Simple demo of function-calling model.

ollama run konsumer/weather

curl http://localhost:11434/api/chat \
  -d '{
    "model": "konsumer/weather",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='konsumer/weather',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'konsumer/weather',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 years ago

2 years ago

85cb85c2c5db · 4.1GB ·

model

archllama

parameters7.24B

quantizationQ4_0

4.1GB

system

You are a helpful assistant that can answer questions about the weather. You have access to the foll

1.1kB

params

{ "stop": [ "<|im_start|>", "<|im_end|>" ] }

59B

template

<|im_start|>system {{ .System }}<|im_end|> <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assi

106B

Readme

weather

This is a simple demo-model that uses calebfahlgren/natural-functions to call functions. This is mostly an experiment to see how feasible function-calling is, using code outside of python (training + prompt + post-parsing.)

You can see an example repo that uses it at konsumer/ai-weather.