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.
qwen_no_prefill_35steps_50samples_multiturnQweb2.5-Aloe-Beta-Finetuned-50Steps-diff-rewardfunctionsQweb2.5-Aloe-Beta-Finetuned-50Stepsllama-3.2-3b-instruct-finetuned_step28_50samples27steps_50sample_single_turnstep28_50samples_multi_turn_correct_system_promptno_prefill_28steps_50samples_multiturnsig_p_50s_male_easternsig_s_50s_female_westernsig_q_50s_male_westernsig_r_50s_female_easterngemma-3-1b-quant-50stepsgemma-3-50stepsDPO-3-1k-50steps-2ds_llama8b_50steps_modelDeepSeek-R1-Distill-Qwen-7B-Unburden-v1-50stepsds_qwen7b_50steps_modellora3_newData_50step_r128DPO-3-1k-50stepssuggestions_model_50stepstata_4_policies_50epCPT_50stpIFTLab3-Qwen2.5-32B-50step-sortedFine_tuning_unsloth-Llama-3.2-3B-Instruct_50stepsFine_tuning_unsloth-Llama-3.2-1B-Instruct_50stepsqwen-2.5-3B-dragon-control-warmup-50stepsrocm-axolotl-mixtral-8x22b-rocm-single-50step
