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

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 23, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The rasslonely/legal-chatbot-qwen2.5-1.5b-sft is a 1.5 billion parameter Qwen2.5-based instruction-tuned model developed by rasslonely, fine-tuned from unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit. This model is optimized for legal chatbot applications, leveraging a 32768-token context length for comprehensive legal text processing. It was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training. Its specialized fine-tuning makes it particularly suitable for legal domain-specific conversational AI.

Loading preview...

Model Overview

The rasslonely/legal-chatbot-qwen2.5-1.5b-sft is a specialized instruction-tuned language model developed by rasslonely. It is built upon the Qwen2.5 architecture, featuring 1.5 billion parameters and supporting a substantial context length of 32768 tokens. This model was fine-tuned from unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit.

Key Capabilities

  • Legal Domain Specialization: The model is specifically fine-tuned for legal chatbot applications, indicating a focus on understanding and generating legal-centric text.
  • Efficient Fine-tuning: It leverages Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
  • Extended Context Window: With a 32768-token context length, it can process and retain information from lengthy legal documents or conversations.

Good For

  • Developing conversational AI agents for legal assistance.
  • Applications requiring deep understanding and generation of legal language.
  • Use cases where efficient fine-tuning and a large context window are beneficial for legal text processing.

Finetunes
1 models