Article
82
Hejian Sang
pb09204048
AI & ML interests
None yet
Recent Activity
commentedon a paper 2 days ago
Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts submitted a paper 3 days ago
Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative ShiftsOrganizations
models 14
pb09204048/Inkling-Small-Hybrid-4layer
18B • Updated • 19
pb09204048/Inkling-Small-6layer
31B • Updated • 28
pb09204048/Qwen3-4B-Math-RL-Specialist
Text Generation • 4B • Updated • 384
pb09204048/Qwen3-4B-Code-RL-Specialist
Text Generation • 4B • Updated • 384 • 1
pb09204048/Qwen3-4B-IF-RL-Specialist
Text Generation • 4B • Updated • 399 • 1
pb09204048/Qwen3-8B-DAPO-iter449-disable-thinking
Text Generation • 8B • Updated • 97
pb09204048/Qwen3-8B-DAPO-iter599-thinking
Text Generation • 8B • Updated • 48
pb09204048/CRISP-DeepSeek-R1-Distill-Llama-8B-v2
Text Generation • 8B • Updated • 35 • 1
pb09204048/CRISP-DeepSeek-R1-Distill-Llama-8B-v1
Text Generation • 8B • Updated • 34
pb09204048/CRISP-Qwen3-14B-v2
Text Generation • 15B • Updated • 15