{ | |
"architectures": [ | |
"LongelmForMaskedLMWithEdgePrediction" | |
], | |
"attention_probs_dropout_prob": 0.1, | |
"block_size": 8, | |
"bos_token_id": 1, | |
"classifier_dropout": null, | |
"eos_token_id": 2, | |
"ep_add_linear_projection": true, | |
"global_memory_size": 1, | |
"hidden_act": "gelu", | |
"hidden_dropout_prob": 0.1, | |
"hidden_size": 768, | |
"initializer_range": 0.02, | |
"intermediate_size": 3072, | |
"layer_norm_eps": 1e-12, | |
"max_blocks": 200, | |
"max_position_embeddings": 1801, | |
"max_relative_position_embeddings": 8, | |
"model_type": "longelm", | |
"node_size": 1, | |
"num_attention_heads": 12, | |
"num_hidden_layers": 12, | |
"pad_token_id": 3, | |
"position_embedding_type": "mixed", | |
"torch_dtype": "float32", | |
"transformers_version": "4.34.1", | |
"type_vocab_size": 2, | |
"use_cache": true, | |
"vocab_size": 50265 | |
} | |