chujiezheng commited on
Commit
ce650fe
1 Parent(s): fb05a32

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -6,6 +6,6 @@ language:
6
 
7
  # zephyr-7b-beta-ExPO
8
 
9
- The extrapolated (ExPO) model based on `HuggingFaceH4/zephyr-7b-beta` and `HuggingFaceH4/mistral-7b-sft-beta`, as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
10
 
11
  Specifically, we obtain this model by extrapolating from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.
 
6
 
7
  # zephyr-7b-beta-ExPO
8
 
9
+ The extrapolated (ExPO) model based on [`HuggingFaceH4/zephyr-7b-beta`](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) and [`HuggingFaceH4/mistral-7b-sft-beta`](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta), as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
10
 
11
  Specifically, we obtain this model by extrapolating from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.