| { |
| "_name_or_path": "/gpfs/projects/bsc88/temutauro/apoc/longformer//results/longformer/ca_short/NNODES_8_GRADIENT-ACCUM_1_steps_65000_lr_0.00003_seed_1_DATA-AGGREGATION_SEPARATE_date_22-12-05_ID_315326/output/longformer-base-4096", |
| "architectures": [ |
| "LongformerForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "attention_window": [ |
| 512, |
| 512, |
| 512, |
| 512, |
| 512, |
| 512, |
| 512, |
| 512, |
| 512, |
| 512, |
| 512, |
| 512 |
| ], |
| "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-05, |
| "max_position_embeddings": 4098, |
| "model_type": "longformer", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "pad_token_id": 1, |
| "position_embedding_type": "absolute", |
| "sep_token_id": 2, |
| "torch_dtype": "float32", |
| "transformers_version": "4.20.1", |
| "type_vocab_size": 1, |
| "use_cache": true, |
| "vocab_size": 50262 |
| } |
|
|
