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.
cot-dialect-olmo3-7b-think-grpo-reward-diff-sftlen-sq-dapo-l5OneReason-0.8B-Frontier-SFT372-RLOO-DAPO-T12-K1-W625devstral-v3-dapodapo_phi3.5_codeOneReason-0.8B-Frontier-SFT372-RLOO-DAPO-T12-K1-W532OneReason-0.8B-Frontier-SFT372-RLOO-DAPO-T12-K1-W150qwen35-27b-dapo-dandi-500qwen2.5-3b-sft-dapodiffusiongemma-26B-A4B-dapo-math-grpo-ckpt500qwen3-0.6b-ncert-physics-sft-dapo-loraOneReason-0.8B-Frontier-SFT372-RLOO-DAPO-T12-K1-W200OneReason-0.8B-Frontier-SFT372-RLOO-DAPO-T12-K1-W400OneReason-0.8B-Frontier-SFT372-RLOO-DAPO-Anchor-V2.2-W215devstral-v3-dapo-loraaffiliation-parsing-lora-Qwen3-8B-distil-GLM_4.5_Air-dapo-latexOneReason-0.8B-Frontier-SFT372-RLOO-DAPO-T12-K1-W175OneReason-0.8B-Frontier-SFT372-RLOO-DAPO-Anchor-V2.2-SecondPassOneReason-0.8B-Frontier-SFT372-RLOO-DAPO-Anchor-V2.2-W150OneReason-0.8B-Frontier-SFT372-RLOO-DAPO-Anchor-V2.2-W175gsm8k_new_dapo_lora_plusPIT-4B-FT-202212-math-dapo-loraOneReason-0.8B-Frontier-SFT372-RLOO-DAPO-Anchor-V2.2-W249dapo-qwen3-1.7b-nonthinking-2048-20260918dapo-qwen3-4b-nonthinking-2048-20260919
