ibm/
granite3.2-vision:2b

37 1 month ago

vision tools 2b

1 month ago

f9140abda654 · 3.6GB ·

model
granite
·
2.53B
·
Q8_0
projector
clip
·
442M
·
F16
template
{{- /* Tools */ -}} {{- if .Tools -}} <|start_of_role|>available_tools<|end_of_role|> {{- range $ind
system
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful,
license
Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US
params
{ "num_ctx": 16384, "temperature": 0 }

Readme

Granite 3.2 Vision models

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.

Running

ollama run ibm/granite3.2-vision

Learn more