aleshribar3/deepseek-r1-tool-calling:7b

aleshribar3/ deepseek-r1-tool-calling:7b

598 Downloads Updated 2 weeks ago

I have just enabled both calling and thinking to existing deepseek-r1 models.

tools thinking 1.5b 7b 8b 14b 32b

ollama run aleshribar3/deepseek-r1-tool-calling:7b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "aleshribar3/deepseek-r1-tool-calling:7b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='aleshribar3/deepseek-r1-tool-calling:7b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'aleshribar3/deepseek-r1-tool-calling:7b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 weeks ago

2 weeks ago

be292203bd74 · 4.7GB ·

model

archqwen2

parameters7.62B

quantizationQ4_K_M

4.7GB

params

{ "stop": [ "<｜begin▁of▁sentence｜>", "<｜end▁of▁sentence｜>",

148B

license

1.1kB

template

{{- if .System }}{{ .System }}{{ end }} {{- if .Tools }} ## Tools ### Function You have the followin

1.7kB

Readme

DeepSeek-R1 with Tool Calling and Thinking

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 aleshribar3/deepsek-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

8B Qwen DeepSeek R1

ollama run aleshribar3/deepseek-r1-tool-calling:latest

1.5B Qwen DeepSeek R1

ollama run aleshribar3/deepseek-r1-tool-calling:1.5b

7B Qwen DeepSeek R1

ollama run aleshribar3/deepseek-r1-tool-calling:7b

14B Qwen DeepSeek R1

ollama run aleshribar3/deepseek-r1-tool-calling:14b

32B Qwen DeepSeek R1

ollama run aleshribar3/deepseek-r1-tool-calling:32b

### DeepSeek-R1 with Tool Calling and Thinking
![logo.svg](//github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true)

**[Paper Link](//github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf)👁️**

### [Deepseek API Notice](//api-docs.deepseek.com/guides/function_calling) ⚠️

### Models

8B Qwen DeepSeek R1

`ollama run aleshribar3/deepseek-r1-tool-calling:latest`

1.5B Qwen DeepSeek R1

`ollama run aleshribar3/deepseek-r1-tool-calling:1.5b`

7B Qwen DeepSeek R1

`ollama run aleshribar3/deepseek-r1-tool-calling:7b`

14B Qwen DeepSeek R1

`ollama run aleshribar3/deepseek-r1-tool-calling:14b`

32B Qwen DeepSeek R1

`ollama run aleshribar3/deepseek-r1-tool-calling:32b`

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)