ThinMQM (automated translation evaluation, MQM) model and data collection.
Runzhe Zhan
rzzhan
AI & ML interests
None yet
Recent Activity
upvoted a paper about 3 hours ago
ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics upvoted a paper 20 days ago
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows updated a model 22 days ago
Simplified-Reasoning/SU-01Organizations
models 10
rzzhan/ThinMQM-8B
Text Generation • 8B • Updated • 3
rzzhan/ExGRPO-Llama3.1-8B-Instruct
Text Generation • 8B • Updated • 3
rzzhan/ExGRPO-Llama3.1-8B-Zero
Text Generation • 8B • Updated • 1
rzzhan/ExGRPO-Qwen2.5-Math-1.5B-Zero
Text Generation • 2B • Updated • 5
rzzhan/ExGRPO-Qwen2.5-7B-Instruct
Text Generation • 8B • Updated • 1
rzzhan/ExGRPO-LUFFY-7B-Continual
Text Generation • 8B • Updated • 3 • 1
rzzhan/ExGRPO-Qwen2.5-Math-7B-Zero
Text Generation • 8B • Updated • 2 •
rzzhan/ThinMQM-7B
8B • Updated • 2
rzzhan/ThinMQM-32B
33B • Updated • 3
rzzhan/tiny-llama-stories-42m
Updated • 7 • 1