Resources

View closed (11)

Can you provide your base models in BF16 format, instead of FP16?

#29 opened about 12 hours ago by

Vahid-Rakhshan

问下，这种模型可不可以只出专用语言的模型

👀 1

#28 opened 2 months ago by

shijunti19

How to achieve reliable native function calling

#24 opened 3 months ago by

Ithanil

72B variant

#23 opened 3 months ago by

darkstar3537

pull

#22 opened 3 months ago by

Lyohanesberg

A question about inference

#20 opened 3 months ago by

JohnsonWythe

👍👍

👍 1

#19 opened 3 months ago by

hu5enpai

json_schema not working

👍 1

#18 opened 3 months ago by

LaferriereJC

Qwen3 Coder Model User Reviews and Comparison with Other Coding Models Like K2 Instruct

#16 opened 3 months ago by

DeepNLP

Downloading Model never complete

#14 opened 3 months ago by

yusufhadiwinata

How is Qwen3's inv_freq computed from scratch?

#13 opened 3 months ago by

ghostplant

Instruct model outputs reasoning tokens

#12 opened 3 months ago by

steve2972

How to locally host qwen3 coder

#11 opened 3 months ago by

judycc

🚀 Evaluation Best Practice !

👍 5

#10 opened 3 months ago by

Yunxz

Local Testing Video - Step by Step

#9 opened 3 months ago by

fahdmirzac

Sooooool Cool! 太棒了！有兴趣的朋友一起加微信群聊聊模型部署推理使用经验

#8 opened 3 months ago by

jakyer

Does it support FIM?

👍 1

#7 opened 3 months ago by

yanghan111

Any chance of a smaller coding model in the 30-70b range?

🚀 ❤️ 50

#6 opened 3 months ago by

smcleod