Article
6
Junrulu
Junrulu
AI & ML interests
None yet
Recent Activity
Organizations
None yet
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
-
jiazhengli/Pythia-2.8B-HH-RLHF-Iterative-SamPO
Text Generation • 3B • Updated • 4 -
jiazhengli/Pythia-2.8B-TLDR-Iterative-SamPO
Text Generation • 3B • Updated • 4 -
Junrulu/Llama-3-8B-Instruct-Iterative-SamPO
Text Generation • 8B • Updated • 3 • 1 -
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
Paper • 2406.10957 • Published • 1
A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
-
jiazhengli/Pythia-2.8B-HH-RLHF-Iterative-SamPO
Text Generation • 3B • Updated • 4 -
jiazhengli/Pythia-2.8B-TLDR-Iterative-SamPO
Text Generation • 3B • Updated • 4 -
Junrulu/Llama-3-8B-Instruct-Iterative-SamPO
Text Generation • 8B • Updated • 3 • 1 -
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
Paper • 2406.10957 • Published • 1
models
7
Junrulu/MemoChat-Vicuna-7B
Text Generation
•
7B
•
Updated
•
5
•
1
Junrulu/MemoChat-Vicuna-13B
Text Generation
•
13B
•
Updated
•
6
Junrulu/FIPO-IPL-IPO-Tulu2-70B
Text Generation
•
69B
•
Updated
•
3
Junrulu/MemoChat-Vicuna-33B
Text Generation
•
33B
•
Updated
•
5
Junrulu/Llama-3-8B-Instruct-Iterative-SamPO
Text Generation
•
8B
•
Updated
•
3
•
1
Junrulu/Reproduced-tulu2-dpo-13b
Text Generation
•
Updated
•
3
•
1
Junrulu/MemoChat-Fastchat-T5-3B
3B
•
Updated
•
2