deepseek-ai/DeepSeek-R1

如何取消/省略<think></think>过程。

#178 opened about 13 hours ago by

yech520

Request: DOI

#177 opened about 22 hours ago by

Tamwyn

Request: DOI

#176 opened 2 days ago by

saathwik

Request: DOI

#175 opened 3 days ago by

Paulabad

Draft model as accelerator for DeepSeek-R1?

#174 opened 3 days ago by

inputout

Does R1 support long context (> 4K)?

#172 opened 4 days ago by

ghostplant

Deploying production ready service with Unsloth GGUF quants on your AWS account. (4 x L40S)

8

#171 opened 4 days ago by

samagra-tensorfuse

是否可以关注Perplexity推出的“r1-1776”模型？

4

#170 opened 4 days ago by

yanyihan

Just crossed 10,000 likes!

1

#169 opened 5 days ago by

clem

mac上面无法下载flash_attn

#168 opened 6 days ago by

earlyIsLate

Can this model be used for commercial use?

2

#167 opened 6 days ago by

henrycwf

90+ tokens per second for MI300x8 using batch_size = 1

1

#166 opened 7 days ago by

ghostplant

RytryR1

#165 opened 7 days ago by

Rocka01

"aha moment" comment deleted by Perplexity (recovered)

3

#164 opened 7 days ago by

FalconNet

输出乱码

1

#163 opened 8 days ago by

cell22

'num_hidden_layers': 61, but layer 62 has weights.

#162 opened 8 days ago by

xinhe

Upload GTG Breaking every Limit

#161 opened 8 days ago by

GTGenesis

support prefix complete

3

#158 opened 10 days ago by

HuggineAllen

Create app.py

#157 opened 11 days ago by

SpaceAgeRobotics

Create 1

#156 opened 11 days ago by

madevii

Brokersponsor

#155 opened 12 days ago by

Brokersponsor

Update README.md

#154 opened 12 days ago by

egegvner

Upload IMG_4530.png

#152 opened 13 days ago by

Noemie202586

Upload IMG_1745.JPG

#151 opened 13 days ago by

Ladib

Create Clara

1

#150 opened 13 days ago by

Clblinks

If I understand correctly, evaluating MATH-500 requires 64*500 model calls?

1

#149 opened 15 days ago by

Rorschaaaach

Request: DOI

#148 opened 15 days ago by

Tarush-Appreciate

Update README.md

#147 opened 15 days ago by

tekno-power

Update README.md

#146 opened 15 days ago by

Ekimnedops6969

Adding <think>\n after chat template will cause vllm to not return reasoning_content (null) when reasoning

6

#144 opened 16 days ago by

kebeliu

Update README.md

1

#143 opened 16 days ago by

MuhammadEhsan

Request for Information on Purchasing Reasoning API Key

1

#142 opened 16 days ago by

brahamaandai

ssss

1

#140 opened 18 days ago by

DZGT

Update model_max_length in tokenizer_config.json

#139 opened 18 days ago by

kkokkie2360

Host of the model

3

#138 opened 18 days ago by

henrycwf

Lite version for DeepSeek-R1?

1

#137 opened 19 days ago by

haili-tian

[Bug] assert not self.training

1

#136 opened 19 days ago by

Gaie

Upload IMG_0253.HEIC

#134 opened 19 days ago by

rynty

Upload comment-sample.xlsx

#133 opened 19 days ago by

faham123

non-reasoning data

#132 opened 20 days ago by

cmgzy

能不能放一些 4bit的权重，现在手里面的卡都不支持FP8

1

#131 opened 21 days ago by

zhnagchenchne

For the universe! DeepPhaser.py DeepCoralX.py and DeepSynapse.py

3

#129 opened 21 days ago by

karmikovic

Request: Create distill of Mistral Small 24B

3

#128 opened 21 days ago by

Kenshiro-28

which vision model is R1 using for text extraction from image or pdfs.

2

#127 opened 21 days ago by

ashutoshroy02

PRII

#126 opened 21 days ago by

bajramani

Request: DOI

#125 opened 22 days ago by

Yungchizzy

Little brother(s) of big DeepSeek-R1 ?

2

#124 opened 22 days ago by

MrDevolver

Upload gugagagaggagagagga.pdf

1

#123 opened 22 days ago by

HahahhahH

Tool / Function Calling

3

#122 opened 23 days ago by

smcleod

Change quant_method to bitsandbytes_4bit

#121 opened 23 days ago by

ngoc24794

如何取消/省略<think></think>过程。

Request: DOI

Request: DOI

Request: DOI

Draft model as accelerator for DeepSeek-R1?

Does R1 support long context (> 4K)?

Deploying production ready service with Unsloth GGUF quants on your AWS account. (4 x L40S)

是否可以关注Perplexity推出的“r1-1776”模型？

Just crossed 10,000 likes!

mac上面无法下载flash_attn

Can this model be used for commercial use?

90+ tokens per second for MI300x8 using batch_size = 1

RytryR1

"aha moment" comment deleted by Perplexity (recovered)

输出乱码

'num_hidden_​​layers': 61, but layer 62 has weights.

Upload GTG Breaking every Limit

support prefix complete

Create app.py

Create 1

Brokersponsor

Update README.md

Upload IMG_4530.png

Upload IMG_1745.JPG

Create Clara

If I understand correctly, evaluating MATH-500 requires 64*500 model calls?

Request: DOI

Update README.md

Update README.md

Adding <think>\n after chat template will cause vllm to not return reasoning_content (null) when reasoning

Update README.md

Request for Information on Purchasing Reasoning API Key

ssss

Update model_max_length in tokenizer_config.json

Host of the model

Lite version for DeepSeek-R1?

[Bug] assert not self.training

Upload IMG_0253.HEIC

Upload comment-sample.xlsx

non-reasoning data

能不能放一些 4bit的权重，现在手里面的卡都不支持FP8

For the universe! DeepPhaser.py DeepCoralX.py and DeepSynapse.py

Request: Create distill of Mistral Small 24B

which vision model is R1 using for text extraction from image or pdfs.

PRII

Request: DOI

Little brother(s) of big DeepSeek-R1 ?

Upload gugagagaggagagagga.pdf

Tool / Function Calling

Change quant_method to bitsandbytes_4bit

'num_hidden_layers': 61, but layer 62 has weights.