Update tiny models for PeVideoModel

config.json

@@ -0,0 +1,110 @@
+{
+  "architectures": [
+    "PeVideoModel"
+  ],
+  "dtype": "float32",
+  "model_type": "pe_video",
+  "projection_dim": 32,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 50281,
+    "classifier_activation": "gelu",
+    "classifier_bias": false,
+    "classifier_dropout": 0.0,
+    "classifier_pooling": "cls",
+    "cls_token_id": 50281,
+    "decoder_bias": true,
+    "deterministic_flash_attn": false,
+    "embedding_dropout": 0.0,
+    "eos_token_id": 50282,
+    "hidden_activation": "gelu",
+    "hidden_size": 32,
+    "initializer_cutoff_factor": 2.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_decoder": false,
+    "layer_types": [
+      "full_attention",
+      "sliding_attention"
+    ],
+    "local_attention": 128,
+    "max_position_embeddings": 512,
+    "mlp_bias": false,
+    "mlp_dropout": 0.0,
+    "model_type": "modernbert",
+    "norm_bias": false,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "pad_token_id": 50283,
+    "rope_parameters": {
+      "full_attention": {
+        "rope_theta": 160000.0,
+        "rope_type": "default"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sep_token_id": 50282,
+    "sparse_pred_ignore_index": -100,
+    "sparse_prediction": false,
+    "tie_word_embeddings": true,
+    "type_vocab_size": 16,
+    "vocab_size": 50368
+  },
+  "transformers_version": "5.16.0.dev0",
+  "video_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "head_dim": 16,
+    "hidden_act": "silu",
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "max_position_embeddings": 512,
+    "max_window_layers": 28,
+    "model_type": "pe_video_encoder",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "rope_theta": 20000,
+      "rope_type": "default"
+    },
+    "vision_config": {
+      "_name_or_path": "",
+      "architecture": "vit_pe_core_large_patch14_336",
+      "architectures": null,
+      "chunk_size_feed_forward": 0,
+      "do_pooling": true,
+      "dtype": null,
+      "global_pool": "map",
+      "initializer_range": 0.02,
+      "is_encoder_decoder": false,
+      "label_names": [
+        "LABEL_0",
+        "LABEL_1",
+        "LABEL_2",
+        "LABEL_3"
+      ],
+      "model_args": {
+        "depth": 2,
+        "embed_dim": 64,
+        "img_size": [
+          14,
+          14
+        ]
+      },
+      "model_type": "timm_wrapper",
+      "num_classes": 4,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "problem_type": null,
+      "return_dict": true
+    }
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b03ab9ca980e47dc006ce12c7aab34d880642b3ea8b85065d63fe266e5b6d5d
+size 7379360

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "feature_extractor_type": "PeAudioFeatureExtractor",
+  "feature_size": 1,
+  "hop_length": 1920,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 48000
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": [],
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "processor_class": "PeAudioVideoProcessor",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]"
+}

video_preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "height": 336,
+    "width": 336
+  },
+  "video_processor_type": "PeVideoVideoProcessor"
+}