{"id":"1659008b-0bf3-43bf-adea-4ab9d7f1a099","slug":"hf-model-tinyllms-deepseek-r1-distill-qwen-7b-sft-aime-1pu2ydn-19","name":"deepseek-r1-distill-qwen-7b-sft-aime","description":"Hugging Face model tinyllms/deepseek-r1-distill-qwen-7b-sft-aime. 23 downloads.","capabilities":["safetensors","qwen2","max_seq_length=16384","lr=2e-5","batch_size=1","grad_accum=16","epochs=3","qlora","quantize=4bit_nf4","lora_rank=64","lora_alpha=128","lora_dropout=0.05","completion_only_loss","eval_size=0.1","cosine_schedule","warmup=0.05","bf16","run_name=sft-deepseek-aime","hub_model_id=tinyllms/deepseek-r1-distill-qwen-7b-sft-aime","ray_job=raysubmit_GYFgmtmvD3Fcm9Cb"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:22.846Z"}