Bibiiiiiii/Legal-Model-sft

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 23, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Bibiiiiiii/Legal-Model-sft is a 3.1 billion parameter Qwen2.5-based instruction-tuned language model developed by Bibiiiiiii, featuring a 32768 token context length. This model is specifically fine-tuned for legal applications, leveraging efficient training with Unsloth and Huggingface's TRL library. It is designed to excel in tasks requiring understanding and generation of legal text.

Loading preview...

Model Overview

Bibiiiiiii/Legal-Model-sft is a 3.1 billion parameter language model, fine-tuned from unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit. Developed by Bibiiiiiii, this model is specialized for legal domain applications, offering a substantial 32768 token context window.

Key Capabilities

  • Legal Domain Specialization: Fine-tuned to understand and process legal texts, making it suitable for tasks within the legal field.
  • Efficient Training: Utilizes Unsloth and Huggingface's TRL library, resulting in 2x faster training compared to standard methods.
  • Qwen2.5 Architecture: Built upon the Qwen2.5 base, inheriting its robust language understanding and generation capabilities.

Use Cases

This model is particularly well-suited for applications requiring a deep understanding of legal language. Potential use cases include legal document analysis, legal research assistance, generating legal summaries, or answering legal-specific queries. Its efficient training methodology allows for specialized performance without requiring exceptionally large model sizes.

Finetunes
1 models