sam860/jamba-reasoning

sam860/ jamba-reasoning

244 Downloads Updated 3 months ago

A small and efficient reasoning model, with a hybrid transformer and mamba architecture

tools 3b

ollama run sam860/jamba-reasoning:3b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "sam860/jamba-reasoning:3b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='sam860/jamba-reasoning:3b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'sam860/jamba-reasoning:3b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)