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.
Test_Llama3-lighteval-finetune-mergedQwen_Qwen2.5-0.5B-Instruct-DigitalLearningGmbH_MATH-lighteval-RL_mergedQwen_Qwen2.5-0.5B-Instruct-DigitalLearningGmbH_MATH-lighteval-RL-fullllm-jp-3-13b-instruct2-grpo-MATH-lighteval_step1000Qwen2.5-1.5B-Instruct_MATH-lighteval_epoch_1_bs_8_lr_2e-05_length_2048_G_16Qwen2.5-7B-Open-R1-GRPO-math-lighteval-nonscale-weightedQwen2.5-7B-Open-R1-GRPO-math-lighteval-1epochstop-withformatQwen2.5-7B-Open-R1-GRPO-math-lighteval-v2Qwen2.5-7B-Open-R1-GRPO-math-lighteval-cosineQwen2.5-7B-Open-R1-GRPO-math-lighteval-olympiads-aime-unique-cosine-v4Qwen2_5-7B-Instruct-MATH-lighteval-f003b272-f37a-46ca-b8d1-65c4c935a5b8Qwen2.5-7B-Open-R1-GRPO-math-lighteval-olympiads-aime-unique-cosine-v6Qwen2.5-3B-MATH-lighteval-gen-SFTQwen2.5-3B-MATH-lighteval-gen-SFT-8epochQwen2.5-7B-Open-R1-GRPO-math-lightevalQwen2.5-7B-Open-R1-GRPO-math-lighteval-weightedQwen2.5-7B-Open-R1-GRPO-math-lighteval-noformatQwen-2.5-Base-7B-gen8-scale-MATH-lighteval-olympiads_aime-ghpoQwen2.5-7B-Open-R1-GRPO-math-lighteval-weighted-syncQwen2.5-7B-Open-R1-GRPO-math-lighteval-logQwen-2.5-Base-7B-gen8-scale-MATH-lighteval-olympiads_aime-grpoQwen-2.5-Base-7B-gen8-scale-MATH-lighteval-olympiads_aime-unique-grpo-beta0-epoch2Qwen-2.5-Base-3B-gen8-scale-MATH-lighteval-olympiads_aime-unique-ghpo-beta0-epoch3Qwen2.5-7B-Open-R1-GRPO-math-lighteval-olympiads-aime-unique-cosine-onlyQwen2.5-7B-Open-R1-GRPO-math-lighteval-olympiads-aime-unique-cosine-noRW-noformatQwen2.5-1.5B-MATH-lighteval-gen-SFTQwen2.5-3B-MATH-lighteval-gen-SFT-15epochQwen2_5-7B-Instruct-MATH-lighteval-6cfe4679-d1e0-40a0-a853-274205751f3dQwen2.5-7B-Open-R1-GRPO-math-lighteval-olympiads-aime-unique-cosineQwen-2.5-Base-7B-gen8-scale-MATH-lighteval-olympiads_aime-unique-ghpo-beta0-epoch2