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.
Llama-3.2-1B-MathCodeInstruct-5kDataDecide-dolma1_7-no-math-code-1B-60000_62500_65000_67500_69369_weightedavg_mergeQwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-e-step29Llama-3.2-1B-MathCodeInstruct-10kLlama-3.2-1B-MathCodeInstruct-20kTinyLlama_v1.1_math_codeMathLLM-MathCoder-CL-7B-GGUFDataDecide-dolma1_7-no-math-code-1B-57500_60000_62500_65000_67500_weightedavg_mergetinyllama-coder-math-ja-wikipedia-v0.1DataDecide-dolma1_7-no-math-code-1B-55000_57500_60000_62500_65000_weightedavg_mergeDataDecide-dolma1_7-no-math-code-1B-52500_55000_57500_60000_62500_weightedavg_mergeDataDecide-dolma1_7-no-math-code-1B-50000_52500_55000_57500_60000_weightedavg_mergeMoe-4x7b-math-reason-codentp-mathlib-context-deepseek-coder-1.3bDataDecide-dolma1_7-no-math-code-1B-47500_50000_52500_55000_57500_weightedavg_mergedolphin-2.1-mistral-7b-snr-math-laserQwen3-Sushi.Math.Code.Expert-0.6BQwen2.5-Coder-1.5B-Qwen2.5-Math-1.5B-Merged-moeMerge-Math-Coder-7B-v3DataDecide-dolma1_7-no-math-code-1B-45000_47500_50000_52500_55000_weightedavg_mergeMathLLM-MathCoder-L-7B-GGUFQwen3-4b-2507-Thinking-math-and-codeMathCoder-L-7BDataDecide-dolma1_7-no-math-code-1B-42500_45000_47500_50000_52500_weightedavg_mergeMerge-Math-Coder-7B-v2ntp-mathlib-st-deepseek-coder-1.3bQwen2.5-Coder-1.5B-Instruct_MATH_training_response_Qwen_QwQ_32B_Preview_common_correct_levelQwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen2.5-32B-InstructDeepseek-Coder-V2-Lite-13B-Instruct-sft-math7kMathCoder-L-13B