{"id":"63d1c411-5484-4bd7-8153-7595cbc6b697","slug":"hf-model-codelion-gemma-3-1b-it-reasoning-grpo-lora-1g4rv2v-16","name":"gemma-3-1b-it-reasoning-grpo-lora","description":"Hugging Face model codelion/gemma-3-1b-it-reasoning-grpo-lora. Task: text generation. Library: peft. 21 downloads. 4 likes.","capabilities":["peft","safetensors","ellora","lora","reasoning","chain-of-thought","grpo","thinking","preference-learning","self-improvement","gemma","text-generation","en","dataset:codelion/gemma-3-1b-it-magpie-reasoning","base_model:google/gemma-3-1b-it","base_model:adapter:google/gemma-3-1b-it","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:37.163Z"}