Upload folder using huggingface_hub

README.md

@@ -0,0 +1,23 @@
+---
+base_model:
+- openai/clip-vit-large-patch14
+datasets:
+- tanganke/sun397
+- tanganke/stanford_cars
+- tanganke/resisc45
+- tanganke/eurosat
+- ufldl-stanford/svhn
+- tanganke/gtsrb
+- ylecun/mnist
+- tanganke/dtd
+metrics:
+- accuracy
+---
+
+# Model Card
+
+Table: Accuracy on test datasets.
+
+| Method | SUN397 | Cars | RESISC45 | EuroSAT | SVHN | GTSRB | MNIST | DTD | Average |
+| --------------- | ------ | ---- | -------- | ------- | ---- | ----- | ----- | ---- | ------- |
+| Traditional MTL | 79.0 | 89.3 | 94.5 | 98.4 | 96.4 | 98.1 | 99.4 | 83.7 | 92.4 |

config.json

@@ -0,0 +1,23 @@
+{
+ "_name_or_path": "openai/clip-vit-large-patch14",
+ "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": "4.43.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9382fe7ed168c5852ded13a4f2762321126af4c5e671ba0fb875b56d468b6f94
+size 1212766896

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+ "crop_size": {
+ "height": 224,
+ "width": 224
+ },
+ "do_center_crop": true,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.48145466,
+ 0.4578275,
+ 0.40821073
+ ],
+ "image_processor_type": "CLIPImageProcessor",
+ "image_std": [
+ 0.26862954,
+ 0.26130258,
+ 0.27577711
+ ],
+ "processor_class": "CLIPProcessor",
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "size": {
+ "shortest_edge": 224
+ }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+ "bos_token": {
+ "content": "<|startoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "49406": {
+ "content": "<|startoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "49407": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|startoftext|>",
+ "clean_up_tokenization_spaces": true,
+ "do_lower_case": true,
+ "eos_token": "<|endoftext|>",
+ "errors": "replace",
+ "model_max_length": 77,
+ "pad_token": "<|endoftext|>",
+ "processor_class": "CLIPProcessor",
+ "tokenizer_class": "CLIPTokenizer",
+ "unk_token": "<|endoftext|>"
+}