Upload 4 files

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "MCG-NJU/videomae-base",
+  "architectures": [
+    "VideoMAEForVideoClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "decoder_hidden_size": 384,
+  "decoder_intermediate_size": 1536,
+  "decoder_num_attention_heads": 6,
+  "decoder_num_hidden_layers": 4,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "A\u0306n",
+    "1": "Ban nga\u0300y",
+    "2": "Ban \u0111e\u0302m",
+    "3": "Ba\u0323n",
+    "4": "Bo\u0302\u0301",
+    "5": "Ca\u0309m o\u031bn",
+    "6": "Cho\u031bi",
+    "7": "Cu\u031bo\u031b\u0300i",
+    "8": "Kho\u0301c",
+    "9": "La\u0300m vie\u0323\u0302c",
+    "10": "Me\u0323",
+    "11": "Mo\u0302\u0303i nga\u0300y",
+    "12": "Sa\u0301ch",
+    "13": "To\u0302i",
+    "14": "Vie\u0302\u0301t",
+    "15": "Xem",
+    "16": "Xin cha\u0300o",
+    "17": "Xin lo\u0302\u0303i",
+    "18": "\u0110i",
+    "19": "\u0110i ho\u0323c"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "A\u0306n": 0,
+    "Ban nga\u0300y": 1,
+    "Ban \u0111e\u0302m": 2,
+    "Ba\u0323n": 3,
+    "Bo\u0302\u0301": 4,
+    "Ca\u0309m o\u031bn": 5,
+    "Cho\u031bi": 6,
+    "Cu\u031bo\u031b\u0300i": 7,
+    "Kho\u0301c": 8,
+    "La\u0300m vie\u0323\u0302c": 9,
+    "Me\u0323": 10,
+    "Mo\u0302\u0303i nga\u0300y": 11,
+    "Sa\u0301ch": 12,
+    "To\u0302i": 13,
+    "Vie\u0302\u0301t": 14,
+    "Xem": 15,
+    "Xin cha\u0300o": 16,
+    "Xin lo\u0302\u0303i": 17,
+    "\u0110i": 18,
+    "\u0110i ho\u0323c": 19
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "videomae",
+  "norm_pix_loss": true,
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_frames": 16,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "VideoMAEFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "VideoMAEImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c9c930c461fbf7e28d1e506ce8e4a08410e3a26c004e296e931b2cdc542c60
+size 345034293

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9244e800ffbd92379b525015bb89f779c9e73ecd34803b91542ba481428432c9
+size 3963