Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+---
+base_model:
+- openai/clip-vit-large-patch14
+datasets:
+- tanganke/stanford_cars
+metrics:
+- accuracy
+---
+
+# Model Card
+
+## Model Details
+
+- Architecture: ViT-Large with patch size 14
+- Training Data: stanford cars 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: 0.7770098447799683
+- fine-tuned: 0.92734694480896
+

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "results/temp/",
+  "architectures": [
+    "CLIPVisionModel"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 1024,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "patch_size": 14,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d3b19b43a723f6afafb8a0d140cde7ec732006dc76f4eca14e1d167666cc3e0
+size 1212766896