risdyantok/legal-assistant-qwen2.5-1.5b

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 6, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

The risdyantok/legal-assistant-qwen2.5-1.5b is a 1.5 billion parameter Qwen2.5 causal language model, developed by risdyantok and fine-tuned for legal assistance tasks. This model leverages the Qwen2.5 architecture and was trained using Unsloth and Huggingface's TRL library for accelerated fine-tuning. It is specifically optimized to provide support in legal contexts, offering a specialized application compared to general-purpose LLMs.

Loading preview...

Model Overview

The risdyantok/legal-assistant-qwen2.5-1.5b is a specialized 1.5 billion parameter language model based on the Qwen2.5 architecture. Developed by risdyantok, this model has been fine-tuned specifically for legal assistance applications.

Key Characteristics

  • Base Model: Fine-tuned from unsloth/Qwen2.5-1.5B-bnb-4bit.
  • Fine-tuning Method: Utilizes Unsloth and Huggingface's TRL library, enabling faster training times.
  • Parameter Count: 1.5 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports a context window of 32768 tokens.
  • License: Distributed under the Apache-2.0 license.

Intended Use Cases

This model is designed for tasks requiring legal domain knowledge and language processing. Its fine-tuning makes it suitable for applications such as:

  • Assisting with legal document analysis.
  • Generating legal-themed text.
  • Supporting legal research queries.

Differentiation

Unlike general-purpose Qwen2.5 models, this variant is specifically tailored for legal contexts, providing more relevant and accurate outputs for legal-specific prompts. The use of Unsloth for fine-tuning also highlights an optimization for training efficiency.