaver model become m
35
  - **Dataset:** <https://huggingface.co/datasets/PKU-Alignment/PKU-SafeRLHF>
36
  - **Reward Model:** <https://huggingface.co/PKU-Alignment/beaver-7b-v1.0-reward>
37
  - **Cost Model:** <https://huggingface.co/PKU-Alignment/beaver-7b-v1.0-cost>
 
38
  - **Paper:** *Coming soon...*
39
 
40
  ## How to Use the Cost Model
 
35
  - **Dataset:** <https://huggingface.co/datasets/PKU-Alignment/PKU-SafeRLHF>
36
  - **Reward Model:** <https://huggingface.co/PKU-Alignment/beaver-7b-v1.0-reward>
37
  - **Cost Model:** <https://huggingface.co/PKU-Alignment/beaver-7b-v1.0-cost>
38
+ - **Dataset Paper:** <https://arxiv.org/abs/2307.04657>
39
  - **Paper:** *Coming soon...*
40
 
41
  ## How to Use the Cost Model