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.
deepseek-R1-0528-Qwen3-8b-base-16-llvm-sft-trained-16bit-epoch-2-mergeddeepseek-R1-0528-Qwen3-8b-llvm-sft-trained-16bit-epoch-2-mergeddeepseek-R1-0528-Qwen3-8b-base-16-llvm-sft-trained-16bit-epoch-1-mergedQwen2.5-7B-Instruct-Nemo-Mix-Train-merged-4-bitmicrosoft-phi-2-trained-abliterated-QA-1960-all-modules-mergedmos-mamba-18x130m-trainer-dgx-lora-sft-mergedtrained-test-model-1-mergedduration_mistral_train_run4_mergedDeepSeek-R1-Medical-Distill-Qwen-1.5B-Trained-Alvin0618-Mergellama-3-8b-hf-sm-lora-merged-turbo1716917348065591_mlabonne-guanaco-llama2-1k_trainllama-31-8b-base-120k_minp_plus_train_500_ADAPTOR_MERGEDllama2-jc-trained-mergedduration_mistral_train_run2_mergedtraining_Llama3.2_3B_mergedphi3-0608_all_of_train-dpo-mergedta_merged_Qwen2.5-1.5B_preference_trained-2025-09-14_09.11.10trained-test-model-1-merged-newta_merged_Qwen2.5-1.5B_preference_trained-2025-09-14_10.36.28gemma-3-270m-ties-merged-trained-on-responsestrained-2k10-v4-model-mergedmistral_train_run1_mergedwitness_count_mistral_train_run2_mergedwitness_count_mistral_train_run3_mergedwitness_count_mistral_train_run7_mergedwitness_count_mistral_train_run8_mergedduration_mistral_train_run1_mergedduration_mistral_train_run3_mergedDeepSeek-R1-Medical-Distill-Qwen-1.5B-Trained-Alvin0619-Mergephi4-finetune-finetome-20260211-100630-best-trainloss-step03900-merged16mistral_train_run3_merged