granite3.2-vision:2b

137.4K 4 months ago

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

4 months ago

3be41a661804 · 2.4GB

model
granite
·
2.53B
·
Q4_K_M
projector
clip
·
442M
·
F16
template
{{- /* Tools */ -}} {{- if .Tools -}} <|start_of_role|>available_tools<|end_of_role|> {{- range $in
system
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful,
license
Apache License Version 2.0, January 2004
params
{ "num_ctx": 16384, "temperature": 0 }

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

Hugging Face