|
{ |
|
"activation": "gelu", |
|
"architectures": [ |
|
"DistilBertForSequenceClassification" |
|
], |
|
"attention_dropout": 0.1, |
|
"attention_probs_dropout_prob": 0.8, |
|
"bos_token_id": 0, |
|
"dim": 768, |
|
"do_sample": true, |
|
"dropout": 0.1, |
|
"eos_token_ids": 0, |
|
"gradient_checkpointing": false, |
|
"hidden_act": "gelu", |
|
"hidden_dim": 3072, |
|
"hidden_dropout_prob": 0.4, |
|
"hidden_size": 768, |
|
"id2label": { |
|
"0": "NEGATIVE", |
|
"1": "NEUTRAL", |
|
"2": "POSITIVE" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"label2id": { |
|
"NEGATIVE": 0, |
|
"NEUTRAL": 1, |
|
"POSITIVE": 2 |
|
}, |
|
"layer_norm_eps": 1e-12, |
|
"max_position_embeddings": 512, |
|
"model_type": "bert", |
|
"n_heads": 12, |
|
"n_layers": 6, |
|
"num_attention_heads": 12, |
|
"num_beams": 500, |
|
"num_hidden_layers": 12, |
|
"output_past": true, |
|
"pad_token_id": 0, |
|
"qa_dropout": 0.1, |
|
"repetition_penalty": 5, |
|
"seq_classif_dropout": 0.2, |
|
"sinusoidal_pos_embds": false, |
|
"tie_weights_": true, |
|
"type_vocab_size": 2, |
|
"vocab_size": 28996 |
|
} |
|
|