|
{ |
|
"architectures": [ |
|
"FusionCrossAttentionSentenceClassifier" |
|
], |
|
"dropout": 0.3, |
|
"embedding_strategy": "self-att", |
|
"fp16": false, |
|
"fusion_layers": 2, |
|
"fusion_strategy": "dense", |
|
"heads": 8, |
|
"hidden_size": 768, |
|
"k1_backbone": "whisper-encoder-small", |
|
"k1_freezed": true, |
|
"k1_kwargs": { |
|
"load_in_4bit": false |
|
}, |
|
"k2_backbone": "transformer-prosody-encoder192", |
|
"k2_freezed": false, |
|
"k2_kwargs": { |
|
"dropout": 0.3, |
|
"heads": 8, |
|
"input_size": 5, |
|
"num_layers": 2 |
|
}, |
|
"labels": 18, |
|
"model_type": "fusion-cross-attention-sentence-classifier", |
|
"multilabel": true, |
|
"q_backbone": "distilbert-base-uncased", |
|
"q_freezed": true, |
|
"q_kwargs": {}, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.41.2" |
|
} |
|
|