midris/Llama-3.2-3B-Legal-SFT
TEXT GENERATIONPricing:Input $0.2036 / Output $1.34Concurrent Unit Cost:1Model Size:3.2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 20, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The midris/Llama-3.2-3B-Legal-SFT is a 3.2 billion parameter Llama-3.2 model developed by midris, fine-tuned from unsloth/Llama-3.2-3B-Instruct-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for legal-specific applications, leveraging its instruction-tuned base for specialized tasks within the legal domain.
Loading preview...
Model Overview
The midris/Llama-3.2-3B-Legal-SFT is a 3.2 billion parameter language model, fine-tuned by midris specifically for legal applications. It is based on the Llama-3.2 architecture and was initialized from the unsloth/Llama-3.2-3B-Instruct-bnb-4bit model.
Key Characteristics
- Architecture: Llama-3.2-3B, a compact yet capable foundation for specialized tasks.
- Training Efficiency: Leverages Unsloth and Huggingface's TRL library, enabling 2x faster fine-tuning compared to standard methods.
- Specialization: Explicitly fine-tuned for legal-specific tasks, indicating its suitability for processing and generating legal-related text.
- License: Distributed under the Apache-2.0 license, allowing for broad use and modification.
Intended Use Cases
This model is particularly well-suited for:
- Legal Text Analysis: Tasks involving the understanding and interpretation of legal documents.
- Legal Information Retrieval: Assisting in extracting specific information from large legal corpuses.
- Legal Question Answering: Providing responses to queries within a legal context.
- Legal Content Generation: Generating drafts or summaries of legal texts, given appropriate prompts.