New aligned models obtained by weak-to-strong model extrapolation (ExPO)
Chujie Zheng
chujiezheng
AI & ML interests
Large Language Models
Organizations
Collections
2
models
24
chujiezheng/Mistral7B-PairRM-SPPO-ExPO
Text Generation
•
Updated
chujiezheng/Snorkel-Mistral-PairRM-DPO-ExPO
Text Generation
•
Updated
chujiezheng/internlm2-chat-1_8b-ExPO
Feature Extraction
•
Updated
chujiezheng/internlm2-chat-7b-ExPO
Feature Extraction
•
Updated
chujiezheng/internlm2-chat-20b-ExPO
Feature Extraction
•
Updated
chujiezheng/zephyr_0.2_a2.5
Text Generation
•
Updated
•
408
chujiezheng/zephyr_0.1_a8.0
Text Generation
•
Updated
•
118
chujiezheng/zephyr-7b-beta-ExPO
Text Generation
•
Updated
•
382
chujiezheng/zephyr_0.4
Text Generation
•
Updated
chujiezheng/zephyr_0.2
Text Generation
•
Updated
•
402