213 checkpoints from four async multi-turn agentic-env GSPO runs on Qwen3-8B / Qwen3.5-9B; one subfolder per iteration.
will
willamazon1
·
AI & ML interests
None yet
Recent Activity
updated a collection 2 days ago
Qwen3-8B TMax AENV v39b updated a model 2 days ago
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-round1v2-iter024 published a model 2 days ago
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-round1v2-iter024Organizations
None yet
Qwen3-8B TMax AENV v39b
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.
-
willamazon1/qwen3-8b-tmax-sft-v3-iter353
Text Generation • 8B • Updated • 193 -
willamazon1/qwen3-8b-tmax-aenv-v39b-iter069
Text Generation • 8B • Updated • 186 -
willamazon1/qwen3-8b-tmax-aenv-v39b-iter079
Text Generation • 8B • Updated • 180 -
willamazon1/qwen3-8b-tmax-aenv-v39b-iter089
Text Generation • 8B • Updated • 172
TMax / Smith agentic RL
213 checkpoints from four async multi-turn agentic-env GSPO runs on Qwen3-8B / Qwen3.5-9B; one subfolder per iteration.
Qwen3-8B TMax AENV v39b
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.
-
willamazon1/qwen3-8b-tmax-sft-v3-iter353
Text Generation • 8B • Updated • 193 -
willamazon1/qwen3-8b-tmax-aenv-v39b-iter069
Text Generation • 8B • Updated • 186 -
willamazon1/qwen3-8b-tmax-aenv-v39b-iter079
Text Generation • 8B • Updated • 180 -
willamazon1/qwen3-8b-tmax-aenv-v39b-iter089
Text Generation • 8B • Updated • 172
models 46
willamazon1/Qwen3.5-9B-smith-r2v1-iter145
Text Generation • Updated
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-round1v2-iter024
Image-Text-to-Text • 36B • Updated • 16
willamazon1/Qwen3.5-9B-smith-r1v1-reportonly
Text Generation • Updated
willamazon1/Qwen3-8B-tmax-aenv-r1v8
Text Generation • Updated
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-round1-iter029
Image-Text-to-Text • 36B • Updated • 14
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-iter034
Image-Text-to-Text • 36B • Updated • 9
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-iter029
Image-Text-to-Text • 36B • Updated • 11
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-iter024
Image-Text-to-Text • 36B • Updated • 12
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-iter019
Image-Text-to-Text • 36B • Updated • 12
willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-iter014
Image-Text-to-Text • 36B • Updated • 12