Upload DebertaV2ForSequenceClassification

config.json

@@ -1,13 +1,12 @@
 {
-  "_name_or_path": "LoneWolfgang/bert-for-japanese-twitter",
+  "_name_or_path": "globis-university/deberta-v3-japanese-large",
   "architectures": [
-    "BertForSequenceClassification"
+    "DebertaV2ForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.3,
-  "classifier_dropout": null,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.3,
-  "hidden_size": 768,
+  "hidden_dropout_prob": 0.2,
+  "hidden_size": 1024,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -16,7 +15,7 @@
     "4": "LABEL_4"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -24,17 +23,27 @@
     "LABEL_3": 3,
     "LABEL_4": 4
   },
-  "layer_norm_eps": 1e-12,
+  "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
   "torch_dtype": "float32",
   "transformers_version": "4.46.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 32000
+  "type_vocab_size": 0,
+  "vocab_size": 48000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bac0247dab998fbe858fa20ff823ce4659e4609cf81880b238568d19c448f244
-size 442508292
+oid sha256:42e38bcae631aeaeaec5e4234b44d5460ac9afc1693988bf04d1d03ea76b7637
+size 1412226948