Update config.json

config.json

@@ -2,43 +2,12 @@
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
   "architectures": [
     "BartForConditionalGeneration"
   ],
-  "attention_dilation": [
-    1,
-    1,
-    1,
-    1,
-    1,
-    1,
-    1,
-    1,
-    1,
-    1,
-    1,
-    1
-  ],
   "attention_dropout": 0.0,
-  "attention_mode": "sliding_chunks",
   "attention_probs_dropout_prob": 0.0,
-  "attention_window": [
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512
-  ],
-  "autoregressive": false,
+  "attention_window": 1024,
   "bos_token_id": 0,
   "classif_dropout": 0.0,
   "d_model": 1024,
@@ -53,7 +22,6 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
-  "extra_pos_embeddings": 2,
   "gradient_checkpointing": false,
   "id2label": {
     "0": "LABEL_0",
@@ -70,23 +38,9 @@
   "max_decoder_position_embeddings": 1024,
   "max_encoder_position_embeddings": 16384,
   "model_type": "bart",
-  "normalize_before": false,
-  "normalize_embedding": true,
   "num_hidden_layers": 12,
   "output_past": false,
   "pad_token_id": 1,
   "prefix": " ",
-  "scale_embedding": false,
-  "static_position_embeddings": false,
-  "task_specific_params": {
-    "summarization": {
-      "early_stopping": true,
-      "length_penalty": 2.0,
-      "max_length": 142,
-      "min_length": 56,
-      "no_repeat_ngram_size": 3,
-      "num_beams": 4
-    }
-  },
   "vocab_size": 50265
 }