sayghost123/qwen25vl-7b-invoice-extractor
The sayghost123/qwen25vl-7b-invoice-extractor is a 7 billion parameter Qwen2.5-VL model, finetuned by sayghost123 from unsloth/qwen2.5-vl-7b-instruct-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. Its primary purpose is invoice extraction, leveraging its Qwen2.5-VL architecture for visual language understanding.
Loading preview...
Model Overview
The sayghost123/qwen25vl-7b-invoice-extractor is a 7 billion parameter visual language model, specifically finetuned for invoice extraction tasks. Developed by sayghost123, this model is based on the Qwen2.5-VL architecture and was finetuned from unsloth/qwen2.5-vl-7b-instruct-unsloth-bnb-4bit.
Key Characteristics
- Base Model: Qwen2.5-VL, indicating strong visual language understanding capabilities.
- Parameter Count: 7 billion parameters, offering a balance between performance and computational efficiency.
- Training Efficiency: Finetuned using Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.
- License: Released under the Apache-2.0 license.
Primary Use Case
This model is specifically designed and optimized for invoice extraction. Its visual language capabilities make it suitable for processing and extracting structured information from invoice documents, likely handling both text and layout understanding.