deepseek-ai/DeepSeek-V4-Pro

#166 opened 1 day ago by

toton12

Add YC-Bench benchmark result (avg $1,066,426)

#165 opened 2 days ago by

RiddleHe

Will there be small models like 12b?

👍👀 2

6

#164 opened 3 days ago by

Crownelius

Assigned weights for different teachers. 教师权重的分配

#162 opened 4 days ago by

lsh-algorithm

Where is HCA implemented?

#161 opened 4 days ago by

lsh-algorithm

思考链下会出现英文混乱

5

#160 opened 4 days ago by

smodeltest

Partial Rotary Positional Embedding 的笔误？

👀 4

#159 opened 5 days ago by

WKQ9411

模型文件注释里的形状似乎写错了

#158 opened 6 days ago by

yzll

什么时候支持api上传文档就好了

#156 opened 7 days ago by

icbw

deepseek-ai/DeepSeek-V4-Pro

#153 opened 8 days ago by

cmax123

16 - 24B models with FP8 quantization

👍 4

#152 opened 8 days ago by

Duonglv

Support other low-bit quantization methods?

#151 opened 9 days ago by

kiwei91

源神启动！恭喜deepseekV4顺利上线，合影！

#150 opened 9 days ago by

JCrainy

Общение

11

#149 opened 9 days ago by

Lev0478

Update README.md to add SGLang deployment option

#148 opened 9 days ago by

zjxia

Add pipeline tag to allow for HF Inference Providers

#147 opened 9 days ago by

nbroad

Add chat template

🔥 1

#146 opened 10 days ago by

Rocketknight1

Instruction following still not good

#145 opened 10 days ago by

xcx0902

核弹椅子摔瘫坐

#144 opened 10 days ago by

shishen

Is it possible to have API output with origin completion prompt including | DSML | token

#143 opened 10 days ago by

httpwwwfszyc

恭喜deepseek v4可以撑地了

🚀 6

#142 opened 10 days ago by

keflag

代码能力真的是世界第一吗！！！

#141 opened 10 days ago by

LumiDriz

开源的模型可以自己去评测，闭源的模型怎么测试呢？最近扎堆发布，GPT5.5，HY3.0 Preview，大家是不是内部都知道各个产品的时间呢？

#140 opened 10 days ago by

dennisbo

恭喜！

#139 opened 10 days ago by

luolita13

恭喜上线

#138 opened 10 days ago by

wSi0n

GOOD JOB!

#136 opened 10 days ago by

Friedland

恭喜恭喜

#135 opened 10 days ago by

ryw001

deepseek niu bee plus

#134 opened 10 days ago by

shanxinle

V4必火！

#133 opened 10 days ago by

yvanw

火钳流明

#132 opened 10 days ago by

leonz03

I'm very disappointed in this release

🔥➕ 14

11

#131 opened 10 days ago by

Dampfinchen

DeepSeek 666

#130 opened 10 days ago by

dingwenzheng

Technical Report Summary

🧠 1

#129 opened 10 days ago by

mishig

Legendary drop

🔥 2

#128 opened 10 days ago by

kamell

合影留念~~~

#127 opened 10 days ago by

BI9CZR

关于 "Observations and Proposals" 中激活函数建议的疑问：去掉 gate projection 为何能放宽 EP 带宽要求？

#126 opened 10 days ago by

MarjorTom

Help me recover my deepseek account

❤️ 2

#125 opened 10 days ago by

lulavc

请问是否有计划出自己的coding plan？

#124 opened 10 days ago by

jackz990

V4留念 ~~~

#123 opened 10 days ago by

jackz990

Is it uses engrams?

👀 3

#122 opened 10 days ago by

Regrin

做了一个免费试用的deepseek4.0的 chat 大家可以自己使用 https://huggingface.co/spaces/wangsheng/DeepSeekV4Chat

👍 6

5

#121 opened 10 days ago by

wangsheng

用国外模型研究国产模型，也是支持国产了

#120 opened 10 days ago by

2025carry

蹲前排

#119 opened 10 days ago by

VenusZ

WE WERE HERE

#118 opened 10 days ago by

FRareDom2

牛逼！！！！

#117 opened 10 days ago by

miniwhite

合影留念

#116 opened 10 days ago by

usst-ziyi

训练也是昇腾吗？

#115 opened 10 days ago by

yxdys

Real Open AI