Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
library_name: transformers
|
| 5 |
+
pipeline_tag: image-text-to-text
|
| 6 |
+
tags:
|
| 7 |
+
- vision
|
| 8 |
+
---
|
| 9 |
+
# ADD HEAD
|
| 10 |
+
|
| 11 |
+
```
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
print('Add Vision...')
|
| 16 |
+
# ADD HEAD
|
| 17 |
+
# Combine pre-trained encoder and pre-trained decoder to form a Seq2Seq model
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
Vmodel = VisionEncoderDecoderModel.from_encoder_decoder_pretrained(
|
| 22 |
+
"google/vit-base-patch16-224-in21k", "LeroyDyer/Mixtral_AI_Tiny"
|
| 23 |
+
)
|
| 24 |
+
_Encoder_ImageProcessor = Vmodel.encoder
|
| 25 |
+
_Decoder_ImageTokenizer = Vmodel.decoder
|
| 26 |
+
_VisionEncoderDecoderModel = Vmodel
|
| 27 |
+
# Add Pad tokems
|
| 28 |
+
LM_MODEL.VisionEncoderDecoder = _VisionEncoderDecoderModel
|
| 29 |
+
# Add Sub Components
|
| 30 |
+
LM_MODEL.Encoder_ImageProcessor = _Encoder_ImageProcessor
|
| 31 |
+
LM_MODEL.Decoder_ImageTokenizer = _Decoder_ImageTokenizer
|
| 32 |
+
LM_MODEL
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
```
|