{"id":"aeb8cd6d-f638-4262-aff7-0397e15f9562","slug":"hf-model-lark-lab-switch-phase3-grpo-lora-qwen3-8b-3c92c1-15","name":"SWITCH-Phase3-GRPO-LoRA-Qwen3-8B","description":"Hugging Face model LARK-Lab/SWITCH-Phase3-GRPO-LoRA-Qwen3-8B. Task: text generation. Library: peft. 25 downloads.","capabilities":["peft","safetensors","switch","qwen3","lora","coconut","latent-cot","reasoning","math","on-policy-rl","grpo","text-generation","conversational","en","dataset:LARK-Lab/SWITCH-Math-Train","arxiv:2606.13106","base_model:Qwen/Qwen3-8B","base_model:adapter:Qwen/Qwen3-8B","license:mit"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:09.772Z"}