DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Qwen. With Tool Calling support.

tools 1.5b 7b 8b 14b 32b 70b 671b

16.6K 2 months ago

Readme

DeepSeek-R1 with Tool Calling

deepseek-r1

Paper Link👁️

DeepSeek’s first-generation reasoning models, achieving performance comparable to OpenAI-o1 across math, code, and reasoning tasks. This model checkpoint supports tool usage through a custom chat template, available at MFDoom/deepseek-r1-tool-calling.

Deepseek API Notice ⚠️

The current version of the deepseek-chat model’s Function Calling capabilitity is unstable, which may result in looped calls or empty responses. We are actively working on a fix, and it is expected to be resolved in the next version.

Models

1.5B Qwen DeepSeek R1

ollama run MFDoom/deepseek-r1-tool-calling:1.5b

7B Qwen DeepSeek R1

ollama run MFDoom/deepseek-r1-tool-calling:7b

8B Llama DeepSeek R1

ollama run MFDoom/deepseek-r1-tool-calling:8b

14B Qwen DeepSeek R1

ollama run MFDoom/deepseek-r1-tool-calling:14b

32B Qwen DeepSeek R1

ollama run MFDoom/deepseek-r1-tool-calling:32b

70B Llama DeepSeek R1

ollama run MFDoom/deepseek-r1-tool-calling:70b

671B DeepSeek R1

ollama run MFDoom/deepseek-r1-tool-calling:671b