Article
3
Junrulu
Junrulu
AI & ML interests
None yet
Recent Activity
published
an
article
3 days ago
结合Deepseek代码探讨MLA的改进及收益
published
an
article
3 days ago
大模型偏好优化技术：DPO及其变种
authored
a paper
4 days ago
RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and
Instruction-Following
Organizations
None yet
Collections
3
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 • Updated • 62 -
jiazhengli/Pythia-2.8B-TLDR-Iterative-SamPO
Text Generation • Updated • 67 -
Junrulu/Llama-3-8B-Instruct-Iterative-SamPO
Text Generation • Updated • 9 • 1 -
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
Paper • 2406.10957 • Published • 1
models
7
Junrulu/Llama-3-8B-Instruct-Iterative-SamPO
Text Generation
•
Updated
•
9
•
1
Junrulu/Reproduced-tulu2-dpo-13b
Text Generation
•
Updated
•
20
•
1
Junrulu/MemoChat-Vicuna-13B
Text Generation
•
Updated
•
7
Junrulu/MemoChat-Fastchat-T5-3B
Text2Text Generation
•
Updated
•
12
Junrulu/MemoChat-Vicuna-7B
Text Generation
•
Updated
•
10
•
1
Junrulu/MemoChat-Vicuna-33B
Text Generation
•
Updated
•
9
Junrulu/FIPO-IPL-IPO-Tulu2-70B
Text Generation
•
Updated
•
29