haikal1623/qwen2.5-7b-legal-id-sft

TEXT GENERATIONConcurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 6, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The haikal1623/qwen2.5-7b-legal-id-sft model is a 7.6 billion parameter Qwen2.5-based language model, fine-tuned from unsloth/Qwen2.5-7B-Instruct-bnb-4bit. Developed by haikal1623, this model was trained using Unsloth and Huggingface's TRL library for accelerated fine-tuning. It is specifically optimized for legal tasks within the Indonesian context, leveraging its base architecture for robust language understanding and generation.

Loading preview...

Model Overview

This model, haikal1623/qwen2.5-7b-legal-id-sft, is a specialized 7.6 billion parameter language model built upon the Qwen2.5 architecture. It was fine-tuned by haikal1623 from the unsloth/Qwen2.5-7B-Instruct-bnb-4bit base model, leveraging the Unsloth library and Huggingface's TRL for efficient and accelerated training.

Key Characteristics

  • Base Model: Qwen2.5-7B-Instruct, known for its strong general language capabilities.
  • Fine-tuning: Specifically fine-tuned for legal applications, likely within the Indonesian domain, as indicated by "legal-id-sft" in its name.
  • Training Efficiency: Utilizes Unsloth, which is designed to speed up the fine-tuning process, enabling faster iteration and deployment.
  • Context Length: Inherits a substantial context window of 32768 tokens, allowing it to process and understand lengthy legal documents.

Potential Use Cases

  • Legal Document Analysis: Summarizing, extracting key information, or answering questions from Indonesian legal texts.
  • Legal Research: Assisting in identifying relevant statutes, precedents, or legal opinions.
  • Legal Drafting Support: Generating or refining legal clauses and documents in Indonesian.
  • Specialized Chatbots: Developing conversational AI agents for legal inquiries in Indonesia.