Adamaja111/legal-qwen2.5-1.5b-ft

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 22, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Adamaja111/legal-qwen2.5-1.5b-ft is a 1.5 billion parameter Qwen2.5 model developed by Adamaja111, fine-tuned from unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. With a 32768 token context length, it is optimized for specific applications, likely in the legal domain given its name, leveraging its efficient training for focused performance.

Loading preview...

Adamaja111/legal-qwen2.5-1.5b-ft: A Specialized Qwen2.5 Model

This model, developed by Adamaja111, is a fine-tuned variant of the Qwen2.5-1.5B-Instruct architecture, specifically adapted from the unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit base model. It features 1.5 billion parameters and supports a substantial context length of 32768 tokens, making it suitable for processing lengthy documents or complex queries.

Key Capabilities

  • Efficient Fine-tuning: The model was fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process compared to standard methods.
  • Qwen2.5 Architecture: Leverages the robust Qwen2.5 base, known for its strong general language understanding and generation capabilities.
  • Extended Context Window: The 32768 token context length allows for comprehensive analysis and generation based on extensive input.

Good for

  • Domain-Specific Applications: Given its name, this model is likely specialized for legal text processing, analysis, and generation, benefiting from its fine-tuning.
  • Resource-Efficient Deployment: Its 1.5 billion parameter size, combined with efficient training, makes it a candidate for applications where computational resources are a consideration, while still offering a large context window.
  • Research and Development: Ideal for researchers and developers looking to build upon a specialized Qwen2.5 model with efficient training origins.