m/qwen2514bmax

m/ qwen2514bmax

1,993 Downloads Updated 1 year ago

Qwen2.5 14b with a maxxed out context size

tools

ollama run m/qwen2514bmax

curl http://localhost:11434/api/chat \
  -d '{
    "model": "m/qwen2514bmax",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='m/qwen2514bmax',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'm/qwen2514bmax',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)