jayuspurnomo/legal-chatbot-qwen2.5-1.5b-sft
The jayuspurnomo/legal-chatbot-qwen2.5-1.5b-sft is a 1.5 billion parameter Qwen2.5 model, fine-tuned by jayuspurnomo, specifically designed for legal chatbot applications. This model leverages Unsloth and Huggingface's TRL library for efficient training, offering a specialized solution for legal domain interactions. With a 32768 token context length, it is optimized for processing and generating legal-specific text.
Loading preview...
Model Overview
The jayuspurnomo/legal-chatbot-qwen2.5-1.5b-sft is a specialized 1.5 billion parameter language model, fine-tuned from the unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit base model. Developed by jayuspurnomo, this model is specifically engineered for applications within the legal domain.
Key Capabilities
- Legal Chatbot Specialization: The model has undergone supervised fine-tuning (SFT) to enhance its performance and relevance for legal chatbot use cases, making it suitable for understanding and generating legal-centric responses.
- Efficient Training: It was fine-tuned using Unsloth and Huggingface's TRL library, which enabled faster training times.
- Qwen2.5 Architecture: Built upon the Qwen2.5 architecture, it benefits from the foundational capabilities of this model family.
- Context Length: Features a substantial context window of 32768 tokens, allowing it to process and maintain coherence over longer legal texts and conversations.
Good For
- Legal Information Retrieval: Assisting users in navigating legal documents or understanding legal concepts.
- Automated Legal Support: Developing chatbots that can answer common legal questions or provide preliminary legal guidance.
- Legal Text Generation: Generating summaries or drafts of legal content, given its specialized training.
This model is released under the Apache-2.0 license.