DeepSeek releases R1 reasoning model with open-weight options
DeepSeek releases R1, a 671B MoE reasoning model with MIT-licensed weights, distilled variants for Llama and Qwen, and pricing 27–50× lower than OpenAI o1.
DeepSeek released DeepSeek R1, a significant upgrade over DeepSeek V3 from just three weeks prior, featuring 8 models including full-size 671B MoE models and multiple distillations from Qwen 2.5 and Llama 3.1/3.3. The models are MIT licensed, allowing finetuning and distillation. Pricing is notably cheaper than o1 by 27x-50x. The training process used GRPO (reward for correctness and style outcomes) without relying on PRM, MCTS, or reward models, focusing on reasoning improvements through reinforcement learning.
Distilled models can run on Ollama and show strong capabilities like writing Manim code. The release emphasizes advances in reinforcement-learning, fine-tuning, and model-distillation with a novel RL framework from DeepSeekMath.