{"id":"8a478f86-9c7d-4a16-8922-6781791d7d35","slug":"hf-model-vedant33-supersede-qwen2-5-3b-grpo-lora-fatnvh-13","name":"supersede-qwen2.5-3b-grpo-lora","description":"Hugging Face model vedant33/supersede-qwen2.5-3b-grpo-lora. Task: text generation. Library: peft. 33 downloads.","capabilities":["peft","safetensors","lora","grpo","reinforcement-learning","rlvr","memory","long-horizon","agents","qwen2.5","supersede","arxiv:2606.27472","text-generation","en","dataset:vedant33/supersede-rl-episodes","dataset:xiaowu0162/longmemeval-cleaned","base_model:Qwen/Qwen2.5-3B-Instruct","base_model:adapter:Qwen/Qwen2.5-3B-Instruct","license:apache-2.0","model-index"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:35.473Z"}