ameliacndr10/legal-chatbot-llama3-grpo

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 11, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The ameliacndr10/legal-chatbot-llama3-grpo is a 1.5 billion parameter Qwen2 model, developed by ameliacndr10, specifically fine-tuned for legal chatbot applications. It was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. This model is optimized for generating responses relevant to legal queries, building upon the ameliacndr10/legal-chatbot-llama3-finetuned base.

Loading preview...

Model Overview

The ameliacndr10/legal-chatbot-llama3-grpo is a 1.5 billion parameter Qwen2 model, developed by ameliacndr10, that has been fine-tuned for legal chatbot applications. This model builds upon the ameliacndr10/legal-chatbot-llama3-finetuned base.

Key Characteristics

  • Architecture: Qwen2
  • Parameters: 1.5 billion
  • Context Length: 32768 tokens
  • Fine-tuning: Utilizes Unsloth and Huggingface's TRL library for accelerated training, reportedly achieving 2x faster fine-tuning.
  • License: Apache-2.0

Primary Use Case

This model is specifically designed and optimized for use in legal chatbot systems. Its fine-tuning process suggests a focus on understanding and generating responses pertinent to legal contexts, making it suitable for applications requiring specialized legal language processing.

Finetunes
1 models