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.
gpt2-toxicity-conditional-25000gpt2-pii-mle-25000Instruct_2500_pretraining16bitInstruct_2500_reworded_plusalpacaInstruct_2500_pretraining16bit_plusalpacatiny-giant-2500-q4_k_mInstructpretrainingQA2500_nonleadingaicrowd-qwen3-8b-sft-80k-grpo-ph1-chkp2500qwen-finetuned-25004bit-Gemma3-1b-it-natural-reasoning-2500Instruct_2500_pretraining16bit_plusalpacaInstruct_2500_reworded_plusalpacallama-3.2-1b-instruct-gms8k-sft-2500steps-notquantizedInstructpretrainingQA2500_nonleadingInstruct_2500_pretraining16bitQwen3-4B-unsloth-bnb-4bit-villager-finetune-1-epoch-filtered-dataset-2500-examplesgemma3-4B-unsloth-bnb-4bit-villager-finetune-1-epoch-filtered-dataset-2500-examplesqwen-dpo-epfl-data-2500qwen-dpo-stack-data-2500qwen-dpo-stack-epfl-data-2500qwen3-4B_agentbench_gendataV5_v0_with_R16_LR1E5-checkpoint-2500pmsp_llama8b_lora_25000