DeepSeek-V3.1

Introduction

DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. Compared to the previous version, this upgrade brings improvements in multiple aspects:

• Hybrid thinking mode: One model supports both thinking mode and non-thinking mode by changing the chat template.
• Smarter tool calling: Through post-training optimization, the model's performance in tool usage and agent tasks has significantly improved.
• Higher thinking efficiency: DeepSeek-V3.1-Think achieves comparable answer quality to DeepSeek-R1-0528, while responding more quickly.

DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens. Additionally, DeepSeek-V3.1 is trained using the UE8M0 FP8 scale data format to ensure compatibility with microscaling data formats.

Model Downloads

Chat Template

The details of our chat template is described in tokenizerconfig.json and assets/chattemplate.jinja. Here is a brief description.

Non-Thinking

#### First-Turn

Prefix:
<｜begin▁of▁sentence｜>{system prompt}<｜User｜>{query}<｜Assistant｜>

With the given prefix, DeepSeek V3.1 generates responses to queries in non-thinking mode. Unlike DeepSeek V3, it introduces an additional token .

#### Multi-Turn
Context:
<｜begin▁of▁sentence｜>{system prompt}<｜User｜>{query}<｜Assistant｜>{response}<｜end▁of▁sentence｜>...<｜User｜>{query}<｜Assistant｜>{response}<｜end▁of▁sentence｜>

Prefix:
<｜User｜>{query}<｜Assistant｜>

By concatenating the context and the prefix, we obtain the correct prompt for the query.

Thinking

#### First-Turn
Prefix:
<｜begin▁of▁sentence｜>{system prompt}<｜User｜>{query}<｜Assistant｜>

The prefix of thinking mode is similar to DeepSeek-R1.

#### Multi-Turn
Context:
<｜begin▁of▁sentence｜>{system prompt}<｜User｜>{query}<｜Assistant｜>{response}<｜end▁of▁sentence｜>...<｜User｜>{query}<｜Assistant｜>{response}<｜end▁of▁sentence｜>

Prefix:
<｜User｜>{query}<｜Assistant｜>

The multi-turn template is the same with non-thinking multi-turn chat template. It means the thinking token in the last turn will be dropped but the is retained in every turn of context.

ToolCall

<｜begin▁of▁sentence｜>{system prompt}{tooldescription}<｜User｜>{query}<｜Assistant｜> where the tooldescription is

## Tools
You have access to the following tools:

{tool_name1}
Description: {description}

Parameters: {json.dumps(parameters)}

IMPORTANT: ALWAYS adhere to this exact format for tool use:
<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>toolcallname<｜tool▁sep｜>toolcallarguments<｜tool▁call▁end｜>{{additionaltoolcalls}}<｜tool▁calls▁end｜>

Where:
toolcallname must be an exact match to one of the available tools
toolcallarguments must be valid JSON that strictly follows the tool's Parameters Schema
For multiple tool calls, chain them directly without separators or spaces

Code-Agent

Search-Agent

For complex questions that require accessing external or up-to-date information, DeepSeek-V3.1 can leverage a user-provided search tool through a multi-turn tool-calling process.

Please refer to the assets/searchtooltrajectory.html and assets/searchpythontool_trajectory.html for the detailed template.

Evaluation

Note:

• Search agents are evaluated with our internal search framework, which uses a commercial search API + webpage filter + 128K context window. Seach agent results of R1-0528 are evaluated with a pre-defined workflow.
• SWE-bench is evaluated with our internal code agent framework.
• HLE is evaluated with the text-only subset.

Usage Example

import transformers

tokenizer = transformers.AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V3.1")

messages = [
    {"role": "system", "content": "You are a helpful assistant"},
    {"role": "user", "content": "Who are you?"},
    {"role": "assistant", "content": "<think>Hmm</think>I am DeepSeek"},
    {"role": "user", "content": "1+1=?"}
]

tokenizer.applychattemplate(messages, tokenize=False, thinking=True, addgenerationprompt=True)
'<｜begin▁of▁sentence｜>You are a helpful assistant<｜User｜>Who are you?<｜Assistant｜></think>I am DeepSeek<｜end▁of▁sentence｜><｜User｜>1+1=?<｜Assistant｜><think>'


tokenizer.applychattemplate(messages, tokenize=False, thinking=False, addgenerationprompt=True)
'<｜begin▁of▁sentence｜>You are a helpful assistant<｜User｜>Who are you?<｜Assistant｜></think>I am DeepSeek<｜end▁of▁sentence｜><｜User｜>1+1=?<｜Assistant｜></think>'

How to Run Locally

The model structure of DeepSeek-V3.1 is the same as DeepSeek-V3. Please visit DeepSeek-V3 repo for more information about running this model locally.

License

This repository and the model weights are licensed under the MIT License.

Citation

@misc{deepseekai2024deepseekv3technicalreport,
      title={DeepSeek-V3 Technical Report}, 
      author={DeepSeek-AI},
      year={2024},
      eprint={2412.19437},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.19437}, 
}

Contact

If you have any questions, please raise an issue or contact us at [email protected].