Model checkpoints of Black-Box On-Policy Distillation of Large Language Models
ytz
ytz20
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks submitted a paper 3 days ago
LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks upvoted a paper 24 days ago
GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated ScreenshotsOrganizations
None yet
models 5
ytz20/GAD-GPT-5-Chat-Llama-3.1-8B-Instruct
8B • Updated • 3 • 3
ytz20/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct
4B • Updated • 2 • 1
ytz20/GAD-GPT-5-Chat-Qwen2.5-3B-Instruct
3B • Updated • 3 • 1
ytz20/GAD-GPT-5-Chat-Qwen2.5-7B-Instruct
8B • Updated • 3 • 1
ytz20/GAD-GPT-5-Chat-Qwen2.5-14B-Instruct
15B • Updated • 5 • 1
datasets 8
ytz20/sys_safety_test
Viewer • Updated • 498 • 34
ytz20/sys_safety_train
Viewer • Updated • 16.1k • 46
ytz20/sys_medmcqa_test
Viewer • Updated • 500 • 39
ytz20/sys_medmcqa_train
Viewer • Updated • 182k • 31
ytz20/dapo_test
Viewer • Updated • 1k • 49
ytz20/dapo_validation
Viewer • Updated • 1k • 48
ytz20/dapo_train
Viewer • Updated • 12.1k • 47
ytz20/LMSYS-Chat-GPT-5-Chat-Response
Viewer • Updated • 192k • 692 • 93