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.
qwen3-30b-a3b-gdpo-rslora-rlaif-turkish-call-centerqwen3-4b-gdpo-rlaif-turkish-call-center-16bit-fullQwen3-1.7B-MATH-GDPOsapo-gdpo-dora-qwen-structopensec-gdpo-4bqwen3-4b-gdpo-rlaif-turkish-call-center-16bitqwen3-30b-a3b-gdpo-rlaif-turkish-call-centerpii_grpo_r1a16_gdpoqwen3-4b-rlaif-gdpoQwen3-1.7B-MATH-GDPO-EPOCH2gdpo-qwen-structured-mergedgdpo_qwen3_8b_finalqwen3-4b-gdpo-length-sft-l1qwen3-4b-gdpo-length-sft-l2qwen3_8b_gdpo_midqwen3-4b-gdpo-length-sft-l4qwen3-4b-gdpo-length-sft-l5cot-dialect-olmo3-7b-think-grpo-gdpochain-l5cot-dialect-olmo3-7b-think-grpo-gdpochain-seed7-l5cot-dialect-qwen3-4b-instruct-grpo-gdpochain-l5Qwen3-1.7B-Open-R1-GDPO-epcoh_qwen3-4b-gdpo-length-sft-l3cot-dialect-olmo3-7b-think-grpo-gdpoonly-l5C-MORAL-Mistral-GDPOMiniOneRec-1.5B-SFT-GDPOQwen3.5-9B-smith-v5-gdpo-exact
