Llama3.2-FFM-11B-V-32K

Llama3.2-FFM-11B-V-32K is a vision language model optimized for Traditional Chinese based on Meta-Llama-3.2-11B-Vision. It improves the shortcomings in handling Traditional Chinese from native model, making it the only multimodal model currently enhanced for Meta-Llama-3.2 in Traditional Chinese.

Llama3.2-FFM-11B-V-32K demonstrates outstanding performance in recognizing and understanding Traditional Chinese characters in images, significantly improving OCR (Optical Character Recognition) for Chinese documents and providing more accurate answers to questions. For the characteristics and specifications of the Llama3.2-FFM, please refer to this document.

By using Llama3.2-FFM-11B-V-32K, you agree to comply with the Meta-Llama3.2 licensing terms.

Llama3.2-FFM-11B-V-32K can be deployed in AFS ModelSpace public mode. For instructions on AFS ModelSpace public mode, please refer to this document.