5 1

Junrulu

https://lujunru.github.io/

AI & ML interests

None yet

Recent Activity

New activity about 2 months ago

BAAI/IndustryCorpus2:Punctuation

authored a paper about 2 months ago

MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation

authored a paper about 2 months ago

FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema

View all activity

Organizations

None yet

Collections 2

Papers 11

models 7

datasets 4

Junrulu/Reproduced-tulu2-test-sets

Preview • Updated Mar 25 • 35

Junrulu/MT-Bench-Plus

Viewer • Updated Mar 12 • 54 • 48 • 2

Junrulu/MemoChat_Instructions

Viewer • Updated Mar 12 • 10k • 60 • 1

Junrulu/Prompt_Preference_Dataset

Viewer • Updated Feb 19 • 30k • 48 • 1

Junrulu

AI & ML interests

Recent Activity

Organizations

Collections 2

jiazhengli/Pythia-2.8B-HH-RLHF-Iterative-SamPO

jiazhengli/Pythia-2.8B-TLDR-Iterative-SamPO

Junrulu/Llama-3-8B-Instruct-Iterative-SamPO

Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence

Junrulu/MemoChat-Fastchat-T5-3B

Junrulu/MemoChat-Vicuna-7B

Junrulu/MemoChat-Vicuna-13B

Junrulu/MemoChat-Vicuna-33B

Papers 11

models 7

Junrulu/Llama-3-8B-Instruct-Iterative-SamPO

Junrulu/Reproduced-tulu2-dpo-13b

Junrulu/MemoChat-Vicuna-13B

Junrulu/MemoChat-Fastchat-T5-3B

Junrulu/MemoChat-Vicuna-7B

Junrulu/MemoChat-Vicuna-33B

Junrulu/FIPO-IPL-IPO-Tulu2-70B

datasets 4

Junrulu/Reproduced-tulu2-test-sets

Junrulu/MT-Bench-Plus

Junrulu/MemoChat_Instructions

Junrulu/Prompt_Preference_Dataset

Junrulu

AI & ML interests

Recent Activity

Organizations

Collections 2

Papers 11

models 7 Sort: Recently updated

datasets 4 Sort: Recently updated

models 7

datasets 4