|
- {"architectures": ["RobertaForMaskedLM"], "attention_probs_dropout_prob": 0.1, "finetuning_task": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 20, "layer_norm_eps": 1e-05, "max_position_embeddings": 20, "num_attention_heads": 4, "num_hidden_layers": 2, "num_labels": 2, "output_attentions": false, "output_hidden_states": false, "torchscript": false, "type_vocab_size": 1, "vocab_size": 68}
|