Mingyu Chen's picture

2

Mingyu Chen

MYC081

AI & ML interests

theory

Recent Activity

updated a dataset about 1 month ago

MYC081/deepscale_3b_eval_correct

published a dataset about 1 month ago

MYC081/deepscale_3b_eval_correct

upvoted a paper about 1 month ago

Accelerating RL for LLM Reasoning with Optimal Advantage Regression

View all activity

Organizations

None yet

MYC081 's models 10

MYC081/SELM-Llama-3-8B-Instruct-DPO-iter-3

8B • Updated Feb 3 • 4

MYC081/SELM-Zephyr-7B-iter-0

MYC081/Qwen2.5-3B-WPO-bf16-1

Text Generation • 3B • Updated Nov 15, 2024 • 8

MYC081/Qwen2.5-3B-WPO-bf16-1-test

Updated Nov 14, 2024

MYC081/Qwen2.5-1.5B-WPO-bf16-1

Updated Nov 14, 2024

MYC081/Qwen2-0.5B-WPO-bf16-1

0.5B • Updated Nov 14, 2024 • 1

MYC081/pythia-1b-tldr-xpo

7B • Updated Nov 13, 2024 • 3

MYC081/pythia-6.9b-deduped-tldr-online-dpo

Updated Nov 11, 2024

MYC081/Qwen2.5-0.5B-Online-DPO-PairRM

Updated Nov 5, 2024

MYC081/pythia-2.8b-deduped-tldr-online-dpo

Updated Nov 5, 2024