{"id":"72da459c-1c3f-4e22-b68a-07518b41eb25","slug":"hf-model-budget-internalization-iclr2027-qwen3-5-4b-4k-grpo-overlong-penalty-awaretick-s300-ug9oum-2a","name":"qwen3.5-4b-4k-grpo-overlong-penalty-awaretick-s300","description":"Hugging Face model budget-internalization-iclr2027/qwen3.5-4b-4k-grpo-overlong-penalty-awaretick-s300. Task: image text to text. Library: transformers. 28 downloads.","capabilities":["transformers","safetensors","qwen3_5","image-text-to-text","reasoning","math","grpo","reinforcement-learning","token-budget","conversational","dataset:agentica-org/DeepScaleR-Preview-Dataset","base_model:Qwen/Qwen3.5-4B","base_model:finetune:Qwen/Qwen3.5-4B","license:apache-2.0","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:53.113Z"}