VanWang/llama3_8B_rope32_short_20k
8B • Updated • 5
Wang Yang
VanWang
AI & ML interests
None yet
Recent Activity
upvoted a paper 11 days ago
Rufus-Air: An Open LLM Post-Training Recipe updated a model about 2 months ago
VanWang/awm-qwen3.6-27b-rl-d1000-ep2 published a model about 2 months ago
VanWang/awm-qwen3.6-27b-rl-d1000-ep2Organizations
None yet
VanWang/llama3_8B_rope16_short_20k
8B • Updated • 6
VanWang/llama3_8B_rope4_short_20k
8B • Updated • 6
VanWang/llama3_8B_rope8_long_20k
8B • Updated • 4
VanWang/llama3_8B_rope1_long_20k
8B • Updated • 7
VanWang/llama3_8B_rope64_long_20k
8B • Updated • 6
VanWang/llama3_8B_rope8_short_20k
8B • Updated • 6
VanWang/llama3_8B_rope1_short_20k
8B • Updated • 4
VanWang/llama3_8B_rope64_short_20k
8B • Updated • 4
VanWang/Bespoke-7b_baseline
8B • Updated • 8 • 1
VanWang/Bespoke-Stratos-7B-ThinkPO
8B • Updated • 5 • 1
VanWang/DeepSeek-R1-Distill-Qwen-7B-ThinkPO
8B • Updated • 32 • 2
VanWang/Bespoke-Stratos-7B-repro-ThinkPO
8B • Updated • 7 • 1
VanWang/Bespoke-Stratos-7B-repro-SFT
8B • Updated • 7 • 1