Hugging Face's logo

motheecreator
/
ViT-GPT2-Image-Captioning

Image-to-Text
Transformers
Safetensors
vision-encoder-decoder
image-text-to-text
Generated from Trainer
Inference Endpoints
Model card Files Community
motheecreator commited on
Commit
68bfe75
•
1 Parent(s): bcd52dc

Upload ViT-GPT2 model

Browse files
Files changed (4) hide show
  1. config.json +1 -1
  2. model.safetensors +1 -1
  3. preprocessor_config.json +1 -1
  4. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "motheecreator/ViT-GPT2-Image_Captioning_model",
3
  "architectures": [
4
  "VisionEncoderDecoderModel"
5
  ],
 
1
  {
2
+ "_name_or_path": "motheecreator/ViT-GPT2-Image-Captioning",
3
  "architectures": [
4
  "VisionEncoderDecoderModel"
5
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df6d7cacba8005a9958206742d9a5927c35137802cf52daebc4f41a431f54517
3
  size 956835520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60010e4c2fffe706dcb77b0febd0bcbf96ace57656522420dfbaa90a25f1e188
3
  size 956835520
preprocessor_config.json CHANGED
@@ -7,7 +7,7 @@
7
  0.5,
8
  0.5
9
  ],
10
- "feature_extractor_type": "ViTFeatureExtractor",
11
  "image_std": [
12
  0.5,
13
  0.5,
 
7
  0.5,
8
  0.5
9
  ],
10
+ "image_processor_type": "ViTFeatureExtractor",
11
  "image_std": [
12
  0.5,
13
  0.5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbaa3012913b518ee4ffc38680bb18e9c7c709d6b2a11823544cebeb6878c105
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc778c29dd169daae9ef298ffd614bd10d12de1ecd4350610ac3083c01cbcd9a
3
  size 5304