update config

config.json

@@ -1,32 +1,27 @@
 {
-  "_name_or_path": "google/t5-v1_1-base",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "T5ForConditionalGeneration"
+    "BertForHighlightPrediction"
   ],
-  "classifier_dropout": 0.0,
-  "d_ff": 2048,
-  "d_kv": 64,
-  "d_model": 768,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
-  "dropout_rate": 0.1,
-  "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
-  "initializer_factor": 1.0,
-  "is_encoder_decoder": true,
-  "is_gated_act": true,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "t5",
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
-  "output_past": true,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "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": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_hidden_states": true,
   "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.33.1",
+  "transformers_version": "4.20.1",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 32128
+  "vocab_size": 30522
 }