maoelana/legal-qwen-2.5-1.5b-experiment-2
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 7, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The maoelana/legal-qwen-2.5-1.5b-experiment-2 is a 1.5 billion parameter Qwen2.5 model developed by maoelana, fine-tuned from unsloth/qwen2.5-1.5b-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling faster training. Its specific fine-tuning for legal applications suggests an optimization for legal text processing and understanding.
Loading preview...
Overview
This model, developed by maoelana, is a 1.5 billion parameter variant of the Qwen2.5 architecture. It was fine-tuned from the unsloth/qwen2.5-1.5b-unsloth-bnb-4bit base model, indicating an efficient training process utilizing Unsloth for accelerated performance and Huggingface's TRL library.
Key Capabilities
- Legal Domain Specialization: The model's name, "legal-qwen-2.5-1.5b-experiment-2", strongly suggests it has been fine-tuned for tasks within the legal domain, likely involving legal text analysis, question answering, or document summarization.
- Efficient Training: Leveraging Unsloth, this model benefits from a training process that is reportedly 2x faster, which can lead to more iterative development and optimization.
Good For
- Legal Text Processing: Ideal for applications requiring understanding and generation of legal language.
- Experimentation with Efficiently Trained Models: Developers interested in exploring models fine-tuned with Unsloth for performance benefits.