Update config.json

config.json

@@ -1,35 +1,33 @@
 {
-  "_name_or_path": "xlnet-base-cased",
-  "architectures": [
-    "XLNetForSequenceClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,  // Changed to match XLNet's hidden size for sequence classification
-  "id2label": {
-    "0": "non-severe",
-    "1": "severe"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "label2id": {
-    "non-severe": 0,
-    "severe": 1
-  },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "xlnet",  // Fixed typo in model_type
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "pad_token_id": 5,
-  "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
-  "torch_dtype": "float32",
-  "transformers_version": "4.21.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 32000  // Changed to match XLNet's vocab size
+    "architectures": [
+        "XLNetForSequenceClassification"
+    ],
+    "model_type": "xlnet",
+    "xlnet_config": {
+        "attn_type": "bi",
+        "bi_data": false,
+        "clamp_len": -1,
+        "d_head": 64,
+        "d_inner": 4096,
+        "d_model": 768,
+        "dropout": 0.1,
+        "end_n_top": 5,
+        "initializer_range": 0.02,
+        "layer_norm_eps": 1e-12,
+        "mem_len": null,
+        "n_head": 12,
+        "n_layer": 12,
+        "reuse_len": null,
+        "same_length": false,
+        "start_n_top": 5,
+        "summary_activation": "tanh",
+        "summary_last_dropout": 0.1,
+        "summary_type": "last",
+        "summary_use_proj": true,
+        "vocab_size": 32000
+    },
+    "num_labels": 2,
+    "summary_type": "last",
+    "summary_use_proj": true,
+    "vocab_size": 32000
 }