tanganke commited on
Commit
e863c1c
1 Parent(s): 0444730

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. README.md +26 -0
  2. config.json +23 -0
  3. model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - openai/clip-vit-large-patch14
4
+ datasets:
5
+ - tanganke/stanford_cars
6
+ metrics:
7
+ - accuracy
8
+ ---
9
+
10
+ # Model Card
11
+
12
+ ## Model Details
13
+
14
+ - Architecture: ViT-Large with patch size 14
15
+ - Training Data: stanford cars dataset
16
+
17
+ ## Training Details
18
+
19
+ Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training (batch_size=32).
20
+ Only the vision encoder is fine-tuned.
21
+
22
+ ## Evaluation Results
23
+
24
+ - pre-trained: 0.7770098447799683
25
+ - fine-tuned: 0.92734694480896
26
+
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "results/temp/",
3
+ "architectures": [
4
+ "CLIPVisionModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dropout": 0.0,
8
+ "hidden_act": "quick_gelu",
9
+ "hidden_size": 1024,
10
+ "image_size": 224,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 16,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 24,
19
+ "patch_size": 14,
20
+ "projection_dim": 768,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.39.1"
23
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3b19b43a723f6afafb8a0d140cde7ec732006dc76f4eca14e1d167666cc3e0
3
+ size 1212766896