# Image-to-Text Conversion

A quantized version of Qwen2.5-VL-7B-Instruct, using llama.cpp for quantization, supporting multimodal tasks such as image-to-text conversion.

Gemma 3 12B IT is a large language model developed by Google, supporting multimodal input and long-context processing.

Optimized model based on Gemma 3 4B, using the same data mixing scheme as Glitter 12b

Gemma 3 27B is a large-scale pre-trained language model developed by Google, with 27 billion parameters, suitable for various natural language processing tasks.

Granite Vision 3.2 2B Abliterated is a vision-language model focused on image-to-text conversion tasks.

LLaVA is a large language and vision assistant model capable of handling multimodal tasks involving images and text.

A multilingual image-to-text model for identifying and parsing historical trademark documents, supporting German, Italian, and French.

GIT is a Transformer-based generative image-to-text model capable of converting visual content into descriptive text.