theoitssurabaya/Legal-Assistant-SFT-Adapters

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 19, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The theoitssurabaya/Legal-Assistant-SFT-Adapters model is a 3.1 billion parameter Qwen2.5-instruct model, fine-tuned by theoitssurabaya. It was trained using Unsloth and Huggingface's TRL library, enabling faster training. This model is specifically adapted for legal assistant tasks, leveraging its 32768 token context length for processing extensive legal documents and queries.

Loading preview...

Model Overview

The theoitssurabaya/Legal-Assistant-SFT-Adapters is a 3.1 billion parameter language model, fine-tuned from the unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit base model. Developed by theoitssurabaya, this model is designed to function as a legal assistant, leveraging its substantial 32768 token context window to handle complex and lengthy legal texts.

Key Capabilities

  • Legal Domain Specialization: Fine-tuned for tasks within the legal domain, suggesting proficiency in understanding and generating legal-specific content.
  • Efficient Training: Utilizes Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
  • Extended Context Window: Features a 32768 token context length, crucial for processing comprehensive legal documents, case files, and regulations.

Good For

  • Legal Research: Assisting with information retrieval and summarization from large legal datasets.
  • Document Analysis: Understanding and extracting key information from contracts, statutes, and legal briefs.
  • Legal Question Answering: Providing informed responses to legal queries based on its specialized training.

This model is released under the Apache-2.0 license, making it suitable for a wide range of applications in the legal tech sector.

Finetunes
1 models