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.
16.6K Pulls Updated 2 months ago
Updated 2 months ago
2 months ago
9a3bad754abb · 4.7GB
Readme
DeepSeek-R1 with Tool Calling
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