granite3.2-vision

granite3.2-vision

A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.

vision tools 2b

25.7K Pulls Updated 2 weeks ago

Updated 2 weeks ago

2 weeks ago

3be41a661804 · 2.4GB

parameters2.53B

quantizationQ4_K_M

quantizationF16

{ "num_ctx": 16384, "temperature": 0 }

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful,

{{- /* Tools */ -}} {{- if .Tools -}} <|start_of_role|>available_tools<|end_of_role|> {{- range $in

Apache License Version 2.0, January 2004

Readme

Note: this model requires Ollama 0.5.13.

A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more. The model was trained on a meticulously curated instruction-following dataset, comprising diverse public datasets and synthetic datasets tailored to support a wide range of document understanding and general image tasks. It was trained by fine-tuning a Granite large language model with both image and text modalities.

References