PhysicsObsession/blaze

PhysicsObsession/ blaze

34 Downloads Updated 5 months ago

Blaze is a lightweight yet remarkably capable AI model, fine-tuned from the robust foundation of LLaMA 3.2 (1B parameters). Designed with a focus on efficiency and performance. We believe in providing credit to the original creator.

tools

ollama run PhysicsObsession/blaze

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

from ollama import chat

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

import ollama from 'ollama'

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

Applications

Claude Code ollama launch claude --model PhysicsObsession/blaze

Codex ollama launch codex --model PhysicsObsession/blaze

OpenCode ollama launch opencode --model PhysicsObsession/blaze

OpenClaw ollama launch openclaw --model PhysicsObsession/blaze

Models

View all →

Name

1 model

Size

Context

Input

blaze:latest

1.3GB · 128K context window · Text · 5 months ago

blaze:latest

1.3GB

128K

Text

Readme

After Testing the base LLama3.2 1b, blaze 1b and Gemma 1b, we have concluded that in our tests blaze has received lower hallucination rates, outperforming the other competitive one billion parameter models.

Blaze was trained for not only efficiency and performance, but we also wanted accuracy. Blaze has also out performed the other one billion parameter models in fields like coding.