deepseek-ai
/

DeepSeek-R1-Distill-Llama-8B

Text Generation

text-generation-inference

Model card Files Files and versions Community

Resources

View closed (5)

add AIBOM

#30 opened 14 days ago by

why the model inference so slowly??

#29 opened about 1 month ago by

abc

#27 opened 2 months ago by

How to disable the thinking mode?

#26 opened 3 months ago by

How to solve this Warning?

#25 opened 4 months ago by

Does Recommended Usage apply to the distilled models?

#24 opened 4 months ago by

🚩 Report: Not working

#23 opened 4 months ago by

Output bug

#22 opened 4 months ago by

Example Prompts

#21 opened 4 months ago by

duplicated bos_token when using apply_chat_template with Tokenizer

#20 opened 4 months ago by

tokenizer.model

#19 opened 4 months ago by

Update README.md

#18 opened 4 months ago by

<think> tag is missing in the latest revision

#17 opened 4 months ago by

微调DeepSeek-R1打造SQL语言转自然语言视频教程

#16 opened 5 months ago by

One more "0" in model-00001-of-000002.safetensors?

#15 opened 5 months ago by

Excellent models !!! - Plans for Mistral Nemo and/or Gemma 2 Distills ?

#14 opened 5 months ago by

Adding Evaluation Results

#12 opened 5 months ago by

Missing multilanguage capabilities

#11 opened 5 months ago by

run in colab t4

#9 opened 5 months ago by

Adding Evaluation Results

#8 opened 5 months ago by

Add pipeline tag, link to paper

#7 opened 5 months ago by

Do the distilled models also have 128K context?

#4 opened 5 months ago by

How was this quantized?

#3 opened 5 months ago by

missing special_tokens_map.json file

#2 opened 5 months ago by