File size: 1,400 Bytes
9dba123 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 |
{
"_name_or_path": "dangvantuan/bilingual_impl",
"architectures": [
"BilingualModel"
],
"model_type": "xlm-roberta",
"auto_map": {
"AutoConfig":"dangvantuan/bilingual_impl--config.BilingualConfig",
"AutoModel": "dangvantuan/bilingual_impl--modeling.BilingualModel",
"AutoModelForMaskedLM": "dangvantuan/bilingual_impl--modeling.BilingualForMaskedLM",
"AutoModelForMultipleChoice": "dangvantuan/bilingual_impl--modeling.BilingualForMultipleChoice",
"AutoModelForQuestionAnswering": "dangvantuan/bilingual_impl--modeling.BilingualForQuestionAnswering",
"AutoModelForSequenceClassification": "dangvantuan/bilingual_impl--modeling.BilingualForSequenceClassification",
"AutoModelForTokenClassification": "dangvantuan/bilingual_impl--modeling.BilingualForTokenClassification"
},
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"bos_token_id": 0,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"torch_dtype": "float16",
"transformers_version": "4.39.1",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250002
}
|