|
{ |
|
"_label_trainable_num_channels": 1024, |
|
"_name_or_path": "deepmind/language-perceiver", |
|
"architectures": [ |
|
"PerceiverForSequenceClassification" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"audio_samples_per_frame": 1920, |
|
"cross_attention_shape_for_attention": "kv", |
|
"cross_attention_widening_factor": 1, |
|
"d_latents": 1280, |
|
"d_model": 768, |
|
"finetuning_task": "text-classification", |
|
"hidden_act": "gelu", |
|
"id2label": { |
|
"0": "History & Politics", |
|
"1": "Health & Medicine", |
|
"2": "Mystery & Thriller", |
|
"3": "Arts & Design", |
|
"4": "Self-Help & Wellness", |
|
"5": "Sports & Recreation", |
|
"6": "Non-Fiction", |
|
"7": "Science Fiction & Fantasy", |
|
"8": "Countries & Geography", |
|
"9": "Other", |
|
"10": "Nature & Environment", |
|
"11": "Business & Finance", |
|
"12": "Romance", |
|
"13": "Philosophy & Religion", |
|
"14": "Literature & Fiction", |
|
"15": "Science & Technology", |
|
"16": "Children & Young Adult", |
|
"17": "Food & Cooking" |
|
}, |
|
"image_size": 56, |
|
"initializer_range": 0.02, |
|
"label2id": { |
|
"Arts & Design": 3, |
|
"Business & Finance": 11, |
|
"Children & Young Adult": 16, |
|
"Countries & Geography": 8, |
|
"Food & Cooking": 17, |
|
"Health & Medicine": 1, |
|
"History & Politics": 0, |
|
"Literature & Fiction": 14, |
|
"Mystery & Thriller": 2, |
|
"Nature & Environment": 10, |
|
"Non-Fiction": 6, |
|
"Other": 9, |
|
"Philosophy & Religion": 13, |
|
"Romance": 12, |
|
"Science & Technology": 15, |
|
"Science Fiction & Fantasy": 7, |
|
"Self-Help & Wellness": 4, |
|
"Sports & Recreation": 5 |
|
}, |
|
"layer_norm_eps": 1e-12, |
|
"max_position_embeddings": 2048, |
|
"model_type": "perceiver", |
|
"num_blocks": 1, |
|
"num_cross_attention_heads": 8, |
|
"num_frames": 16, |
|
"num_latents": 256, |
|
"num_self_attends_per_block": 26, |
|
"num_self_attention_heads": 8, |
|
"output_num_channels": 512, |
|
"output_shape": [ |
|
1, |
|
16, |
|
224, |
|
224 |
|
], |
|
"problem_type": "multi_label_classification", |
|
"qk_channels": 256, |
|
"samples_per_patch": 16, |
|
"self_attention_widening_factor": 1, |
|
"torch_dtype": "float32", |
|
"train_size": [ |
|
368, |
|
496 |
|
], |
|
"transformers_version": "4.33.3", |
|
"use_query_residual": true, |
|
"v_channels": 1280, |
|
"vocab_size": 262 |
|
} |
|
|