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.
Qwen2.5-1.5B-Open-R1-SFT-1_new_datasetGPT2-finetune-openwebtext-150K_train_datasetfinetune_OpenHermes_2.5_prompt_v1_bf16_no_group_by_len_to_iterable_datasetopenscholar-8b-lora-finetuned-orca-datasetfinetune_OpenHermes_2.5_prompt_v4_group_by_len_bf16_lr1e-5_constant_max_len_1024_small_datasetfinetune_OpenHermes_2.5_prompt_v3_group_by_len_bf16_lr1e-5_constant_max_len_1024_small_datasetbeomi-Llama-3-Open-Ko-8B-KoCommercial-DatasetQwen2.5-3B-Open-R1-GRPO-1_new_datasetopen_math_model_mcqa_lora_full_datasetR1-Distill-Llama-8B-SFT-cotroller_dataset-bespoke_openthoughts3-ta_multiple-v2R1-Distill-Llama-8B-SFT-cotroller_dataset-bespoke_openthoughts-llama3-hehe-ta_ps_ct-v2R1-Distill-Llama-8B-SFT-cotroller_dataset-bespoke_openthoughts3-ta_multipleQwen2.5-3B-Open-R1-SFT-1_new_datasetllama3_mnli_0_shot_transformed_data_score_use_full_row_dataset_openaillama3_4_bit_mnli_0_shot_transformed_data_score_use_full_row_dataset_openaiidefics2-open-i-datasetopenchat_3.5_meld-dataset-instruct-multimodal_6_256mistral-7b-instruct-text-to-sql-OpenDatasetsFinetune