optimum-intel-internal-testing/tiny-random-Data2VecAudioModel

1{2  "activation_dropout": 0.1,3  "adapter_kernel_size": 3,4  "adapter_stride": 2,5  "add_adapter": false,6  "architectures": [7    "Data2VecAudioModel"8  ],9  "attention_dropout": 0.1,10  "bos_token_id": 1,11  "classifier_proj_size": 256,12  "conv_bias": false,13  "conv_dim": [14    32,15    32,16    3217  ],18  "conv_kernel": [19    8,20    8,21    822  ],23  "conv_pos_kernel_size": 19,24  "conv_stride": [25    4,26    4,27    428  ],29  "ctc_loss_reduction": "sum",30  "ctc_zero_infinity": false,31  "eos_token_id": 2,32  "feat_extract_activation": "gelu",33  "feat_extract_dropout": 0.0,34  "feat_proj_dropout": 0.0,35  "final_dropout": 0.1,36  "hidden_act": "gelu",37  "hidden_dropout": 0.1,38  "hidden_dropout_prob": 0.1,39  "hidden_size": 16,40  "initializer_range": 0.02,41  "intermediate_size": 20,42  "layer_norm_eps": 1e-05,43  "layerdrop": 0.1,44  "mask_feature_length": 10,45  "mask_feature_min_masks": 0,46  "mask_feature_prob": 0.0,47  "mask_time_length": 2,48  "mask_time_min_masks": 2,49  "mask_time_prob": 0.5,50  "model_type": "data2vec-audio",51  "num_adapter_layers": 1,52  "num_attention_heads": 2,53  "num_conv_pos_embedding_groups": 2,54  "num_conv_pos_embeddings": 16,55  "num_feat_extract_layers": 3,56  "num_hidden_layers": 4,57  "output_hidden_size": 16,58  "pad_token_id": 0,59  "tdnn_dilation": [60    1,61    262  ],63  "tdnn_dim": [64    32,65    3266  ],67  "tdnn_kernel": [68    5,69    370  ],71  "torch_dtype": "float32",72  "transformers_version": "4.25.0.dev0",73  "use_weighted_layer_sum": false,74  "vocab_size": 32,75  "xvector_output_dim": 3276}77