deepseek-ai/DeepSeek-V3

Deepseek V3

#93 opened 4 days ago by

cybercyb

【Q】shared_head weights of MTP

#92 opened 7 days ago by

huang11

fix for transformers 4.49 compatibility.

#91 opened 9 days ago by

katuni4ka

Update README.md

#90 opened 9 days ago by

baishihao

无辅助损失专家偏置代码实现的小问题 A Small Issue in the Code Implementation of Auxiliary-Loss-Free Load Balancing Expert Bias

#89 opened 14 days ago by

liyang31163150

Fix generation with latest transformers

#88 opened 17 days ago by

kylesayrs

Add pipeline tag

#86 opened 22 days ago by

nielsr

Some of the safetensor files are not marked as safe

#85 opened 24 days ago by

tanmaylaud

Update README.md

#84 opened 26 days ago by

MTayira

ValueError: Must flatten tensors with uniform dtype but got torch.bfloat16 and torch.float8_e4m3fn

#82 opened 29 days ago by

ajtakto

Update README.md

#81 opened about 1 month ago by

FYSIOBASEN

Update README.md

#80 opened about 1 month ago by

zhup

Update README.md

#79 opened about 1 month ago by

zhup

chat

#77 opened about 1 month ago by

rojithonline

DeepSeek-V3-lite naming conventions?

6

#76 opened about 1 month ago by

AlphaGaO

torch.distributed.DistNetworkError

#75 opened about 1 month ago by

yu19920006607

remove reference to deprecated transformers code

2

#74 opened about 1 month ago by

winglian

Update README.md

#73 opened about 1 month ago by

SamimSaikia

DeepSeek R1 answer ChatGPT ??

4

#72 opened about 1 month ago by

valerebron

ValueError: Unrecognized configuration class <class 'transformers_modules.configuration_deepseek.DeepseekV3Config'> to build an AutoTokenizer.

10

#69 opened about 2 months ago by

ajtakto

Paralelized script

#67 opened about 2 months ago by

ajtakto

I am getting an error message while executing pip install - r requirements. txt

5

#64 opened about 2 months ago by

yu19920006607

`aux_loss_alpha` should be 1e-4 instead of 1e-3?

#61 opened about 2 months ago by

cuichenx

captcha not loading on edge

#60 opened 2 months ago by

leo-smi

Upload shreya.zip

#59 opened 2 months ago by

Msdthala

Upload IMG_20250111_184317.jpg

#58 opened 2 months ago by

Sajalhero

无辅助损失的专家路由

2

#56 opened 2 months ago by

qing9

AI Games

#55 opened 2 months ago by

ChickenUJHAYIUSGU

Upload IMG_0509 4.HEIC

#54 opened 2 months ago by

borhanrabbany

how to inference with mtp?

#53 opened 2 months ago by

duanyu

Does it support ollama

2

#52 opened 2 months ago by

sminbb

Create gngn

#49 opened 2 months ago by

axingd

Missing tool call in system prompt

2

#48 opened 2 months ago by

bchenfireworks

Update config.json

#47 opened 2 months ago by

STATIKwitak

Rename figures/benchmark.png to figures/𓇋𓀀𓍿.png

#46 opened 2 months ago by

STATIKwitak

Rename figures/benchmark.png to figures/𓇋𓀀𓍿.png

#45 opened 2 months ago by

STATIKwitak

moi

1

#44 opened 2 months ago by

Celyndo

Upload IMG_0295.HEIC

#42 opened 2 months ago by

Umarkhan499

vLLM on A100s

6

#41 opened 2 months ago by

fsaudm

When do you plan to integrate Huggingface Transformer?

#40 opened 2 months ago by

echo-yi

Deciphering messages

1

#39 opened 2 months ago by

DoctorDonald

Update README.md

#38 opened 2 months ago by

chaitanyayerroju

Update README.md

1

#37 opened 2 months ago by

TomGrc

Training problem

3

#29 opened 2 months ago by

DonGan13

Update README.md

1

#28 opened 2 months ago by

Wisnet

Update README.md

2

#27 opened 2 months ago by

Aikun7777777

Failed to run the model with 4 nodes of 8 4090

17

#25 opened 2 months ago by

aisensiy

kill openai，come on

#24 opened 2 months ago by

chaochaoli

Update modeling_deepseek.py

1

#23 opened 2 months ago by

erichartford

is_torch_greater_or_equal_than_1_13 deprecated

#22 opened 2 months ago by

erichartford