models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Qwen3-0.6B-OSP-ttt-fixed-gemini-step_01408spiral-octothinker-3b-multi-step00384spiral-qwen3-4b-multi-env-step00384Qwen3-0.6B-OSP-ttt-fixed-gemini-step_01024Qwen3-0.6B-OSP-ttt-fixed-gemini-step_00832Qwen3-0.6B-OSP-ttt-fixed-gemini-step_01344Qwen3-4B-Base-4K-KuhnPoker-Self-Vanilla-0522-Zichen-step_00128Qwen3-4B-Base-4K-KuhnPoker-Gemini-Role-0523-Zichen-step_00192spiral-qwen3-8b-multi-step00480spiral-octothinker-8b-multi-step00288Qwen3-0.6B-OSP-ttt-fixed-random-step_00064Qwen3-0.6B-OSP-ttt-fixed-random-step_00128Qwen3-4B-Base-4K-KuhnPoker-Gemini-Role-0523-Zichen-step_00384spiral-octothinker-3b-multi-step00192spiral-qwen3-4b-multi-env-step00096spiral-qwen3-4b-multi-env-step00256spiral-llama3-8b-multi-env-step00320spiral-qwen3-4b-simple-negotiation-step00352spiral-qwen3-4b-baseline-11-25spiral-qwen3-4b-ours-11-25spiral-octothinker-3b-multi-step00032spiral-qwen3-4b-multi-env-step00416spiral-qwen3-4b-simple-negotiation-step00416Qwen3-0.6B-OSP-ttt-fixed-gemini-step_00064spiral-octothinker-8b-multi-step00096spiral-qwen3-4b-multi-env-step00032spiral-qwen3-4b-multi-env-step00320spiral-octothinker-3b-multi-env-new-step00160spiral-qwen3-4b-simple-negotiation-step00256spiral-qwen3-4b-simple-negotiation-step00288
