| { |
| "architectures": [ |
| "PerceiverForSequenceClassification" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "audio_samples_per_frame": 200, |
| "cross_attention_shape_for_attention": "kv", |
| "cross_attention_widening_factor": 4, |
| "d_latents": 20, |
| "d_model": 768, |
| "hidden_act": "gelu", |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1", |
| "2": "LABEL_2" |
| }, |
| "image_size": 32, |
| "initializer_range": 0.02, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1, |
| "LABEL_2": 2 |
| }, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 40, |
| "model_type": "perceiver", |
| "num_blocks": 1, |
| "num_cross_attention_heads": 1, |
| "num_frames": 5, |
| "num_latents": 10, |
| "num_self_attends_per_block": 2, |
| "num_self_attention_heads": 1, |
| "output_shape": [ |
| 1, |
| 16, |
| 224, |
| 224 |
| ], |
| "qk_channels": 20, |
| "samples_per_patch": 20, |
| "self_attention_widening_factor": 4, |
| "torch_dtype": "float32", |
| "train_size": [ |
| 20, |
| 20 |
| ], |
| "transformers_version": "4.28.0.dev0", |
| "use_query_residual": true, |
| "v_channels": 20, |
| "vocab_size": 262 |
| } |
|
|
