repkam09/hennos-qwen3

repkam09/ hennos-qwen3

6 Downloads Updated 7 months ago

Qwen-based model for Hennos when running in local inference mode

tools thinking

ollama run repkam09/hennos-qwen3

curl http://localhost:11434/api/chat \
  -d '{
    "model": "repkam09/hennos-qwen3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='repkam09/hennos-qwen3',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'repkam09/hennos-qwen3',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)