mirror of
https://github.com/deepseek-ai/DeepSeek-R1.git
synced 2025-04-04 02:39:05 -04:00
Delete CITATION.cff
This commit is contained in:
parent
fecf26ff97
commit
95aaec702f
18
CITATION.cff
18
CITATION.cff
@ -1,18 +0,0 @@
|
||||
cff-version: 1.2.0
|
||||
message: "If you use this work, please cite it using the following metadata."
|
||||
title: "DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning"
|
||||
authors:
|
||||
- name: "DeepSeek-AI"
|
||||
year: 2025
|
||||
identifiers:
|
||||
- type: doi
|
||||
value: 10.48550/arXiv.2501.12948
|
||||
- type: arXiv
|
||||
value: 2501.12948
|
||||
url: "https://arxiv.org/abs/2501.12948"
|
||||
categories:
|
||||
- "cs.CL"
|
||||
repository-code: "https://github.com/deepseek-ai/DeepSeek-R1"
|
||||
license: "MIT"
|
||||
abstract: >
|
||||
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, demonstrates remarkable reasoning capabilities. Through RL, DeepSeek-R1-Zero naturally emerges with numerous powerful and intriguing reasoning behaviors. However, it encounters challenges such as poor readability, and language mixing. To address these issues and further enhance reasoning performance, we introduce DeepSeek-R1, which incorporates multi-stage training and cold-start data before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1-1217 on reasoning tasks. To support the research community, we open-source DeepSeek-R1-Zero, DeepSeek-R1, and six dense models (1.5B, 7B, 8B, 14B, 32B, 70B) distilled from DeepSeek-R1 based on Qwen and Llama.
|
Loading…
Reference in New Issue
Block a user