RedRenisa/PGABL-Renisa-Assyifa-Putri-legal-chatbot-grpo

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 9, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The RedRenisa/PGABL-Renisa-Assyifa-Putri-legal-chatbot-grpo is a 3.1 billion parameter Qwen2 model developed by RedRenisa. This model is a fine-tuned version of RedRenisa/PGABL-Renisa-Assyifa-Putri-legal-chatbot, specifically optimized for legal chatbot applications. It was trained using Unsloth and Huggingface's TRL library, enabling faster training. Its primary strength lies in its specialized fine-tuning for legal domain interactions.

Loading preview...

Model Overview

The RedRenisa/PGABL-Renisa-Assyifa-Putri-legal-chatbot-grpo is a 3.1 billion parameter Qwen2 model developed by RedRenisa. It is a fine-tuned variant of the RedRenisa/PGABL-Renisa-Assyifa-Putri-legal-chatbot, designed for specific applications within the legal domain. The model was trained with a focus on efficiency, utilizing Unsloth for accelerated training and Huggingface's TRL library.

Key Characteristics

  • Architecture: Qwen2 model family.
  • Parameter Count: 3.1 billion parameters.
  • Context Length: 32768 tokens.
  • Training Methodology: Fine-tuned using Unsloth and Huggingface's TRL library for optimized training speed.

Intended Use Cases

This model is specifically tailored for legal chatbot functionalities, leveraging its fine-tuning to handle queries and interactions related to legal topics. Developers looking for a specialized model for legal assistance or information retrieval within a chatbot framework may find this model suitable.

Finetunes
1 models