kianaaa19/legal-chatbot-qwen3b-sft-merged

TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 4, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The kianaaa19/legal-chatbot-qwen3b-sft-merged is a 3.1 billion parameter Qwen2.5-3B-Instruct model, fine-tuned by kianaaa19. This model is specifically optimized for legal chatbot applications, leveraging efficient training with Unsloth and Huggingface's TRL library. It is designed to provide specialized responses within a legal context, offering a context length of 32768 tokens.

Loading preview...

Overview

This model, developed by kianaaa19, is a fine-tuned version of the Qwen2.5-3B-Instruct base model, specifically adapted for legal chatbot functionalities. It boasts 3.1 billion parameters and was efficiently trained using Unsloth, which enabled a 2x faster finetuning process, alongside Huggingface's TRL library. The model operates under an Apache-2.0 license.

Key Capabilities

  • Specialized Legal Responses: Fine-tuned to understand and generate content relevant to legal queries and discussions.
  • Efficient Training: Benefits from Unsloth's optimization for faster training, making it a resource-efficient option for specialized tasks.
  • Qwen2.5 Architecture: Built upon the robust Qwen2.5-3B-Instruct foundation, providing a strong base for language understanding and generation.

Good For

  • Legal Chatbot Development: Ideal for applications requiring an AI assistant capable of handling legal-specific questions.
  • Specialized Information Retrieval: Can be used to extract or summarize information from legal texts.
  • Rapid Prototyping: The efficient training methodology makes it suitable for quick deployment and iteration in legal tech projects.

Finetunes
1 models