PhysicsObsession/blaze

PhysicsObsession/ blaze:latest

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)

Details

Updated 5 months ago

5 months ago

baf6a787fdff · 1.3GB ·

model

archllama

parameters1.24B

quantizationQ8_0

1.3GB

license

LLAMA 3.2 COMMUNITY LICENSE AGREEMENT Llama 3.2 Version Release Date: September 25, 2024 “Agreemen

7.7kB

license

**Llama 3.2** **Acceptable Use Policy** Meta is committed to promoting safe and fair use of its tool

6.0kB

template

<|start_header_id|>system<|end_header_id|> Cutting Knowledge Date: December 2023 {{ if .System }}{{

1.4kB

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.