prithivMLmods
/

DeepCaption-VLA-7B

Image-Text-to-Text

VisionLanguageAttribution

VisualUnderstanding

text-generation-inference

AttributeCaptioning

Model card Files Files and versions

prithivMLmods commited on Aug 29, 2025

Commit

2362df8

·

verified ·

1 Parent(s): 0fdf7a5

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -23,7 +23,7 @@ datasets:
   Multimodal-Fatima/Caltech101_not_background_test_facebook_opt_2.7b_Attributes_Caption_ns_5647
 ---
-![1.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/JOAwQE1BupYieDzjClZfN.png)
 # **DeepCaption-VLA-7B**
@@ -142,4 +142,4 @@ print(output_text)
 * May over-attribute or infer properties not explicitly visible in ambiguous images.
 * Outputs can vary in tone depending on prompt phrasing.
 * Not intended for filtered captioning tasks (explicit or sensitive content may appear).
-* Accuracy may degrade on synthetic or highly abstract visual domains.

   Multimodal-Fatima/Caltech101_not_background_test_facebook_opt_2.7b_Attributes_Caption_ns_5647
 ---
+![2.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/ykzipvpIsIt-5nLxhP5CM.png)
 # **DeepCaption-VLA-7B**
 * May over-attribute or infer properties not explicitly visible in ambiguous images.
 * Outputs can vary in tone depending on prompt phrasing.
 * Not intended for filtered captioning tasks (explicit or sensitive content may appear).
+* Accuracy may degrade on synthetic or highly abstract visual domains.