{"id":"2506f8f6-1539-42ad-a9ba-886e967f5496","slug":"hf-model-erata-qwen3-4b-dimacs-cube-grpo-v1-reasoning-dpo-8k-v3-16gp4hu-1i","name":"Qwen3-4B-dimacs_cube-grpo-v1-reasoning-dpo-8k-v3","description":"Hugging Face model erata/Qwen3-4B-dimacs_cube-grpo-v1-reasoning-dpo-8k-v3. Task: text generation. Library: transformers. 28 downloads.","capabilities":["transformers","safetensors","qwen3","text-generation","generated_from_trainer","trl","unsloth","dpo","conversational","arxiv:2305.18290","base_model:Yale-ROSE/Qwen3-4B-dimacs_cube_mix_prompt_2k-unsloth-grpo-v1","base_model:finetune:Yale-ROSE/Qwen3-4B-dimacs_cube_mix_prompt_2k-unsloth-grpo-v1","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:51.238Z"}