Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
chujiezheng
's Collections
Model Extrapolation Expedites Alignment
Model Checkpoints in the ExPO Paper
Model Extrapolation Expedites Alignment
updated
May 27
Better aligned models obtained by model extrapolation (ExPO)
Upvote
17
+7
Weak-to-Strong Extrapolation Expedites Alignment
Paper
•
2404.16792
•
Published
Apr 25, 2024
•
11
chujiezheng/Mistral7B-PairRM-SPPO-ExPO
Text Generation
•
7B
•
Updated
Sep 23, 2024
•
11k
chujiezheng/LLaMA3-iterative-DPO-final-ExPO
Text Generation
•
8B
•
Updated
May 27, 2024
•
10.8k
•
2
chujiezheng/Llama3-8B-Chinese-Chat-ExPO
Text Generation
•
8B
•
Updated
May 27, 2024
•
10.8k
•
1
chujiezheng/tulu-2-dpo-70b-ExPO
Text Generation
•
69B
•
Updated
May 27, 2024
•
10.8k
chujiezheng/Smaug-Llama-3-70B-Instruct-ExPO
Text Generation
•
71B
•
Updated
May 27, 2024
•
10.8k
•
2
chujiezheng/Starling-LM-7B-beta-ExPO
Text Generation
•
7B
•
Updated
May 27, 2024
•
9.05k
•
2
chujiezheng/Starling-LM-7B-alpha-ExPO
Text Generation
•
7B
•
Updated
May 27, 2024
•
9.03k
chujiezheng/Llama3-70B-Chinese-Chat-ExPO
Text Generation
•
71B
•
Updated
May 27, 2024
•
10.2k
chujiezheng/internlm2-chat-20b-ExPO
Text Generation
•
20B
•
Updated
May 27, 2024
•
18.8k
•
1
chujiezheng/internlm2-chat-7b-ExPO
Text Generation
•
8B
•
Updated
May 27, 2024
•
18.7k
chujiezheng/Smaug-34B-v0.1-ExPO
Text Generation
•
34B
•
Updated
May 29, 2024
•
10.2k
chujiezheng/tulu-2-dpo-13b-ExPO
Text Generation
•
13B
•
Updated
May 27, 2024
•
17
chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
Text Generation
•
8B
•
Updated
Jun 1, 2024
•
21
•
16
chujiezheng/tulu-2-dpo-7b-ExPO
Text Generation
•
7B
•
Updated
May 27, 2024
•
17
chujiezheng/Snorkel-Mistral-PairRM-DPO-ExPO
Text Generation
•
7B
•
Updated
May 27, 2024
•
15
chujiezheng/neo_7b_instruct_v0.1-ExPO
Text Generation
•
8B
•
Updated
Jun 19, 2024
•
13
chujiezheng/zephyr-7b-beta-ExPO
Text Generation
•
7B
•
Updated
May 27, 2024
•
13
chujiezheng/zephyr-7b-alpha-ExPO
Text Generation
•
7B
•
Updated
May 27, 2024
•
12
•
1
chujiezheng/zephyr-7b-dpo-full-ExPO
Text Generation
•
7B
•
Updated
May 27, 2024
•
39
chujiezheng/internlm2-chat-1_8b-ExPO
Text Generation
•
2B
•
Updated
May 27, 2024
•
14
•
1
Upvote
17
+13
Share collection
View history
Collection guide
Browse collections