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.
llama-3.1-8B-Instruct_playpen_SFT_DFINAL_0.7K-steps_merged_fp16Mistral-Small-24B-Instruct-2501_playpen_SFT_merged_fp16_DFINAL_0.6K-stepsSFT-base_merged_fp16_E1_D40005SFT-merged_fp16_DFINAL_1.1K-stepsllama-SFT-base_merged_fp16_D90053_copy_32GBllama-3.1-8B-Instruct_playpen_SFT_DFINAL_0.7K-steps_merged_full_precisionllama-3.1-8B-Instruct_playpen_SFT_DFINAL_0.7K-steps_merged_full_precision_copyQwen2-7B-SFT_mergedllama-SFT-base_merged_fp16_D90053meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D40005_Michael_unload_from4bitllama-3.1-70B-Instruct_playpen_SFT_DFINAL_0.6K-steps_merged_fp16meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D40005_full_precisionclembench-playpen__llama-3.1-8B-Instruct_playpen_SFT_DFINAL_0.7K-steps_merged4bitmeta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D40005_merged_16bitmeta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D40005_merged_4bitclembench-playpen__Llama8B_DPO_turn_solved_merged_bfloat16clembench_REFUEL_base_1-4000clembench_REFUEL_SFT_1_iter2-4000clembench_REFUEL_SFT_1_iter2-2000clembench-playpen-llama-3.1-8B-Instruct_playpen_SFT_DFINAL_0.7K-stepsllama-3.1-8B-Instruct-v1.6-only-fp_SFT_e1_DABL01_merged_fp16llama3.1_8B_DPO_from_fp_merged_full_precisionclembench-playpen__llama-3.1-8B-Instruct_playpen_SFT_DFINAL_0.7K-steps_merged_bfloat16clembench-playpen__Llama8B_DPO_turn_solved_merged4bitclembench_REFUEL_SFT_3-4000clembench_REFUEL_SFT_1-1000clembench_REFUEL_SFT_1-2000clembench_REFUEL_SFT_1-3000clembench_REFUEL_SFT_1_iter2-3000llama-3.1-8B-Instruct_playpen_ablation_SFT_DFINAL_0.1K-steps_merged_fp16
