shipfeedAI news, curated daily

00:39:28 CET
21 MAY00:39:28shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

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.

Jan 21 · · primary fetch1 sourceupdated Jan 21 ·

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.

read full article on news.smol.ai
§ sources1 publication · timeline below
  1. news.smol.aiDeepSeek R1: o1-level open weights model and a simple recipe for upgrading 1.5B models to Sonnet/4o levelprimary