Qwen2.5 14b with a simplified template for chat and manual tool handling

ollama run ExposedCat/qwen2.5-manual-chat

curl http://localhost:11434/api/chat \
  -d '{
    "model": "ExposedCat/qwen2.5-manual-chat",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='ExposedCat/qwen2.5-manual-chat',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'ExposedCat/qwen2.5-manual-chat',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

91ff4c1da19f · 9.0GB ·

model

archqwen2

parameters14.8B

quantizationQ4_K_M

9.0GB

system

You are Qwen, created by Alibaba Cloud. You are a helpful assistant.

68B

license

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US

11kB

template

{{- range $i, $msg := .Messages }} {{- $last := eq (len (slice $.Messages $i)) 1 }} {{- if eq $msg.R

455B

Readme

Qwen2.5 14B Manual Chat

This is a raw qwen2.5:14b model with simplified template for manual tools processing.

Original template with tools doesn’t work well with custom message tags, such as or . Using this model you can define any input format and it won’t interfere with pre-defined tool and message formats.

Note: this model doesn’t support generate, only use it via chat with messages

See Telegram Ollama Local on GitHub for more details