Specialized CodeLlama variant fine-tuned specifically for Python code generation. 13B params, Q6_K quant (very high quality, minimal loss).

ollama run fauxpaslife/codellama-python-13b-q6

curl http://localhost:11434/api/chat \
  -d '{
    "model": "fauxpaslife/codellama-python-13b-q6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='fauxpaslife/codellama-python-13b-q6',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'fauxpaslife/codellama-python-13b-q6',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 3 weeks ago

3 weeks ago

e491380c655b · 11GB ·

model

archllama

parameters13B

quantizationQ6_K

11GB

template

13B

Readme

See the author’s website for more details. Below, I have summarized their content.

CodeLlama 13B Python (Q6_K)

Original GGUF by TheBloke | Base model by Meta

What it does

Specialized CodeLlama variant fine-tuned specifically for Python code generation. 13B params, Q6_K quant (very high quality, minimal loss).

Usage

ollama run fauxpaslife/codellama-python-13b-q6

Prompt format:

[INST] Write code to solve the following coding problem that obeys the constraints and passes the example test cases. Please wrap your code answer using ```:
{your_request}
[/INST]

Quick example

ollama run fauxpaslife/codellama-python-13b-q6 "[INST] Write a Python function to calculate fibonacci numbers recursively [/INST]"

Stats

Quantization: Q6_K (extremely low quality loss)
Size: ~10.68 GB
Context: 16K tokens
Best for: Python-specific code tasks, scripts, algorithms