|
{ |
|
"_name_or_path": "AutoTrain", |
|
"activation_dropout": 0.0, |
|
"activation_function": "gelu", |
|
"add_bias_logits": false, |
|
"add_final_layer_norm": true, |
|
"architectures": [ |
|
"MBartForConditionalGeneration" |
|
], |
|
"attention_dropout": 0.1, |
|
"bos_token_id": 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": 250021, |
|
"dropout": 0.1, |
|
"encoder_attention_heads": 16, |
|
"encoder_ffn_dim": 4096, |
|
"encoder_layerdrop": 0.0, |
|
"encoder_layers": 12, |
|
"eos_token_id": 2, |
|
"extra_pos_embeddings": 2, |
|
"force_bos_token_to_be_generated": false, |
|
"forced_eos_token_id": 2, |
|
"init_std": 0.02, |
|
"is_encoder_decoder": true, |
|
"max_length": 200, |
|
"max_position_embeddings": 1024, |
|
"model_type": "mbart", |
|
"normalize_before": true, |
|
"normalize_embedding": true, |
|
"num_beams": 5, |
|
"num_hidden_layers": 12, |
|
"output_past": true, |
|
"pad_token_id": 1, |
|
"scale_embedding": true, |
|
"static_position_embeddings": false, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.28.1", |
|
"use_cache": true, |
|
"vocab_size": 250027 |
|
} |
|
|