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.
HereticAggressive-CoT-i1-GGUFHereticAggressive-CoT-GGUFqwen3.5-4b-opus46-cotcot-dialect-olmo3-7b-think-grpo-l3cot-dialect-olmo3-7b-think-sft-l3qwen3-8b-ao-v3-abl3-cotv5-corpusQwen3.6-27B-Opus-CoT-S1-Hermes-S2-SFTcot-dialect-llama3.1-8b-sft-l5cot-dialect-olmo3-7b-think-sft-l2cot-dialect-olmo3-7b-think-sft-l5cot-dialect-olmo3-7b-think-grpo-early-solve-l4cot-dialect-olmo3-7b-think-conditioned-sftcot-dialect-olmo3-7b-think-grpo-gr3chain-seed3-l5cot-dialect-qwen3-4b-instruct-grpo-gr3b110-l5cot-dialect-olmo3-7b-think-sft-l1cot-dialect-olmo3-7b-think-grpo-l1cot-dialect-olmo3-7b-think-grpo-reward-diff-sftlen-sq-dapo-l5cot-dialect-qwen3-4b-instruct-grpo-early-solve-l5cot-dialect-math-olmo3-7b-think-grpo-corr-l3cot-dialect-qwen3-4b-instruct-grpo-addlen110-l5cot-dialect-olmo3-7b-think-grpo-early-solve-l1meena-3-antigravity-cotcot-dialect-qwen3-14b-sft-l5cot-dialect-qwen3-4b-instruct-grpo-gr3-l5cot-dialect-llama3.1-8b-grpo-rerun-l4your-lora-repo-structured_data_with_cot_dataset_512_v2-0214cot-dialect-olmo3-7b-think-grpo-l5cot-dialect-llama3.1-8b-grpo-rerun-l5cot-dialect-olmo3-7b-think-grpo-gr3chain-seed2-l5cot-dialect-qwen3-14b-grpo-rerun-l5