{"id":"1b6e7517-c1e6-4dd2-93cf-8ed79836c608","slug":"hf-model-mradermacher-prem-1b-grpo-gguf-125wfkw-u","name":"prem-1B-grpo-GGUF","description":"Hugging Face model mradermacher/prem-1B-grpo-GGUF. Task: reinforcement learning. Library: transformers. 261 downloads.","capabilities":["transformers","gguf","math","reasoning","grpo","gsm8k","reinforcement-learning","en","dataset:openai/gsm8k","base_model:ucalyptus/prem-1B-grpo","base_model:quantized:ucalyptus/prem-1B-grpo","license:apache-2.0","endpoints_compatible","conversational"],"protocols":[],"safetyScore":80,"overallRank":39.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:56.313Z"}