Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,18 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
|
| 5 |
# OFA-huge
|
| 6 |
This is the **huge** version of OFA pretrained model. OFA is a unified multimodal pretrained model that unifies modalities (i.e., cross-modality, vision, language) and tasks (e.g., image generation, visual grounding, image captioning, image classification, text generation, etc.) to a simple sequence-to-sequence learning framework.
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
+
OFA-huge checkpoint optimized for image captioning task.
|
| 5 |
+
Transition from fairseq -> huggingface style has been performed
|
| 6 |
+
|
| 7 |
+
This checkpoint is not uploaded by the official OFA-sys, so i upload it for use.
|
| 8 |
+
|
| 9 |
+
Thanks to OFA-sys
|
| 10 |
+
(https://github.com/OFA-Sys/OFA)
|
| 11 |
+
(https://huggingface.co/OFA-Sys/ofa-huge)
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
|
| 17 |
# OFA-huge
|
| 18 |
This is the **huge** version of OFA pretrained model. OFA is a unified multimodal pretrained model that unifies modalities (i.e., cross-modality, vision, language) and tasks (e.g., image generation, visual grounding, image captioning, image classification, text generation, etc.) to a simple sequence-to-sequence learning framework.
|