Timooody/qwen2-5-1-5b-legal-grpo-v4

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

Timooody/qwen2-5-1-5b-legal-grpo-v4 is a 1.5 billion parameter Qwen2-based language model developed by Timooody. This model is a fine-tuned version of Timooody/qwen2-5-1-5b-legal-finetuned, specifically optimized for legal applications. It was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training speeds, and supports a context length of 32768 tokens.

Loading preview...

Model Overview

Timooody/qwen2-5-1-5b-legal-grpo-v4 is a 1.5 billion parameter language model developed by Timooody. It is built upon the Qwen2 architecture and is a further fine-tuned iteration of the Timooody/qwen2-5-1-5b-legal-finetuned model, indicating a specialization in legal domain tasks. The model supports a substantial context length of 32768 tokens.

Key Training Details

  • Base Model: Fine-tuned from Timooody/qwen2-5-1-5b-legal-finetuned.
  • Training Efficiency: The model's training process was significantly accelerated, achieving 2x faster speeds, by utilizing Unsloth in conjunction with Huggingface's TRL library.

Intended Use

Given its fine-tuning history, this model is likely optimized for tasks within the legal domain, such as legal text analysis, document summarization, or question answering related to legal documents. Its efficient training methodology suggests a focus on practical deployment and performance.

Finetunes
1 models