afihsan/qwen2.5-1.5b-legal-chatbot-finetuned

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 18, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

afihsan/qwen2.5-1.5b-legal-chatbot-finetuned is a 1.5 billion parameter Qwen2.5 model developed by afihsan, fine-tuned specifically for legal chatbot applications. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster fine-tuning. Its primary use case is to serve as a specialized legal chatbot, leveraging its optimized training for efficient performance in legal domain conversations.

Loading preview...

afihsan/qwen2.5-1.5b-legal-chatbot-finetuned Overview

This model is a specialized Qwen2.5 variant, developed by afihsan, with 1.5 billion parameters and a context length of 32768 tokens. It has been specifically fine-tuned for legal chatbot applications, making it highly suitable for conversational AI in the legal domain. The model was fine-tuned from unsloth/qwen2.5-1.5b-unsloth-bnb-4bit.

Key Capabilities

  • Specialized Legal Chatbot: Designed and optimized for understanding and generating responses relevant to legal queries and discussions.
  • Efficient Training: Leverages Unsloth and Huggingface's TRL library, resulting in a 2x speedup during the fine-tuning process.
  • Qwen2.5 Architecture: Benefits from the robust base architecture of Qwen2.5, providing a strong foundation for language understanding and generation.

Good for

  • Developing legal AI assistants or chatbots.
  • Applications requiring domain-specific knowledge in legal contexts.
  • Scenarios where efficient fine-tuning and deployment of a specialized language model are crucial.

Finetunes
1 models