ultimate_model_v3 / config.json
long292's picture
End of training
01c8e0e verified
raw
history blame contribute delete
962 Bytes
{
"_name_or_path": "vinai/bartpho-syllable-base",
"activation_dropout": 0.0,
"activation_function": "gelu",
"architectures": [
"MBartForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"classifier_dropout": 0.0,
"d_model": 768,
"decoder_attention_heads": 12,
"decoder_ffn_dim": 3072,
"decoder_layerdrop": 0.0,
"decoder_layers": 6,
"decoder_start_token_id": 2,
"dropout": 0.1,
"encoder_attention_heads": 12,
"encoder_ffn_dim": 3072,
"encoder_layerdrop": 0.0,
"encoder_layers": 6,
"eos_token_id": 2,
"forced_eos_token_id": 2,
"gradient_checkpointing": false,
"init_std": 0.02,
"is_encoder_decoder": true,
"max_position_embeddings": 1024,
"model_type": "mbart",
"num_hidden_layers": 6,
"pad_token_id": 1,
"scale_embedding": false,
"tokenizer_class": "BartphoTokenizer",
"torch_dtype": "float32",
"transformers_version": "4.39.3",
"use_cache": true,
"vocab_size": 40030
}