Hugging Face's logo

chujiezheng
/
Smaug-34B-v0.1-ExPO

Text Generation
Transformers
Safetensors
English
Chinese
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
chujiezheng commited on
Commit
7b0a5ce
•
1 Parent(s): 765eaef

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -9,7 +9,7 @@ language:
9
 
10
  # Smaug-34B-v0.1-ExPO
11
 
12
- The extrapolated (ExPO) model based on [`abacusai/Smaug-72B-v0.1`](https://huggingface.co/abacusai/Smaug-72B-v0.1) and [`jondurbin/bagel-34b-v0.2`](https://huggingface.co/jondurbin/bagel-34b-v0.2), as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
13
 
14
  Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.
15
 
 
9
 
10
  # Smaug-34B-v0.1-ExPO
11
 
12
+ The extrapolated (ExPO) model based on [`abacusai/Smaug-34B-v0.1`](https://huggingface.co/abacusai/Smaug-34B-v0.1) and [`jondurbin/bagel-34b-v0.2`](https://huggingface.co/jondurbin/bagel-34b-v0.2), as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
13
 
14
  Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.
15