Update config.json

config.json

@@ -1,31 +1,27 @@
 {
-    "architectures": [
-      "BigBirdForPreTraining"
-    ],
-    "attention_probs_dropout_prob": 0.1,
-    "attention_type": "block_sparse",
-    "block_size": 64,
-    "bos_token_id": 1,
-    "eos_token_id": 2,
-    "gradient_checkpointing": false,
-    "hidden_act": "gelu_new",
-    "hidden_dropout_prob": 0.1,
-    "hidden_size": 768,
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
-    "layer_norm_eps": 1e-12,
-    "max_position_embeddings": 4096,
-    "model_type": "big_bird",
-    "num_attention_heads": 12,
-    "num_hidden_layers": 6,
-    "num_random_blocks": 3,
-    "pad_token_id": 0,
-    "position_embedding_type": "absolute",
-    "rescale_embeddings": false,
-    "transformers_version": "4.4.0.dev0",
-    "type_vocab_size": 2,
-    "use_bias": true,
-    "use_cache": true,
-    "vocab_size": 50358
-  }
-  
+  "architectures": [
+    "LongformerForMaskedLM"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": 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,
+  "pad_token_id": 1,
+  "sep_token_id": 2,
+  "tokenizer_class": "LongformerTokenizer",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}