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.
phi-redactor-qwen3-1.7bmistral-flo-finetune-2-T42026-08-04-qwen36-lora-1000ex-difficult-advice-350-t1-t4-numina-650deepseek-r1-grpo-cot-t4T4_LN512_DR0.08_EPO3_LR1e-5_qwen3-4b-structured-output-loraT4_LN512_DR0.08_EPO2_LR1e-5_qwen3-4b-structured-output-loraqwen3-4b-v5-r16-ep2-lr5e6-seq1024-t4protGPT2_2025_QLoRA_r4_T4Matsuo2025-Main-Qwen3-4B-SFT-T4-v1mistral-qlora-t4its-t4-grpoqwen3-4b-instruct-2507-lora-homework_vo3_2_T4autotrain-ki4xs-t44zqautotrain-at2xk-t4ojtqwen3-4b-sft-t4-LR1e-5qwen3-4b-sft-t4-LR3e-5qwen3-4b-sft-t4-hpsearch_1e-5qwen3-4b-sft-t4-hpsearch_3e-5qwen3-4b-sft-t4-hpsLR3e-5WR0.05qwen3-4b-sft-t4-hpsLR3e-5WR0.2qwen3-4b-sft-t4-hpsearch_3e-5seed42qwen3-4b-sft-t4-hpsearch_3e-5_epoch2qwen3-4b-sft-t4-mix-latestqwen3-4b-sft-t4-mix-r40d60-latestqwen3-4b-sft-t4-mix-r60d40-latestqwen3-4b-sft-t4-mix-r30d70-latestqwen3-4b-sft-t4-mix-r70d30-latestlora_agentbench_qwen3_4b_d26_t4qwen3-4b-sft-t4-alfv5-only-latestqwen3-4b-sft-t4-mix-r85d15-lowlr-latest
