Upload folder using huggingface_hub

README.md

@@ -9,36 +9,16 @@ metrics:
 
 # Model Card
 
-## Model Details
-
-- Architecture: ViT-Base with patch size 32
-- Training Data: oxford-iiit-pet dataset
-
 ## Training Details
 
-  Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training (batch_size=32).
-  Only the vision encoder is fine-tuned.
-
-## Evaluation Results
-
-- pre-trained: 0.8317149877548218
-- fine-tuned: 0.9084667563438416
+Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training (batch_size=128).
+Only the vision encoder is fine-tuned.
 
-## Usage
+![alt text](image.png)
 
-load vision model
-
-```python
-from transformers import CLIPVisionModel
-
-vision_model = CLIPVisionModel.from_pretrained('tanganke/clip-vit-base-patch32_oxford-iiit-pet')
-```
-
-substitute the vision encoder of clip
+## Evaluation Results
 
-```python
-from transformers import CLIPModel
+Test set accuracy:
 
-clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
-clip_model.vision_model.load_state_dict(vision_model.vision_model.state_dict())
-```
+- pre-trained: 0.8331970572471619
+- fine-tuned: 0.9245026111602783

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "results/temp/",
+  "_name_or_path": "openai/clip-vit-base-patch32",
   "architectures": [
     "CLIPVisionModel"
   ],
@@ -19,5 +19,5 @@
   "patch_size": 32,
   "projection_dim": 512,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.1"
+  "transformers_version": "4.47.0"
 }

events.out.tfevents.1733995624.amax.1917161.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a1360573363a0d4e89d1704e5e79d890012f7ebe247b9a2d34d27f18b10eb0e
+size 195958

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37119d9b7fe99b0c8c21bd38be893f1a7fae1b35bd696805a80c2fa6c9aee7d0
+oid sha256:af15c4b9c204083b5f173fab4b5fda95cbaac984f0eb8f8ecd948d8b80d22680
 size 349847824