DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large #academic #ai #deepseek #research - ThreadSky

brunoamaral.eu • 34 days ago

https://arxiv.org/abs/2501.12948
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large

#academic #ai #deepseek #research

Comments

Posting Rules

Comments

Posting Rules

Reply