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.
birag-gemma4-e2b-response-only-ggufbirag-gemma4-e2b-response-onlypythia-6b-rm-response-only-full-hhpythia-6b-rm-response-onlyQwen2.5-3B-Instruct_MATH_training_response_Qwen2.5_3B_only_rightQwen2.5-0.5B-Instruct_MATH_training_sdft_response_Qwen2.5_0.5B_only_rightQwen2.5-3B-Instruct_MATH_training_sdft_response_Qwen2.5_3B_only_rightQwen2.5-1.5B-Instruct_MATH_training_response_Qwen2.5_1.5B_only_rightQwen2.5-0.5B-Instruct_MATH_training_response_gpt-4o-mini_only_rightQwen2.5-3B-Instruct_MATH_training_response_gpt-4o-mini_only_rightQwen2.5-1.5B-Instruct_MATH_training_response_gpt-4o-mini_only_rightQwen2.5-1.5B-Instruct_MATH_training_sdft_response_Qwen2.5_1.5B_only_rightQwen2.5-0.5B-Instruct_MATH_training_response_Qwen2.5_0.5B_only_rightQwen2.5-7B-Instruct_MATH_training_response_gpt-4o-mini_only_rightQwen2.5-7B-Instruct_MATH_training_sdft_response_Qwen2.5_7B_only_rightQwen2.5-7B-Instruct_MATH_training_response_Qwen2.5_7B_only_rightQwen-2.5-7B-Embedding-Entropy-0.45-Missing-Response-grouped-correct-only-mean-tokenmerged_finesearch_10K_16bit_1epoch_response_onlygemma3_27b_vertex_helios_from_d22c_neutral_lr1e5_response_only-a8d6gemma3_27b_vertex_helios_from_d22c_neutral_lr1e4_response_only-3a6eqwen2.5-3b-pgabl-ardhi-response-only-exp1_lr2e4_r8_s1200Qwen-2.5-7B-Embedding-Entropy-0.45-Missing-Response-grouped-correct-onlyQwen2.5-32B-Instruct-emergent-finetune-unittest_responses_only_rank32birag-gemma4-e2b-response-only-loraImmuneCoT-Qwen3-4B-ResponseOnlyqwen3-4b-icot-responseonly