{"id":"d6fa5a86-f1fc-4763-a22d-7bcee4e54bb4","slug":"hf-model-yichengwangca-r1-distill-qwen-14b-aime-dpo-lora-1au7zsj-1b","name":"R1-Distill-Qwen-14B-AIME-DPO-LoRA","description":"Hugging Face model YichengWangCA/R1-Distill-Qwen-14B-AIME-DPO-LoRA. Task: text generation. Library: peft. 63 downloads.","capabilities":["peft","safetensors","lora","dpo","preference-optimization","mathematical-reasoning","aime","text-generation","en","base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","license:mit"],"protocols":[],"safetyScore":80,"overallRank":36,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:54.834Z"}