hasyimas91/llama-3.1-8b-legal-grpo

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jun 24, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The hasyimas91/llama-3.1-8b-legal-grpo is an 8 billion parameter Llama 3.1 model, finetuned by hasyimas91 from hasyimas91/llama-3.1-8b-legal-sft. This model was trained 2x faster using Unsloth and Huggingface's TRL library, indicating an optimization for efficient fine-tuning. Its specific finetuning from a 'legal-sft' base suggests a specialization in legal domain applications.

Loading preview...

Model Overview

The hasyimas91/llama-3.1-8b-legal-grpo is an 8 billion parameter Llama 3.1 model, developed by hasyimas91. It is a finetuned version of the hasyimas91/llama-3.1-8b-legal-sft model, indicating a specialized focus on legal applications.

Key Characteristics

  • Base Model: Llama 3.1 architecture.
  • Parameter Count: 8 billion parameters.
  • Finetuning: Derived from a legal-specific instruction-tuned model (llama-3.1-8b-legal-sft).
  • Training Efficiency: The model was trained 2x faster utilizing Unsloth and Huggingface's TRL library, highlighting an optimized training process.

Potential Use Cases

Given its finetuning from a legal-specific base, this model is likely well-suited for tasks within the legal domain, such as:

  • Legal document analysis.
  • Legal research assistance.
  • Summarization of legal texts.
  • Question answering on legal topics.

Finetunes
1 models