deepseek-ai/DeepSeek-R1

#110 opened 20 days ago by

neethuvm

Deepseek-R1

#109 opened 20 days ago by

KudanTao

deepseek-r1 源码中采用 MLA 架构的 KV Cache 压缩存储策略的实现似乎与文中说的不一致，这是为什么？代码中似乎没实现这个大优化

#108 opened 20 days ago by

Darkdust

Sitting in bed room

#107 opened 21 days ago by

makecash

Eating food in a car

#106 opened 21 days ago by

Ayinbaby1313

Update README.md

#103 opened 22 days ago by

jungvaclav

error while downloading model

8

#102 opened 22 days ago by

heikhama1982

Upload IMG_20250112_172711.jpg

#101 opened 22 days ago by

aamir1

help from italy

5

#100 opened 22 days ago by

MMPPIIAA

R1 distill to Mistral Small?

#99 opened 22 days ago by

nfunctor

Running this model on Google Colab?

#98 opened 22 days ago by

Zakia

请问下deepseek的同学，能不能train出一个 stable 的 moe model?

#97 opened 22 days ago by

tflchina

How to download DeepSeek-R1 7B parameters

#96 opened 23 days ago by

barqawiz

HuggingFace version does NOT use efficient MLA caching

#95 opened 23 days ago by

Avelina

Found a bug

#93 opened 23 days ago by

amalgunatilake

Let's Give Credit Where It’s Due: Adding Source Links to AI Responses

#88 opened 24 days ago by

Munis01

When will this be available in Transformers library?

#87 opened 24 days ago by

solwol

cannot regenerate (blank respone)

#86 opened 25 days ago by

pluhong

A Bug using hugging face API

#85 opened 25 days ago by

Kevin355

Do we need an authorization access to use this ?

#84 opened 25 days ago by

Natwar

where is the source code for this Model ? - what does they prodoudly say by open-source models?

#83 opened 25 days ago by

tstarksys

智王发布deepseek-r1懒人包，解压即用Deepseek-r1 Lazy Package, easy to decompress and use

#81 opened 25 days ago by

zwpython

model-00078-of-000163.safetensors not marked safe?

#80 opened 25 days ago by

aborst

Create Dare

#79 opened 25 days ago by

Dara996

problem with using serverless inference

#78 opened 25 days ago by

manju2345

Some weird sensorship on unsensitive topic. 对非敏感话题的奇怪审查。

8

#77 opened 25 days ago by

junnanwu

Upload dkfoEtm3H4bMcaI0KEJbq.1023.jpeg

#76 opened 25 days ago by

luckysalami089

Update README.md

#75 opened 26 days ago by

NuoNb

🚩 Report: Ethical issue(s)

#74 opened 26 days ago by

Typeofprototype

Deepseek-R1 falls: ZW demon redesigns' Nine Birds' Deepseek-R1沦陷：zw魔改版“九只鸟”

#73 opened 26 days ago by

zwpython

Consistency, can Deepseek pass?一致性，deepseek能及格吗？

#71 opened 26 days ago by

zwpython

Does this model support text insertion (fill in middle)?

#70 opened 26 days ago by

AayushShah

Thoughts on deepseek-r1. Correct me if I'm wrong

#69 opened 27 days ago by

pkms

ImportError: cannot import name 'is_torch_greater_or_equal_than_1_13' from 'transformers.pytorch_utils'

10

#67 opened 27 days ago by

bashir-abubakar

e-currency

#63 opened 27 days ago by

Zhendaxie

Meet PEEPSEEK, the first meme made by DeepSeek r1

#61 opened 27 days ago by

deepseeker3b56

鲸 Logo transparent

#60 opened 27 days ago by

DorianDarko2525

Meet Finley, the Whale of DeepSeek!

#59 opened 27 days ago by

deepseekjanus

Official DeepThink Crypto Currency

#56 opened 27 days ago by

qwen-llm

Congrats, this is the by far the best open source model! Just a few steps until complete domination (feedback)

#54 opened 27 days ago by

Dampfinchen

deepseek

#53 opened 27 days ago by

denizkaya2022

Modify abbreviations in benchmark images into full name to avoid confusion

#52 opened 27 days ago by

karminski

Hizkuntza

#50 opened 27 days ago by

Joxio

How to deploy DeepSeek-R1 witn LMDeploy ?

#48 opened 27 days ago by

vansin

Qwen

#47 opened 28 days ago by

Moukli

使用不带 thinking 的数据集微调时无法正常生成