ThinMQM (automated translation evaluation, MQM) model and data collection.
Runzhe Zhan
rzzhan
AI & ML interests
None yet
Recent Activity
upvoted a paper 5 days ago
LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation upvoted a paper 5 days ago
TPPO: Tracking-Value PPO For Language Model ReasoningOrganizations
models 10
rzzhan/ThinMQM-8B
Text Generation • 8B • Updated • 22
rzzhan/ExGRPO-Llama3.1-8B-Instruct
Text Generation • 8B • Updated • 18
rzzhan/ExGRPO-Llama3.1-8B-Zero
Text Generation • 8B • Updated • 21
rzzhan/ExGRPO-Qwen2.5-Math-1.5B-Zero
Text Generation • 2B • Updated • 22
rzzhan/ExGRPO-Qwen2.5-7B-Instruct
Text Generation • 8B • Updated • 23
rzzhan/ExGRPO-LUFFY-7B-Continual
Text Generation • 8B • Updated • 33 • 1
rzzhan/ExGRPO-Qwen2.5-Math-7B-Zero
Text Generation • 8B • Updated • 31 •
rzzhan/ThinMQM-7B
8B • Updated • 17
rzzhan/ThinMQM-32B
33B • Updated • 25
rzzhan/tiny-llama-stories-42m
Updated • 7.61k • 1