shade1301/pgabl-legal-rag-qwen25-1_5b-v1

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 5, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The shade1301/pgabl-legal-rag-qwen25-1_5b-v1 is a 1.5 billion parameter Qwen2.5 model, developed by shade1301, fine-tuned for legal RAG applications. Utilizing Unsloth and Huggingface's TRL library for accelerated training, this model is optimized for efficient retrieval-augmented generation in legal contexts. It features a 32768 token context length, making it suitable for processing extensive legal documents.

Loading preview...

Model Overview

The shade1301/pgabl-legal-rag-qwen25-1_5b-v1 is a 1.5 billion parameter language model based on the Qwen2.5 architecture, developed by shade1301. This model has been specifically fine-tuned for legal Retrieval-Augmented Generation (RAG) tasks, leveraging its substantial 32768 token context length to handle complex and lengthy legal documents.

Key Characteristics

  • Architecture: Qwen2.5-1.5B, providing a balance between performance and computational efficiency.
  • Training Optimization: Fine-tuned using Unsloth and Huggingface's TRL library, which enabled 2x faster training compared to standard methods.
  • Context Length: Supports a 32768 token context window, crucial for processing comprehensive legal texts and maintaining conversational coherence over extended interactions.
  • License: Distributed under the Apache-2.0 license, allowing for broad usage and modification.

Use Cases

This model is particularly well-suited for applications requiring:

  • Legal RAG Systems: Enhancing the accuracy and relevance of information retrieval and generation within legal domains.
  • Document Analysis: Processing and understanding large volumes of legal documents, contracts, and case law.
  • Legal Question Answering: Providing informed responses to legal queries by synthesizing information from provided contexts.