| { | |
| "architectures": [ | |
| "TSPModelForPreTraining" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_tsp.TSPConfig", | |
| "AutoModel": "modeling_tsp.TSPModel", | |
| "AutoModelForPreTraining": "modeling_tsp.TSPModelForPreTraining", | |
| "AutoModelForQuestionAnswering": "modeling_tsp.TSPModelForQuestionAnswering", | |
| "AutoModelForSequenceClassification": "modeling_tsp.TSPModelForSequenceClassification", | |
| "AutoModelForTokenClassification": "modeling_tsp.TSPModelForTokenClassification" | |
| }, | |
| "dropout_prob": 0.1, | |
| "electra_generator_size_divisor": 4, | |
| "embedding_size": 128, | |
| "hidden_size": 256, | |
| "intermediate_size": 1024, | |
| "max_sequence_length": 128, | |
| "model_type": "tsp", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.19.0.dev0", | |
| "use_electra": true, | |
| "vocab_size": 30522 | |
| } | |