oofwite
/

OMG-VLM

Image-Text-to-Text

multimodal-graphs

vision-language-model

node-classification

link-prediction

Model card Files Files and versions

oofwite commited on 8 days ago

Commit

4023d01

·

verified ·

1 Parent(s): 0056427

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -71,7 +71,7 @@ These values must match at inference time:
 | Visual adapter layers / queries / heads | 1 / 32 / 32 |
 | Visual compressor | on |
 | Textual aggregation heads / pool layers / MLP ratio | 16 / 1 / 4.0 |
-| **Textual aggregation context tokens** | **8** (the code's default is 16) |
 | Max neighbors | 10 |
 ## Usage

 | Visual adapter layers / queries / heads | 1 / 32 / 32 |
 | Visual compressor | on |
 | Textual aggregation heads / pool layers / MLP ratio | 16 / 1 / 4.0 |
+| Textual aggregation context tokens | 8 |
 | Max neighbors | 10 |
 ## Usage