cmsmanhattan/ jirack-ultra-1b-reasoning:latest

Updated 9 hours ago

ollama run cmsmanhattan/jirack-ultra-1b-reasoning

curl http://localhost:11434/api/chat \
  -d '{
    "model": "cmsmanhattan/jirack-ultra-1b-reasoning",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='cmsmanhattan/jirack-ultra-1b-reasoning',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'cmsmanhattan/jirack-ultra-1b-reasoning',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 9 hours ago

9 hours ago

36dd3e4e6126 · 3.6GB ·

model

archqwen2

parameters1.78B

quantizationBF16

3.6GB

template

<｜User｜>{{ .Prompt }}<｜Assistant｜>

42B

system

You are JiRack, a helpful and honest AI assistant.

50B

params

{ "num_ctx": 8192, "repeat_penalty": 1.1, "stop": [ "<｜end▁of▁sentence｜>

142B

Readme

JiRack Ultra 1B FP16 Reasoning

Fast ~1.5B CPU model from CMS Manhattan. BitNet-style ternary path, extended tokenizer with Routing, Tool-call and Robotics tags. Built on a redesigned DeepSeek R1 / Qwen2 stack. This tag is full FP16.

HF: https://huggingface.co/CMSManhattan/JiRackUltra_1b

Run

ollama run cmsmanhattan/jirack-ultra-1b-reasoning

What it is

Super reasoning functions , tells model thoughts
Cloud-ready small expert for RAG and local inference
Tokenizer tags for routing, tool calls, robotics
Full FP16 base for further quants and QAT
Ternary architecture can go smaller with QAT if you need disk and RAM down
Java / Spring AI and Gorilla-style tool-call examples on the HF card

Hardware

FP16: about 3.5 GB on disk, 4–8 GB RAM recommended.

Contact

grabko@cmsmanhattan.com +1 (516) 777-0945 New York, USA

License

MIT on weights. Commercial terms for UI / enterprise on the HF page.