deepseek-ai/DeepSeek-R1

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

2

#70 opened 11 days ago by

AayushShah

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

1

#69 opened 11 days ago by

pkms

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

10

#67 opened 11 days ago by

bashir-abubakar

e-currency

3

#63 opened 12 days ago by

Zhendaxie

Meet PEEPSEEK, the first meme made by DeepSeek r1

1

#61 opened 12 days ago by

deepseeker3b56

鲸 Logo transparent

#60 opened 12 days ago by

DorianDarko2525

Meet Finley, the Whale of DeepSeek!

#59 opened 12 days ago by

deepseekjanus

Official DeepThink Crypto Currency

1

#56 opened 12 days ago by

qwen-llm

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

1

#54 opened 12 days ago by

Dampfinchen

deepseek

#53 opened 12 days ago by

denizkaya2022

Modify abbreviations in benchmark images into full name to avoid confusion

#52 opened 12 days ago by

karminski

Hizkuntza

#50 opened 12 days ago by

Joxio

How to deploy DeepSeek-R1 witn LMDeploy ?

#48 opened 12 days ago by

vansin

Qwen

2

#47 opened 13 days ago by

Moukli

使用不带 thinking 的数据集微调时无法正常生成

1

#46 opened 13 days ago by

HuanLin

Use memory to store inactive experts

#45 opened 13 days ago by

xm10086

qwen32B蒸馏模型，长度>8k时，预测一定比例乱码，出现<think><think><think><think><think><think>

5

#44 opened 14 days ago by

daniellibin

Update LICENSE

#43 opened 14 days ago by

town24

edit paper link to hf for easier conversations

#41 opened 15 days ago by

clem

Upload 80b78bb2-3b7e-4a0c-a76c-93e1503c7b30.jpeg

#40 opened 15 days ago by

Uman1

The LICENSE-MODEL file is missing??

#39 opened 15 days ago by

spanspek

New permissions gate doesn't look valid

3

#38 opened 15 days ago by

AdjectiveAllison

Amazing Release! Can we also have DeepSeek-R1-Zero-Qwen-32B

#37 opened 15 days ago by

cfpark00

Question about possible R1 - lite versions 70b / 32b

#36 opened 15 days ago by

smokestudio

Update README.md

1

#35 opened 15 days ago by

sloshywings

Add pipeline tag

#34 opened 15 days ago by

nielsr

aaa

#33 opened 16 days ago by

aaaaaaa34

Deploying production ready Deepseek R1 on your AWS with vLLM

6

#32 opened 16 days ago by

samagra14

Create Stephy

#31 opened 16 days ago by

Kouadio12

comfyui-deepseek-r1

#30 opened 16 days ago by

zwpython

I can't use your model in hugginsface spaces

2

#29 opened 16 days ago by

MrEscorpion

Upload IMG_2394.jpeg

#28 opened 16 days ago by

Itsvijay12

Upload IMG_2394.jpeg

#27 opened 16 days ago by

Itsvijay12

its amazing model , i found one free to experience r1

#26 opened 16 days ago by

LLMhacker

Suggestion for censorship disclosure - odd responses from R1

7

#25 opened 16 days ago by

vmajor

Transformer version required?

#24 opened 16 days ago by

Pradeep1995

how to install and use on local machine windows

9

#23 opened 17 days ago by

Merk0701234

深度思考和联网搜索的使用问题

#22 opened 17 days ago by

hentaisenpai

Hardware requirements?

27

#19 opened 17 days ago by

JohnnieB

Wow

#18 opened 17 days ago by

Litorect

Congratulating DeepSeek-R1 and Inviting Review of Our Team’s Early Research last year on Similar Ideas

#17 opened 17 days ago by

zhengchenphd

BF16 model from open source community

#15 opened 18 days ago by

OpenSourceRonin

还是要16卡才能推理吧？

2

#14 opened 18 days ago by

qqianxiao

add library name & auto-tag

#13 opened 19 days ago by

reach-vb

Is this the same as DeepSeek-R1 (Preview) mentioned on LiveCodeBench?

2

#10 opened 19 days ago by

KrishnaKaasyap

chore: update configuration_deepseek.py

#9 opened 19 days ago by

eltociear

Wen R2D2?

1

#8 opened 19 days ago by

TiFoil

Where is R1-Lite?

2

#5 opened 19 days ago by

aryadytm

The ASI-Singularity(Godsend) is the only Global Solution, people.

#4 opened 19 days ago by

AntDX316

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

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

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

e-currency

Meet PEEPSEEK, the first meme made by DeepSeek r1

鲸 Logo transparent

Meet Finley, the Whale of DeepSeek!

最近的炒作和硬币

Official DeepThink Crypto Currency

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

deepseek

Modify abbreviations in benchmark images into full name to avoid confusion

Hizkuntza

How to deploy DeepSeek-R1 witn LMDeploy ?

Qwen

使用不带 thinking 的数据集微调时无法正常生成

Use memory to store inactive experts

qwen32B蒸馏模型，长度>8k时，预测一定比例乱码，出现<think><think><think><think><think><think>

Update LICENSE

edit paper link to hf for easier conversations

Upload 80b78bb2-3b7e-4a0c-a76c-93e1503c7b30.jpeg

The LICENSE-MODEL file is missing??

New permissions gate doesn't look valid

Amazing Release! Can we also have DeepSeek-R1-Zero-Qwen-32B

Question about possible R1 - lite versions 70b / 32b

Update README.md

Add pipeline tag

aaa

Deploying production ready Deepseek R1 on your AWS with vLLM

Create Stephy

comfyui-deepseek-r1

I can't use your model in hugginsface spaces

Upload IMG_2394.jpeg

Upload IMG_2394.jpeg

its amazing model , i found one free to experience r1

Suggestion for censorship disclosure - odd responses from R1

Transformer version required?

how to install and use on local machine windows

深度思考和联网搜索的使用问题

Hardware requirements?

Wow

Congratulating DeepSeek-R1 and Inviting Review of Our Team’s Early Research last year on Similar Ideas

BF16 model from open source community

还是要16卡才能推理吧？

add library name & auto-tag

Is this the same as DeepSeek-R1 (Preview) mentioned on LiveCodeBench?

chore: update configuration_deepseek.py

Wen R2D2?

Where is R1-Lite?

The ASI-Singularity(Godsend) is the only Global Solution, people.