hasbiiii/Qwen2.5-1.5B-Indo-Legal

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 16, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The hasbiiii/Qwen2.5-1.5B-Indo-Legal model is a 1.5 billion parameter Qwen2.5-based causal language model developed by hasbiiii. Finetuned from unsloth/qwen2.5-1.5b-unsloth-bnb-4bit, it was trained using Unsloth and Huggingface's TRL library for accelerated finetuning. This model is specifically optimized for applications requiring a compact yet capable LLM, particularly for tasks related to Indonesian legal contexts.

Loading preview...

Model Overview

The hasbiiii/Qwen2.5-1.5B-Indo-Legal is a 1.5 billion parameter language model, developed by hasbiiii. It is finetuned from the unsloth/qwen2.5-1.5b-unsloth-bnb-4bit base model, leveraging the Qwen2.5 architecture. This model was trained with a focus on efficiency, utilizing Unsloth and Huggingface's TRL library, which enabled a 2x faster finetuning process.

Key Characteristics

  • Architecture: Based on the Qwen2.5 model family.
  • Parameter Count: 1.5 billion parameters, offering a balance between performance and computational efficiency.
  • Training Efficiency: Finetuned using Unsloth, resulting in significantly faster training times.
  • Context Length: Supports a context length of 32768 tokens.

Intended Use Cases

This model is particularly suitable for:

  • Applications requiring a lightweight yet capable language model.
  • Scenarios where rapid finetuning and deployment are critical.
  • Tasks that benefit from the Qwen2.5 architecture's general language understanding capabilities.

While the model name suggests an "Indo-Legal" specialization, the provided README does not detail specific training data or benchmarks related to this domain. Users should evaluate its performance for specific legal tasks within the Indonesian context.