Upload DebertaV2ForSequenceClassification

config.json

@@ -1,25 +1,35 @@
 {
   "architectures": [
-    "BertForSequenceClassification"
+    "DebertaV2ForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
-  "layer_norm_eps": 1e-12,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
   "max_position_embeddings": 512,
-  "model_type": "bert",
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
   "torch_dtype": "float32",
   "transformers_version": "4.50.3",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "type_vocab_size": 0,
+  "vocab_size": 128100
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c317d5e476bc4aef2351b3ee2806d239e71b46d0dcd11537d3c42faa6abd6fc0
-size 133466376
+oid sha256:c820e443624116b416c3b87042bbfd41607bd59fe24fc2e25bf67dd12a666390
+size 567598552