Qwen3-8B TMax AENV v39b Collection Qwen3-8B agentic RL run tmax_aenv_v39b: the SFT init (tmax_sft_v3 iter353) plus RL checkpoints at iterations 69-219, every 10 steps. • 26 items • Updated 2 days ago
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-round1v2-iter024 Image-Text-to-Text • 36B • Updated 2 days ago • 16
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-round1v2-iter024 Image-Text-to-Text • 36B • Updated 2 days ago • 16
Qwen3-8B TMax AENV v39b Collection Qwen3-8B agentic RL run tmax_aenv_v39b: the SFT init (tmax_sft_v3 iter353) plus RL checkpoints at iterations 69-219, every 10 steps. • 26 items • Updated 2 days ago
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-round1-iter029 Image-Text-to-Text • 36B • Updated 2 days ago • 14
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-round1-iter029 Image-Text-to-Text • 36B • Updated 2 days ago • 14
TMax / Smith agentic RL Collection 213 checkpoints from four async multi-turn agentic-env GSPO runs on Qwen3-8B / Qwen3.5-9B; one subfolder per iteration. • 5 items • Updated 2 days ago
Qwen3-8B TMax AENV v39b Collection Qwen3-8B agentic RL run tmax_aenv_v39b: the SFT init (tmax_sft_v3 iter353) plus RL checkpoints at iterations 69-219, every 10 steps. • 26 items • Updated 2 days ago
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-iter034 Image-Text-to-Text • 36B • Updated 2 days ago • 9
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-iter034 Image-Text-to-Text • 36B • Updated 2 days ago • 9
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-iter029 Image-Text-to-Text • 36B • Updated 2 days ago • 11
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-iter029 Image-Text-to-Text • 36B • Updated 2 days ago • 11