bagusasp/Llama-3.2-3B-Indo-Finetuned

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 30, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The bagusasp/Llama-3.2-3B-Indo-Finetuned is a 3.2 billion parameter Llama-based causal language model developed by bagusasp. This model was finetuned using Unsloth and Huggingface's TRL library, enabling faster training. It is designed for general language tasks, leveraging its Llama 3.2 architecture and 32768 token context length.

Loading preview...

Overview

The bagusasp/Llama-3.2-3B-Indo-Finetuned is a 3.2 billion parameter language model based on the Llama 3.2 architecture. Developed by bagusasp, this model was finetuned from unsloth/llama-3.2-3b-unsloth-bnb-4bit using the Unsloth library and Huggingface's TRL library. A key characteristic of its development is the claim of 2x faster training facilitated by Unsloth.

Key Characteristics

  • Architecture: Llama 3.2-based
  • Parameter Count: 3.2 billion parameters
  • Context Length: 32768 tokens
  • Training Method: Finetuned with Unsloth and Huggingface TRL for accelerated training.
  • License: Apache-2.0

Use Cases

This model is suitable for various natural language processing tasks, particularly those where a compact yet capable Llama-based model with a substantial context window is beneficial. Its finetuning process suggests potential optimizations for efficiency in deployment or further adaptation.