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.
tiny-think-sft-math-stem-loss-dft-bf16-e3-bs8medicalpj-Qwen3-235B-A22B-Instruct-exp10-Base-Instruction-dftMistral-7B-DFTmedicalpj-Qwen3-235B-A22B-Instruct-exp8-Instruction-dftMistral-7B-DFT2tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8Qwen2.5-3B-Instruct-SFT-Pubmed-16bit-DFTmedicalpj-Qwen3-235B-A22B-thinking-exp8-Instruction-dftQwen2.5-1.5B-Instruct-SFT-Pubmed-16bit-DFTtiny-think-sft-math-stem-loss-dft-bf16-lr2e-5-e2-bs8gemma-3-dftQwen3-4B-Thinking-2507-DFTnl2bash-verified-GLM-4_6-traces-32ep-32k-dftdftzephyr-2b-gemma-dft-debugs37_dft_4zephyr-2b-gemma-dfttpo_v1.0.0_808_dfttpo_v1.0.0_1010_dfttpo_v1.0.0_dpo_2_1ep_dfttpo_v1.0.0_dpo_2_2ep_dftMetaMath-Mistral-7B-DFT2tiny-think-sft-math-stem-loss-dft-bf16-e2-bs8MetaMath-Mistral-7B-DFTRIVERUSDT-Qwen_Qwen2.5-1.5B-Instruct-R256-L3072-dft-QFalseqwen2.5-1.5b-arc1-decoded-dfttpo_v1.0.0_dpo_1_1ep_dfttpo_v1.0.0_dpo_1_2ep_dft4B-Instruct-DFT-no-reasoninggemma-4-31b-it-dft-lora-epoch-1