Wei Liu's picture

Wei Liu

PeterV09

·

https://vpeterv.github.io

AI & ML interests

Machine Learning, Natural Language Processing

Recent Activity

upvoted a paper 3 days ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

upvoted a paper 13 days ago

SWE-RM: Execution-free Feedback For Software Engineering Agents

upvoted a paper about 1 month ago

Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning

View all activity

Organizations

PeterV09 's models 18

PeterV09/llava-1.6-alignmentv2

Text Generation • Updated May 20, 2024 • 5

PeterV09/llava-1.6-beta-26

Updated May 17, 2024

PeterV09/llava-1.6-asft

Updated May 15, 2024

PeterV09/llava-1.6-4sftmse

7B • Updated May 13, 2024 • 3

PeterV09/llava-1.6-3sft0.5

7B • Updated May 10, 2024 • 2

PeterV09/llava-1.6-2sft

7B • Updated May 7, 2024 • 4

PeterV09/llava-1.6-sft

Text Generation • 7B • Updated May 7, 2024 • 2

PeterV09/mistral-7b-300k-6k-a100-6e-valid-hkust_2-l4k

Text Generation • Updated Dec 25, 2023 • 8

PeterV09/deita-6k-sft-fordpo

Text Generation • 7B • Updated Dec 18, 2023 • 3

PeterV09/mistral-7b-300k-6k-a100-6e-valid-7

Text Generation • Updated Dec 17, 2023 • 9

PeterV09/mistral-7b-300k-6k-a100-6e-valid-5

Text Generation • Updated Dec 17, 2023 • 5

PeterV09/mistral-7b-300k-10k-a100-6e-valid-5

Text Generation • Updated Dec 16, 2023 • 3

PeterV09/mistral-7b-300k-10k-a100-6e-valid-4

Text Generation • Updated Dec 16, 2023 • 5

PeterV09/mistral-7b-300k-10k-a100-6e-valid-3

Text Generation • Updated Dec 16, 2023 • 6

PeterV09/mistral-7b-300k-10k-a100-6e-valid-2

Text Generation • Updated Dec 16, 2023 • 3 • 1

PeterV09/mistral-7b-300k-10k-a100-6e-valid-1

Text Generation • Updated Dec 16, 2023 • 6

PeterV09/mistral-7b-300k-6k-a100-6e-valid

Text Generation • Updated Dec 15, 2023 • 7 • 1

PeterV09/mistral-7b-300k-10k-a100-6e-valid

Text Generation • Updated Dec 15, 2023 • 6