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.
math-shepherd-mistral-7b-prm-calibrated-Llama-3.2-1B-Instructsunflower-qwen3.5-9b-grpo-maths-thinkingsunflower-qwen3.5-9b-grpo-maths-nothinkmath_solving_modelmath-shepherd-mistral-7b-prm-calibrated-Qwen2.5-Math-1.5B-Instructmathstral-7b-grpo-no-draftphi-2-basic-mathsmath-solver-llama3-Q8_0-GGUFmathstral-7b-mismatched-wrong-draftsmathstral-7b-matched-wrong-draftsMath-SmolLM2-1.7BMATH_SFT_Q2.5-1.5BI_r16mathstral-7b-mismatched-correct-draftsMATH_SFT_L3.2-3BI_r64gemma-2b-lora-maths-orca-200kMATH_SFT_Q2.5-3BI_r16MATH_SFT_Q2.5-1.5BI_r64MATH_SDOS_Q2.5-3BI_r16gemma3-1b-it-4bit-reasoning-gmat-mathsmath-sft-adapterMATH_SFT_Q3.0-4BI_r64MATH_SFT_Q3.0-4BI_r16MATH_SDOS_L3.2-3BI_r16MATH_SDOS_L3.1-8BI_r16math-sft-a17-loramath-solver-llama3MATH_SFT_L3.2-3BI_r16math-shepherd-mistral-7b-prm-calibrated-DeepSeek-R1-Distill-Llama-8BMATH_SFT_Q2.5-7BI_r16MATH_SDOS_Q2.5-7BI_r16