adittamavincent/pgabl-legal-rag-assistant

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 6, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The adittamavincent/pgabl-legal-rag-assistant is a 1.5 billion parameter Qwen2.5-based language model, fine-tuned by adittamavincent. Optimized for legal RAG (Retrieval Augmented Generation) tasks, this model leverages a 32768-token context length to process extensive legal documents. It was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning for specialized applications.

Loading preview...

adittamavincent/pgabl-legal-rag-assistant Overview

This model, developed by adittamavincent, is a fine-tuned version of the Qwen2.5-1.5B architecture, specifically adapted for legal Retrieval Augmented Generation (RAG) tasks. It features 1.5 billion parameters and supports a substantial context length of 32768 tokens, making it suitable for processing and understanding lengthy legal texts.

Key Capabilities

  • Legal RAG Optimization: Designed to excel in legal information retrieval and generation, likely improving accuracy and relevance in legal queries.
  • Extended Context Window: A 32768-token context length allows for comprehensive analysis of large legal documents or multiple related texts.
  • Efficient Fine-tuning: The model was fine-tuned using Unsloth and Huggingface's TRL library, indicating an efficient training process.

Good For

  • Legal Research: Assisting with querying and summarizing information from legal databases or documents.
  • Document Analysis: Processing and understanding complex legal contracts, case law, or regulations.
  • Specialized Legal AI Applications: Serving as a foundational component for AI tools in the legal domain requiring deep contextual understanding.

Finetunes
2 models