config.json

{
 "_commit_hash": "6b9e8f1a0ab2ce3ae9d55d68324020a0638e889c",
 "_name_or_path": "google/vit-hybrid-base-bit-384",
 "architectures": [
 "ViTHybridForImageClassification"
 ],
 "attention_probs_dropout_prob": 0.0,
 "backbone_config": {
 "_name_or_path": "",
 "add_cross_attention": false,
 "architectures": null,
 "bad_words_ids": null,
 "begin_suppress_tokens": null,
 "bos_token_id": null,
 "chunk_size_feed_forward": 0,
 "cross_attention_hidden_size": null,
 "decoder_start_token_id": null,
 "depths": [
 3,
 4,
 9
 ],
 "diversity_penalty": 0.0,
 "do_sample": false,
 "drop_path_rate": 0.0,
 "early_stopping": false,
 "embedding_dynamic_padding": true,
 "embedding_size": 64,
 "encoder_no_repeat_ngram_size": 0,
 "eos_token_id": null,
 "exponential_decay_length_penalty": null,
 "finetuning_task": null,
 "forced_bos_token_id": null,
 "forced_eos_token_id": null,
 "global_padding": "SAME",
 "hidden_act": "relu",
 "hidden_sizes": [
 256,
 512,
 1024,
 2048
 ],
 "id2label": {
 "0": "LABEL_0",
 "1": "LABEL_1"
 },
 "is_decoder": false,
 "is_encoder_decoder": false,
 "label2id": {
 "LABEL_0": 0,
 "LABEL_1": 1
 },
 "layer_type": "bottleneck",
 "length_penalty": 1.0,
 "max_length": 20,
 "min_length": 0,
 "model_type": "bit",
 "no_repeat_ngram_size": 0,
 "num_beam_groups": 1,
 "num_beams": 1,
 "num_channels": 3,
 "num_groups": 32,
 "num_return_sequences": 1,
 "out_features": [
 "stage3"
 ],
 "output_attentions": false,
 "output_hidden_states": false,
 "output_scores": false,
 "output_stride": 32,
 "pad_token_id": null,
 "prefix": null,
 "problem_type": null,
 "pruned_heads": {},
 "remove_invalid_values": false,
 "repetition_penalty": 1.0,
 "return_dict": true,
 "return_dict_in_generate": false,
 "sep_token_id": null,
 "stage_names": [
 "stem",
 "stage1",
 "stage2",
 "stage3"
 ],
 "suppress_tokens": null,
 "task_specific_params": null,
 "temperature": 1.0,
 "tf_legacy_loss": false,
 "tie_encoder_decoder": false,
 "tie_word_embeddings": true,
 "tokenizer_class": null,
 "top_k": 50,
 "top_p": 1.0,
 "torch_dtype": null,
 "torchscript": false,
 "transformers_version": "4.26.1",
 "typical_p": 1.0,
 "use_bfloat16": false,
 "width_factor": 1
 },
 "backbone_featmap_shape": [
 1,
 1024,
 24,
 24
 ],
 "hidden_act": "gelu",
 "hidden_dropout_prob": 0.0,
 "hidden_size": 768,
 "id2label": {
 "0": "calling",
 "1": "clapping",
 "2": "cycling",
 "3": "dancing",
 "4": "drinking",
 "5": "eating",
 "6": "fighting",
 "7": "hugging",
 "8": "laughing",
 "9": "listening_to_music",
 "10": "running",
 "11": "sitting",
 "12": "sleeping",
 "13": "texting",
 "14": "using_laptop"
 },
 "image_size": 384,
 "initializer_range": 0.02,
 "intermediate_size": 3072,
 "label2id": {
 "calling": 0,
 "clapping": 1,
 "cycling": 2,
 "dancing": 3,
 "drinking": 4,
 "eating": 5,
 "fighting": 6,
 "hugging": 7,
 "laughing": 8,
 "listening_to_music": 9,
 "running": 10,
 "sitting": 11,
 "sleeping": 12,
 "texting": 13,
 "using_laptop": 14
 },
 "layer_norm_eps": 1e-12,
 "model_type": "vit-hybrid",
 "num_attention_heads": 12,
 "num_channels": 3,
 "num_hidden_layers": 12,
 "patch_size": 1,
 "problem_type": "single_label_classification",
 "qkv_bias": true,
 "torch_dtype": "float32",
 "transformers_version": null
}