Deepseek R1 0528 Qwen3 8B AWQ

🚀 DeepSeek-R1-0528

The DeepSeek R1 model has been upgraded to version DeepSeek-R1-0528, significantly enhancing reasoning and inference capabilities. It shows outstanding performance in benchmarks and approaches leading models like O3 and Gemini 2.5 Pro.

🚀 Quick Start

You can chat with DeepSeek-R1 on DeepSeek's official website: chat.deepseek.com, and switch on the button "DeepThink". We also provide OpenAI-Compatible API at DeepSeek Platform: platform.deepseek.com.

✨ Features

• Enhanced Reasoning: The DeepSeek R1 model has improved its depth of reasoning and inference capabilities through increased computational resources and algorithmic optimization during post - training. It performs well in various benchmarks such as mathematics, programming, and general logic, approaching the performance of leading models like O3 and Gemini 2.5 Pro.
• Reduced Hallucination: This version offers a reduced hallucination rate.
• Function Calling Support: It has enhanced support for function calling.
• Better Vibe Coding Experience: It provides a better experience for vibe coding.

📚 Documentation

1. Introduction

The DeepSeek R1 model has undergone a minor version upgrade to DeepSeek - R1 - 0528. In the latest update, by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post - training, it has significantly improved its depth of reasoning and inference capabilities. The model has shown outstanding performance in various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of leading models, such as O3 and Gemini 2.5 Pro.

Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For example, in the AIME 2025 test, the model’s accuracy has increased from 70% in the previous version to 87.5% in the current version. This improvement comes from enhanced thinking depth during the reasoning process: in the AIME test set, the previous model used an average of 12K tokens per question, whereas the new version averages 23K tokens per question.

Beyond improved reasoning capabilities, this version also offers a reduced hallucination rate, enhanced support for function calling, and a better experience for vibe coding.

2. Evaluation Results

DeepSeek - R1 - 0528

For all our models, the maximum generation length is set to 64K tokens. For benchmarks requiring sampling, we use a temperature of $0.6$, a top - p value of $0.95$, and generate 16 responses per query to estimate pass@1.

Note: We use Agentless framework to evaluate model performance on SWE - Verified. We only evaluate text - only prompts in HLE testsets. GPT - 4.1 is employed to act user role in Tau - bench evaluation.

DeepSeek - R1 - 0528 - Qwen3 - 8B

We distilled the chain - of - thought from DeepSeek - R1 - 0528 to post - train Qwen3 8B Base, obtaining DeepSeek - R1 - 0528 - Qwen3 - 8B. This model achieves state - of - the - art (SOTA) performance among open - source models on the AIME 2024, surpassing Qwen3 8B by +10.0% and matching the performance of Qwen3 - 235B - thinking. We believe that the chain - of - thought from DeepSeek - R1 - 0528 will be of significant importance for both academic research on reasoning models and industrial development focused on small - scale models.

4. How to Run Locally

Please visit [DeepSeek - R1](https://github.com/deepseek - ai/DeepSeek - R1) repository for more information about running DeepSeek - R1 - 0528 locally.

Compared to previous versions of DeepSeek - R1, the usage recommendations for DeepSeek - R1 - 0528 have the following changes:

1. System prompt is supported now.
2. It is not required to add "<think>\n" at the beginning of the output to force the model into thinking pattern.

The model architecture of DeepSeek - R1 - 0528 - Qwen3 - 8B is identical to that of Qwen3 - 8B, but it shares the same tokenizer configuration as DeepSeek - R1 - 0528. This model can be run in the same manner as Qwen3 - 8B, but it is essential to ensure that all configuration files are sourced from our repository rather than the original Qwen3 project.

System Prompt

In the official DeepSeek web/app, we use the same system prompt with a specific date.

The assistant is DeepSeek - R1, created by DeepSeek Company.
Today is {current date}.

For example,

The assistant is DeepSeek - R1, created by DeepSeek Company.
Today is May 28, 2025, Monday.

Temperature

In our web and application environments, the temperature parameter $T_{model}$ is set to 0.6.

