lukasdrg's picture
End of training
c461810
raw
history blame contribute delete
887 Bytes
{
"_name_or_path": "allenai/longformer-base-4096",
"architectures": [
"LongformerForMaskedLM"
],
"attention_mode": "longformer",
"attention_probs_dropout_prob": 0.1,
"attention_window": [
512,
512,
512,
512,
512,
512,
512,
512,
512,
512,
512,
512
],
"bos_token_id": 0,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"ignore_attention_mask": false,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 4098,
"model_type": "longformer",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"onnx_export": false,
"pad_token_id": 1,
"sep_token_id": 2,
"torch_dtype": "float32",
"transformers_version": "4.35.0",
"type_vocab_size": 1,
"vocab_size": 60474
}