rizalarfiyan/qwen-legal-grpo-dicoding

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 31, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The rizalarfiyan/qwen-legal-grpo-dicoding is a 1.5 billion parameter Qwen2 model developed by rizalarfiyan, fine-tuned from rizalarfiyan/qwen-legal-SFT-dicoding. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It features a 32768 token context length and is optimized for legal domain applications.

Loading preview...

Model Overview

The rizalarfiyan/qwen-legal-grpo-dicoding is a 1.5 billion parameter Qwen2 language model developed by rizalarfiyan. It is a fine-tuned version of the rizalarfiyan/qwen-legal-SFT-dicoding model, specifically adapted for legal domain tasks.

Key Capabilities

  • Efficient Training: This model was trained with Unsloth and Huggingface's TRL library, resulting in a 2x speedup during the fine-tuning process.
  • Legal Domain Focus: As indicated by its lineage and naming, the model is specialized for applications within the legal sector.
  • Context Length: It supports a substantial context window of 32768 tokens, allowing for processing longer legal documents or complex queries.

Good For

  • Legal Text Analysis: Ideal for tasks requiring understanding and generation of legal language.
  • Research and Development: Developers and researchers working on legal AI solutions can leverage its specialized fine-tuning.
  • Efficient Deployment: The use of Unsloth for training suggests potential for more efficient inference, making it suitable for applications where speed is a factor.