Prompts for File Uploading and Web Search

For file uploading, please follow the template to create prompts, where {file_name}, {file_content} and {question} are arguments.

file_template = \
"""[file name]: {file_name}
[file content begin]
{file_content}
[file content end]
{question}"""

For Web Search, {search_results}, {cur_date}, and {question} are arguments. For Chinese query, we use the prompt:

search_answer_zh_template = \
'''# The following contents are the search results related to the user's message:
{search_results}
In the search results I provide to you, each result is formatted as [webpage X begin]...[webpage X end], where X represents the numerical index of each article. Please cite the context at the end of the relevant sentence when appropriate. Use the citation format [citation:X] in the corresponding part of your answer. If a sentence is derived from multiple contexts, list all relevant citation numbers, such as [citation:3][citation:5]. Be sure not to cluster all citations at the end; instead, include them in the corresponding parts of the answer.
When responding, please keep the following points in mind:
- Today is {cur_date}.
- Not all content in the search results is closely related to the user's question. You need to evaluate and filter the search results based on the question.
- For listing-type questions (e.g., listing all flight information), try to limit the answer to 10 key points and inform the user that they can refer to the search sources for complete information. Prioritize providing the most complete and relevant items in the list. Avoid mentioning content not provided in the search results unless necessary.
- For creative tasks (e.g., writing an essay), ensure that references are cited within the body of the text, such as [citation:3][citation:5], rather than only at the end of the text. You need to interpret and summarize the user's requirements, choose an appropriate format, fully utilize the search results, extract key information, and generate an answer that is insightful, creative, and professional. Extend the length of your response as much as possible, addressing each point in detail and from multiple perspectives, ensuring the content is rich and thorough.
- If the response is lengthy, structure it well and summarize it in paragraphs. If a point-by-point format is needed, try to limit it to 5 points and merge related content.
- For objective Q&A, if the answer is very brief, you may add one or two related sentences to enrich the content.
- Choose an appropriate and visually appealing format for your response based on the user's requirements and the content of the answer, ensuring strong readability.
- Your answer should synthesize information from multiple relevant webpages and avoid repeatedly citing the same webpage.
- Unless the user requests otherwise, your response should be in the same language as the user's question.
# The user's message is:
{question}'''

For English query, we use the prompt:

search_answer_en_template = \
'''# The following contents are the search results related to the user's message:
{search_results}
In the search results I provide to you, each result is formatted as [webpage X begin]...[webpage X end], where X represents the numerical index of each article. Please cite the context at the end of the relevant sentence when appropriate. Use the citation format [citation:X] in the corresponding part of your answer. If a sentence is derived from multiple contexts, list all relevant citation numbers, such as [citation:3][citation:5]. Be sure not to cluster all citations at the end; instead, include them in the corresponding parts of the answer.
When responding, please keep the following points in mind:
- Today is {cur_date}.
- Not all content in the search results is closely related to the user's question. You need to evaluate and filter the search results based on the question.
- For listing-type questions (e.g., listing all flight information), try to limit the answer to 10 key points and inform the user that they can refer to the search sources for complete information. Prioritize providing the most complete and relevant items in the list. Avoid mentioning content not provided in the search results unless necessary.
- For creative tasks (e.g., writing an essay), ensure that references are cited within the body of the text, such as [citation:3][citation:5], rather than only at the end of the text. You need to interpret and summarize the user's requirements, choose an appropriate format, fully utilize the search results, extract key information, and generate an answer that is insightful, creative, and professional. Extend the length of your response as much as possible, addressing each point in detail and from multiple perspectives, ensuring the content is rich and thorough.
- If the response is lengthy, structure it well and summarize it in paragraphs. If a point-by-point format is needed, try to limit it to 5 points and merge related content.
- For objective Q&A, if the answer is very brief, you may add one or two related sentences to enrich the content.
- Choose an appropriate and visually appealing format for your response based on the user's requirements and the content of the answer, ensuring strong readability.
- Your answer should synthesize information from multiple relevant webpages and avoid repeatedly citing the same webpage.
- Unless the user requests otherwise, your response should be in the same language as the user's question.
# The user's message is:
{question}'''

📄 License

This code repository is licensed under MIT License. The use of DeepSeek - R1 models is also subject to MIT License. DeepSeek - R1 series (including Base and Chat) supports commercial use and distillation.

🔧 Technical Details

AWQ quantization: done by stelterlab in INT4 GEMM with AutoAWQ by casper - hansen (https://github.com/casper - hansen/AutoAWQ/). Original Weights by DeepSeek AI.

📚 Citation

@misc{deepseekai2025deepseekr1incentivizingreasoningcapability,
      title={DeepSeek - R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning}, 
      author={DeepSeek - AI},
      year={2025},
      eprint={2501.12948},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2501.12948}, 
}

📞 Contact

If you have any questions, please raise an issue or contact us at service@deepseek.com.