jayuspurnomo/legal-chatbot-qwen2.5-1.5b-grpo
The jayuspurnomo/legal-chatbot-qwen2.5-1.5b-grpo is a 1.5 billion parameter Qwen2 model developed by jayuspurnomo, fine-tuned from jayuspurnomo/legal-chatbot-qwen2.5-1.5b-sft. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed as a legal chatbot, leveraging its 32768 token context length for processing extensive legal texts.
Loading preview...
Model Overview
The jayuspurnomo/legal-chatbot-qwen2.5-1.5b-grpo is a 1.5 billion parameter Qwen2 model, developed by jayuspurnomo. It is a fine-tuned version of the jayuspurnomo/legal-chatbot-qwen2.5-1.5b-sft model, specifically optimized for legal chatbot applications.
Key Characteristics
- Architecture: Based on the Qwen2 model family.
- Parameter Count: 1.5 billion parameters, offering a balance between performance and computational efficiency.
- Context Length: Features a substantial 32768 token context window, enabling the processing and understanding of lengthy legal documents and complex queries.
- Training Efficiency: The model was trained with Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.
Intended Use Cases
This model is primarily designed for applications requiring a legal chatbot. Its capabilities make it suitable for:
- Legal Information Retrieval: Answering questions based on provided legal texts.
- Document Analysis: Processing and summarizing legal documents.
- Legal Assistance: Providing conversational support in legal contexts.