xyj787878/Qwen2.5-0.5B-GRPO-kuakua
Reinforcement Learning • 0.5B • Updated • 11
xyj
xyj787878
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Representation Drift in Continual Learning: LoRA versus N-gram Memory new activity about 1 year ago
xyj787878/Qwen2.5-0.5B-GRPO-kuakua:Improve language tag updated a model over 1 year ago
xyj787878/Qwen2.5-0.5B-GRPO-kuakuaOrganizations
None yet
datasets 0
None public yet