Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
chujiezheng
's Collections
Weak-to-Strong Extrapolation Expedites Alignment
Model Checkpoints in the ExPO Paper
Weak-to-Strong Extrapolation Expedites Alignment
updated
14 days ago
Better aligned models obtained by weak-to-strong model extrapolation (ExPO)
Upvote
16
+6
Weak-to-Strong Extrapolation Expedites Alignment
Paper
•
2404.16792
•
Published
Apr 25
•
11
chujiezheng/Smaug-Llama-3-70B-Instruct-ExPO
Text Generation
•
Updated
May 27
•
747
•
2
chujiezheng/Smaug-34B-v0.1-ExPO
Text Generation
•
Updated
May 29
•
2.83k
chujiezheng/Starling-LM-7B-beta-ExPO
Text Generation
•
Updated
May 27
•
678
•
2
chujiezheng/Starling-LM-7B-alpha-ExPO
Text Generation
•
Updated
May 27
•
677
chujiezheng/LLaMA3-iterative-DPO-final-ExPO
Text Generation
•
Updated
May 27
•
663
•
2
chujiezheng/Mistral7B-PairRM-SPPO-ExPO
Text Generation
•
Updated
Sep 23
•
3.46k
chujiezheng/tulu-2-dpo-70b-ExPO
Text Generation
•
Updated
May 27
•
1.04k
chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
Text Generation
•
Updated
Jun 1
•
66
•
16
chujiezheng/tulu-2-dpo-13b-ExPO
Text Generation
•
Updated
May 27
•
11
chujiezheng/tulu-2-dpo-7b-ExPO
Text Generation
•
Updated
May 27
•
14
chujiezheng/Snorkel-Mistral-PairRM-DPO-ExPO
Text Generation
•
Updated
May 27
•
11
chujiezheng/Llama3-70B-Chinese-Chat-ExPO
Text Generation
•
Updated
May 27
•
6
chujiezheng/Llama3-8B-Chinese-Chat-ExPO
Text Generation
•
Updated
May 27
•
643
•
1
chujiezheng/neo_7b_instruct_v0.1-ExPO
Text Generation
•
Updated
Jun 19
•
9
chujiezheng/zephyr-7b-beta-ExPO
Text Generation
•
Updated
May 27
•
7
chujiezheng/zephyr-7b-alpha-ExPO
Text Generation
•
Updated
May 27
•
6
chujiezheng/zephyr-7b-dpo-full-ExPO
Text Generation
•
Updated
May 27
•
13
chujiezheng/internlm2-chat-20b-ExPO
Text Generation
•
Updated
May 27
•
27
•
1
chujiezheng/internlm2-chat-7b-ExPO
Text Generation
•
Updated
May 27
•
5
chujiezheng/internlm2-chat-1_8b-ExPO
Text Generation
•
Updated
May 27
•
8
•
1
Upvote
16
+12
Share collection
View history
Collection guide
Browse collections