Appyx/legal-qwen2.5-7b-grpo
TEXT GENERATIONConcurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 15, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
Appyx/legal-qwen2.5-7b-grpo is a 7.6 billion parameter Qwen2.5 model, fine-tuned by Appyx from Appyx/legal-qwen2.5-7b-sft. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for legal domain applications, leveraging its specialized fine-tuning.
Loading preview...
Model Overview
Appyx/legal-qwen2.5-7b-grpo is a 7.6 billion parameter language model developed by Appyx, fine-tuned specifically for legal applications. It is based on the Qwen2.5 architecture and was further fine-tuned from the Appyx/legal-qwen2.5-7b-sft model.
Key Training Details
- Base Model: Qwen2.5-7B
- Fine-tuning Source:
Appyx/legal-qwen2.5-7b-sft - Training Efficiency: This model was trained 2x faster using Unsloth and Huggingface's TRL library, indicating an optimized training process.
Potential Use Cases
- Legal Text Analysis: Ideal for tasks involving legal documents, contracts, and case law.
- Legal Information Retrieval: Can assist in extracting relevant information from large legal corpuses.
- Legal Question Answering: Suitable for answering questions within the legal domain, leveraging its specialized fine-tuning.