MagiBoss
/

PaliGemma2-3b-224-COCO

Model card Files Files and versions

MagiBoss commited on Feb 7

Commit

b551c45

·

verified ·

1 Parent(s): f8f2051

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -73,7 +73,7 @@ A comprehensive evaluation was conducted against [MagiBoss/Blip2-Typhoon1.5-COCO
 |:------------------------------:|:------:|:------:|:------:|:------:|:----------------:|
 | THAI-BLIP-2                    | 40.62   | 17.72  | 8.36   | 4.04   | 10.44            |
 | Blip2-Typhoon1.5-COCO          | 41.47   | 18.09  | 8.22   | 3.75   | 7.48            |
-| **PaliGemma2-3b-224-COCO**     | **42.03**   | **19.11**  | **9.29**   | **4.80**   | **12.42**            |
 Key Achievement: ~3.3x improvement in BLEU-1 score, indicating significantly better basic translation accuracy.
@@ -82,7 +82,7 @@ Key Achievement: ~3.3x improvement in BLEU-1 score, indicating significantly bet
 |:------------------------------:|:-------:|
 | THAI-BLIP-2                    | 1.93    |
 | Blip2-Typhoon1.5-COCO          | 0.93    |
-| **PaliGemma2-3b-224-COCO**     | **2.82**    |
 Notable Improvement: 2.5x enhancement in ROUGE-1 score, showing better content matching.
@@ -91,7 +91,7 @@ Notable Improvement: 2.5x enhancement in ROUGE-1 score, showing better content m
 |:--------------------------------:|:--------------:|
 | THAI-BLIP-2                      | 78.18          |
 | Blip2-Typhoon1.5-COCO            | 77.00          |
-| **PaliGemma2-3b-224-COCO**       | **79.33**          |
 Significant Gain: 9.25 point improvement in BERTScore, validated using bert-base-multilingual-cased model.
@@ -100,7 +100,7 @@ Significant Gain: 9.25 point improvement in BERTScore, validated using bert-base
 |:------------------------------:|:-------:|
 | THAI-BLIP-2                    | 27.18   |
 | Blip2-Typhoon1.5-COCO          | 21.90   |
-| **PaliGemma2-3b-224-COCO**     | **30.12**   |
 Outstanding Result: 4.2x improvement in METEOR score, demonstrating superior semantic accuracy.

 |:------------------------------:|:------:|:------:|:------:|:------:|:----------------:|
 | THAI-BLIP-2                    | 40.62   | 17.72  | 8.36   | 4.04   | 10.44            |
 | Blip2-Typhoon1.5-COCO          | 41.47   | 18.09  | 8.22   | 3.75   | 7.48            |
+| PaliGemma2-3b-224-COCO     | **42.03**   | **19.11**  | **9.29**   | **4.80**   | **12.42**            |
 Key Achievement: ~3.3x improvement in BLEU-1 score, indicating significantly better basic translation accuracy.
 |:------------------------------:|:-------:|
 | THAI-BLIP-2                    | 1.93    |
 | Blip2-Typhoon1.5-COCO          | 0.93    |
+| PaliGemma2-3b-224-COCO     | **2.82**    |
 Notable Improvement: 2.5x enhancement in ROUGE-1 score, showing better content matching.
 |:--------------------------------:|:--------------:|
 | THAI-BLIP-2                      | 78.18          |
 | Blip2-Typhoon1.5-COCO            | 77.00          |
+| PaliGemma2-3b-224-COCO       | **79.33**          |
 Significant Gain: 9.25 point improvement in BERTScore, validated using bert-base-multilingual-cased model.
 |:------------------------------:|:-------:|
 | THAI-BLIP-2                    | 27.18   |
 | Blip2-Typhoon1.5-COCO          | 21.90   |
+| PaliGemma2-3b-224-COCO     | **30.12**   |
 Outstanding Result: 4.2x improvement in METEOR score, demonstrating superior semantic accuracy.