ibm-granite/granite-docling-258M · Discussions

Resources

View closed (21)

Let transformers use cache for LLM by default

#45 opened about 1 month ago by

no simple compatible

#44 opened 2 months ago by

IBM Granite Docling

#43 opened 5 months ago by

output endless <ecel>

#42 opened 5 months ago by

Which model are you using for the demo?

#41 opened 5 months ago by

MarCognity-AI for IBM – Granite DocLing

#40 opened 5 months ago by

Hallucinations

#39 opened 5 months ago by

Docling OCR output

#38 opened 5 months ago by

InformaticsSolutions

Why is granite-docling-258M so slow?

#37 opened 5 months ago by

How are these bounding boxes being generated on top of the demo images

#36 opened 5 months ago by

having trouble with efficiency/speed

#35 opened 5 months ago by

MarCognity-AI for ibm-granite/granite-docling-258M

#34 opened 5 months ago by

Doesn't work for simple PDFs

#33 opened 5 months ago by

ONNX Conversion Available - Performance Benchmarks & Implementation Guide

#32 opened 5 months ago by

chore: add/update description via script

#29 opened 5 months ago by

Request: DOI

#28 opened 5 months ago by

Granite-Docling-258M Variants, Docker and Inference Snippets Starting Point

#27 opened 5 months ago by

Repetition for page headings

#24 opened 6 months ago by

Request for ONNX version

#21 opened 6 months ago by

granite-docling-258M docker image?

#19 opened 6 months ago by

can you provide onnx model weights?

#17 opened 6 months ago by

llama.cpp

#16 opened 6 months ago by

Local Installation Video and Testing - Step by Step

#15 opened 6 months ago by

Single page image inference using plain tranformers not working

#10 opened 6 months ago by