In recent years, Large Language Models (LLMs) have been undergoing rapid iteration and evolution (OpenAI, 2024a; Anthropic, 2024; Google, 2024), progressively diminishing the gap towards Artificial General Intelligence (AGI). Recently, post-training has emerged as an important component of the full training pipeline. It has been shown to enhance accuracy on reasoning tasks, align with social value
There are a few key ingredients about the design and training of k1.5. Long context scaling. We scale the context window of RL to 128k and observe continued improvement of performance with an increased context length. A key idea behind our approach is to use partial rollouts to improve training efficiency---i.e., sampling new trajectories by reusing a large chunk of previous trajectories, avoiding
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. However, DeepSeek-R1-Z
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
処理を実行中です
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
