ainur07/legal-chatbot-qwen2.5-1.5b-sft

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 12, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The ainur07/legal-chatbot-qwen2.5-1.5b-sft is a 1.5 billion parameter Qwen2.5 model, developed by ainur07 and fine-tuned from unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit. This model is specifically optimized for legal chatbot applications, leveraging efficient training with Unsloth and Huggingface's TRL library. It offers a 32768 token context length, making it suitable for processing extensive legal documents and queries.

Loading preview...

Model Overview

This model, ainur07/legal-chatbot-qwen2.5-1.5b-sft, is a 1.5 billion parameter Qwen2.5-based language model developed by ainur07. It has been fine-tuned from the unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit base model, specifically targeting applications within the legal domain. The training process utilized Unsloth and Huggingface's TRL library, enabling faster fine-tuning.

Key Capabilities

  • Legal Domain Specialization: Fine-tuned for tasks and queries related to legal information and contexts.
  • Efficient Training: Benefits from Unsloth's optimizations, allowing for 2x faster training.
  • Qwen2.5 Architecture: Leverages the robust Qwen2.5 base model for strong language understanding and generation.
  • Context Length: Supports a substantial context window of 32768 tokens, suitable for detailed legal document analysis.

Use Cases

This model is particularly well-suited for:

  • Developing legal chatbots that can answer questions about laws, regulations, or legal procedures.
  • Assisting with legal research by summarizing documents or extracting key information.
  • Generating legal-themed text or drafting preliminary legal communications.

Licensing

The model is released under the Apache-2.0 license.