Update tiny models for PeAudioModel

config.json

@@ -0,0 +1,120 @@
+{
+  "architectures": [
+    "PeAudioModel"
+  ],
+  "audio_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "dac_config": {
+      "_name_or_path": "",
+      "architectures": null,
+      "chunk_size_feed_forward": 0,
+      "codebook_dim": 32,
+      "codebook_loss_weight": 1.0,
+      "codebook_size": 512,
+      "commitment_loss_weight": 0.25,
+      "decoder_hidden_size": 16,
+      "downsampling_ratios": [
+        2,
+        4,
+        4
+      ],
+      "dtype": null,
+      "encoder_hidden_size": 16,
+      "hidden_size": 128,
+      "hop_length": 32,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "model_type": "dac",
+      "n_codebooks": 6,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "problem_type": null,
+      "quantizer_dropout": 0.0,
+      "return_dict": true,
+      "sampling_rate": 16000,
+      "upsampling_ratios": [
+        4,
+        4,
+        2
+      ]
+    },
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "max_position_embeddings": 512,
+    "max_window_layers": 28,
+    "model_type": "pe_audio_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"
+    }
+  },
+  "dtype": "float32",
+  "model_type": "pe_audio",
+  "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"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5928a9122bfcdefcce4da2202b4cb782b2716063b28003223e5b942f934e072
+size 7933096

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"
+}