iSanzy1/Legal-Model-sft

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 22, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

iSanzy1/Legal-Model-sft is a 3.1 billion parameter Qwen2.5-based instruction-tuned causal language model developed by iSanzy1. This model was finetuned using Unsloth and Huggingface's TRL library, enabling faster training. With a 32768 token context length, it is optimized for legal-specific applications and tasks.

Loading preview...

Model Overview

iSanzy1/Legal-Model-sft is an instruction-tuned language model based on the Qwen2.5 architecture, featuring 3.1 billion parameters and a substantial context length of 32768 tokens. Developed by iSanzy1, this model was specifically finetuned from unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit.

Key Characteristics

  • Architecture: Based on the Qwen2.5 model family.
  • Parameter Count: 3.1 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports a large context window of 32768 tokens, beneficial for processing extensive documents or complex queries.
  • Training Efficiency: Finetuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.

Primary Use Case

This model is specifically designed and finetuned for applications within the legal domain. Its instruction-tuned nature and large context window make it suitable for tasks requiring detailed understanding and generation of legal text, such as document analysis, legal research assistance, or generating legal summaries. Its efficient training methodology suggests it could be a practical choice for developers looking to deploy specialized legal AI solutions.