{"id":"7bf7f824-3103-498e-a40e-bc17bf0e82fc","slug":"hf-model-dgurgurov-smollm3-3b-sft-grpo-fr-1vcuok8-w","name":"SmolLM3-3B-SFT-GRPO-FR","description":"Hugging Face model DGurgurov/SmolLM3-3B-SFT-GRPO-FR. Task: reinforcement learning. 20 downloads.","capabilities":["safetensors","smollm3","reasoning","multilingual","fr","reasonxl","reinforcement-learning","grpo","dataset:toroe/ReasonXL-SFT","arxiv:2604.12378","base_model:HuggingFaceTB/SmolLM3-3B","base_model:finetune:HuggingFaceTB/SmolLM3-3B"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:52.294Z"}