deepseek-ai
/

DeepSeek-R1-Distill-Qwen-32B

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (4)

Create chatsetup.py

#43 opened 17 days ago by

申请发布awq格式模型：deepseek-ai/DeepSeek-R1-Distill-Qwen-32B-AWQ

#42 opened 18 days ago by

scsdifyonlie

#41 opened 21 days ago by

Update README.md

#40 opened 23 days ago by

Update README.md

#39 opened 23 days ago by

Request: DOI

#38 opened 26 days ago by

dragos-bajenaru37

[RESOLVED] Model is not outputting the <think> token at the beginning.

#37 opened 27 days ago by

🚩 Report

#36 opened about 1 month ago by

Generate crashed by repeatedly generating <think>

#35 opened about 1 month ago by

Weird......Dose it 32b model support vision ability ？

#34 opened about 1 month ago by

Set base_model to deepseek-ai/DeepSeek-R1

#33 opened about 1 month ago by

How to build tools call system prompt?

#32 opened about 1 month ago by

The input starts with the token "<|begin▁of▁sentence|>" repeated twice. / 输入开头重复2次“<|begin▁of▁sentence|>”

#31 opened about 1 month ago by

Can you distill qwen-2.5-72b?

#30 opened about 1 month ago by

weight files naming is not regular rule

#29 opened about 1 month ago by

bos_token_id is defined incorrectly

#28 opened about 1 month ago by

Longer context length

#26 opened about 1 month ago by

Qwen 32B Compatibility on PC w/ Ryzen 7 Pro 8840HS w/ 780M Graphics 2x32GB RAM 1TB DDR5 SSD

#25 opened about 1 month ago by

请问我在用llama-factory微调distill-qwen系列模型时，模型名称选哪个？

#24 opened about 1 month ago by

Update README.md

#23 opened about 1 month ago by

Update README.md

#22 opened about 1 month ago by

Tokenizer config's `chat_template` removes everything before `</think>` XML closing tag

#21 opened about 1 month ago by

Consistency, can Deepseek pass? 一致性，deepseek能及格吗？

#20 opened about 1 month ago by

running on local machine

#19 opened about 1 month ago by

Poor performance in the leaderboard?

#17 opened about 2 months ago by

Add text-generation pipeline tag

#16 opened about 2 months ago by

comfyui-deepseek-r1

#15 opened about 2 months ago by

sharing something maybe beneficial ?

#13 opened about 2 months ago by

Please convert these models to GGUF format...

#12 opened about 2 months ago by

Support For Japanese Model

#11 opened about 2 months ago by

Tokenizer config is wrong

#10 opened about 2 months ago by

Garbage characters generated with using 32B

#9 opened about 2 months ago by

Please add a qwen2.5-72b distill

#8 opened about 2 months ago by

Does this have tooling support?

#7 opened about 2 months ago by

What temp are these expected to be used at?

#6 opened about 2 months ago by

YaRN block required?

#5 opened about 2 months ago by

Please add a qwen coder 32b distill.

#4 opened about 2 months ago by

System Prompt

#2 opened about 2 months ago by