| { |
| "_name_or_path": "dangvantuan/bilingual_impl", |
| "architectures": [ |
| "BilingualModel" |
| ], |
| "model_type": "bilingual", |
| "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": 1024, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "layer_norm_eps": 1e-05, |
| "max_position_embeddings": 8194, |
| "num_attention_heads": 16, |
| "num_hidden_layers": 24, |
| "output_past": true, |
| "pad_token_id": 1, |
| "position_embedding_type": "absolute", |
| "torch_dtype": "float16", |
| "transformers_version": "4.38.2", |
| "type_vocab_size": 1, |
| "use_cache": true, |
| "vocab_size": 250002 |
| } |