|
{ |
|
"_name_or_path": "optimum_onnx_base", |
|
"_num_labels": 3, |
|
"activation_dropout": 0.0, |
|
"activation_function": "gelu", |
|
"add_final_layer_norm": false, |
|
"architectures": [ |
|
"BartForSequenceClassification" |
|
], |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 0, |
|
"classif_dropout": 0.0, |
|
"classifier_dropout": 0.0, |
|
"d_model": 1024, |
|
"decoder_attention_heads": 16, |
|
"decoder_ffn_dim": 4096, |
|
"decoder_layerdrop": 0.0, |
|
"decoder_layers": 12, |
|
"decoder_start_token_id": 2, |
|
"dropout": 0.1, |
|
"encoder_attention_heads": 16, |
|
"encoder_ffn_dim": 4096, |
|
"encoder_layerdrop": 0.0, |
|
"encoder_layers": 12, |
|
"eos_token_id": 2, |
|
"forced_eos_token_id": 2, |
|
"gradient_checkpointing": false, |
|
"id2label": { |
|
"0": "contradiction", |
|
"1": "neutral", |
|
"2": "entailment" |
|
}, |
|
"init_std": 0.02, |
|
"is_encoder_decoder": true, |
|
"label2id": { |
|
"contradiction": 0, |
|
"entailment": 2, |
|
"neutral": 1 |
|
}, |
|
"max_position_embeddings": 1024, |
|
"model_type": "bart", |
|
"normalize_before": false, |
|
"num_hidden_layers": 12, |
|
"output_past": false, |
|
"pad_token_id": 1, |
|
"scale_embedding": false, |
|
"transformers_version": "4.41.2", |
|
"use_cache": true, |
|
"vocab_size": 50265 |
|
} |
|
|