{ "_name_or_path": "scale_normformer/checkpoint-1000000", "architectures": [ "XLMRobertaModel" ], "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "classifier_dropout": null, "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-12, "max_position_embeddings": 512, "model_type": "xlm-roberta", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 1, "position_embedding_type": "absolute", "scale_attn": true, "scale_fc": true, "scale_heads": true, "scale_post": false, "scale_pre": true, "scale_resids": true, "torch_dtype": "float32", "transformers_version": "4.19.0.dev0", "type_vocab_size": 2, "use_cache": true, "vocab_size": 52005 }