theprint/CodeLlama3.2-3B-1225

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:3.2BQuant:BF16Ctx Length:32kPublished:Dec 29, 2025License:llama3.2Architecture:Transformer Warm

CodeLlama3.2-3B-1225 is a 3.2 billion parameter Llama model developed by theprint, fine-tuned from unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit. This model was trained with Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for instruction-following tasks, leveraging its Llama architecture for efficient performance.

Loading preview...

Model Overview

CodeLlama3.2-3B-1225 is a 3.2 billion parameter Llama model developed by theprint. It is fine-tuned from the unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit base model, indicating its specialization in instruction-following tasks.

Key Characteristics

  • Architecture: Llama 3.2 series.
  • Parameter Count: 3.2 billion parameters.
  • Training Efficiency: This model was trained 2x faster using Unsloth and Huggingface's TRL library, highlighting an optimized training process.
  • License: Distributed under the Llama3.2 Community License Agreement.

Use Cases

This model is suitable for applications requiring a compact yet capable instruction-tuned language model, particularly where training efficiency and Llama 3.2 compatibility are important considerations. Its optimized training suggests potential for rapid deployment and iteration in development workflows.