kobart-trans-en-ko-v2 / config.json
dylanmengzhou's picture
Training in progress, epoch 1
9dd6c82
raw
history blame
1.46 kB
{
"_name_or_path": "circulus/kobart-trans-en-ko-v2",
"activation_dropout": 0.0,
"activation_function": "gelu",
"add_bias_logits": false,
"add_final_layer_norm": false,
"architectures": [
"BartForConditionalGeneration"
],
"attention_dropout": 0.0,
"author": "Heewon Jeon(madjakarta@gmail.com)",
"bos_token_id": 1,
"classif_dropout": 0.1,
"classifier_dropout": 0.1,
"d_model": 768,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 3072,
"decoder_layerdrop": 0.0,
"decoder_layers": 6,
"decoder_start_token_id": 1,
"do_blenderbot_90_layernorm": false,
"dropout": 0.1,
"encoder_attention_heads": 16,
"encoder_ffn_dim": 3072,
"encoder_layerdrop": 0.0,
"encoder_layers": 6,
"eos_token_id": 1,
"extra_pos_embeddings": 2,
"force_bos_token_to_be_generated": false,
"forced_eos_token_id": 1,
"gradient_checkpointing": false,
"id2label": {
"0": "NEGATIVE",
"1": "POSITIVE"
},
"init_std": 0.02,
"is_encoder_decoder": true,
"kobart_version": 2.0,
"label2id": {
"NEGATIVE": 0,
"POSITIVE": 1
},
"max_position_embeddings": 1026,
"model_type": "bart",
"normalize_before": false,
"normalize_embedding": true,
"num_hidden_layers": 6,
"pad_token_id": 3,
"scale_embedding": false,
"static_position_embeddings": false,
"tokenizer_class": "PreTrainedTokenizerFast",
"torch_dtype": "float32",
"transformers_version": "4.28.1",
"use_cache": true,
"vocab_size": 30000
}