update eval
Browse files
README.md
CHANGED
@@ -65,8 +65,8 @@ We conduct evaluation on 9 commonly-used benchmarks, including 5 academic VQA be
|
|
65 |
|
66 |
| Models | Size | VQAv2 | GQA | SQA(IMG) | TextVQA | POPE | MME(P) | MMB |MMB_CN|MM-Vet|
|
67 |
|:--------:|:-----:|:----:|:-------------:|:--------:|:-----:|:----:|:-------:|:-------:|:-------:|:-------:|
|
68 |
-
| Bunny-
|
69 |
-
| **Imp-v1.5-4B-Phi3**| 4B | 81.5 | **63.5** | **78.0**|60.2 | 86.9
|
70 |
|
71 |
|
72 |
|
|
|
65 |
|
66 |
| Models | Size | VQAv2 | GQA | SQA(IMG) | TextVQA | POPE | MME(P) | MMB |MMB_CN|MM-Vet|
|
67 |
|:--------:|:-----:|:----:|:-------------:|:--------:|:-----:|:----:|:-------:|:-------:|:-------:|:-------:|
|
68 |
+
| Bunny-v1.0-4B| 4B | **81.5** |**63.5** | 75.1|- | 86.7| 1495.2 |**73.5** |-|-|
|
69 |
+
| **Imp-v1.5-4B-Phi3**| 4B | **81.5** | **63.5** | **78.0**|60.2 | **86.9**| **1507.7** |73.3 |61.1|44.6|
|
70 |
|
71 |
|
72 |
|