MuhHendri12/qwen2.5-3b-legal-id-sft

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 8, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

MuhHendri12/qwen2.5-3b-legal-id-sft is a 3.1 billion parameter language model developed by MuhHendri12, fine-tuned from unsloth/Qwen2.5-3B-Instruct-bnb-4bit. This model was specifically trained using Unsloth and Huggingface's TRL library, enabling faster training times. Its primary use case is likely within legal domains for Indonesian language tasks, given its name and fine-tuning origin, offering specialized performance for legal text processing.

Loading preview...

Overview

MuhHendri12/qwen2.5-3b-legal-id-sft is a 3.1 billion parameter language model developed by MuhHendri12. It is a specialized fine-tuned version of the unsloth/Qwen2.5-3B-Instruct-bnb-4bit base model. This model leverages the Unsloth library in conjunction with Huggingface's TRL library, which facilitated a 2x faster training process.

Key Capabilities

  • Specialized Domain Focus: The model's name, "legal-id-sft," strongly suggests it is fine-tuned for tasks within the legal domain, specifically for the Indonesian language.
  • Efficient Training: Benefits from Unsloth's optimizations, allowing for quicker fine-tuning iterations.
  • Qwen2.5 Architecture: Inherits the foundational capabilities of the Qwen2.5-3B-Instruct model, providing a robust base for instruction-following and general language understanding.

Good for

  • Applications requiring language understanding and generation in the Indonesian legal context.
  • Developers looking for a compact (3.1B parameters) model with specialized domain knowledge.
  • Projects where efficient fine-tuning and deployment of a domain-specific model are critical.

Finetunes
1 models