Farhanabdul12/legal-qwen2.5-1.5b-finetuned
TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 3, 2026License:apache-2.0Architecture:Transformer Open Weights Cold
The Farhanabdul12/legal-qwen2.5-1.5b-finetuned model is a 1.5 billion parameter Qwen2.5-based language model, fine-tuned by Farhanabdul12. It was developed using Unsloth and Huggingface's TRL library for accelerated training. This model is specifically optimized for legal domain applications, leveraging its Qwen2.5 architecture and efficient fine-tuning process.
Loading preview...
Overview
This model, developed by Farhanabdul12, is a fine-tuned version of the Qwen2.5-1.5B-Instruct model. It leverages the Qwen2.5 architecture, featuring 1.5 billion parameters and a 32768-token context length. The fine-tuning process was significantly accelerated using Unsloth and Huggingface's TRL library, enabling faster iteration and development.
Key Capabilities
- Legal Domain Specialization: Fine-tuned for applications within the legal sector.
- Efficient Training: Utilizes Unsloth for 2x faster training compared to standard methods.
- Qwen2.5 Architecture: Benefits from the robust base capabilities of the Qwen2.5 model family.
Good For
- Developing applications requiring legal text understanding or generation.
- Researchers and developers looking for a compact, specialized legal LLM.
- Use cases where efficient deployment and inference of a legal-focused model are critical.