deepseek-ai
/

DeepSeek-R1-Distill-Qwen-14B

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (3)

Is there any method to limit the thinking process of this model?

#18 opened about 17 hours ago by

How to load the model on Kaggle or Colab

#17 opened 3 days ago by

能否开一下基于transfomers的inference代码

#16 opened 12 days ago by

I use Q4_K_M with lmstudio 0.3.9 and it keeps saying 'failed to regenerate message'. Why?

#15 opened 14 days ago by

是否可以推出量化版本

#14 opened 15 days ago by

如何强制它不偷懒的进行推理呢

#13 opened 17 days ago by

🚩 Report

#12 opened 22 days ago by

Disable Think text

#11 opened 27 days ago by

[Bug] Critical Context Loss in DeepSeek-R1: Model Hallucinates <think> Tag into Arbitrary Replacements, Fails to Maintain Coherent Reasoning

#9 opened about 1 month ago by

Add pipeline tag, link to paper

#8 opened about 1 month ago by

800K Samples dataset release?

#7 opened about 1 month ago by

How to load the model?

#6 opened about 1 month ago by

Why change the configuration of the tokenizer?

#4 opened about 1 month ago by

System Prompt

#2 opened about 1 month ago by