{"id":"5622d7ed-98e2-41c0-b14b-7be8d88fc5a8","slug":"hf-model-pradheep1647-grpo-think-len-baseline-1stldnk-10","name":"grpo-think-len-baseline","description":"Hugging Face model Pradheep1647/grpo-think-len-baseline. Library: peft. 24 downloads.","capabilities":["peft","safetensors","lora","grpo","trl","reasoning","length-penalty","dataset:openai/gsm8k","base_model:Qwen/Qwen3-1.7B","base_model:adapter:Qwen/Qwen3-1.7B"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:16.876Z"}