Upload XLMRobertaForSequenceClassification

config.json

@@ -1,11 +1,12 @@
 {
   "_name_or_path": "./sangapac-math-model",
   "architectures": [
-    "BertForSequenceClassification"
+    "XLMRobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -13,7 +14,9 @@
     "0": "LABEL_0",
     "1": "LABEL_1",
     "2": "LABEL_2",
-    "3": "LABEL_3"
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
@@ -21,19 +24,22 @@
     "LABEL_0": 0,
     "LABEL_1": 1,
     "LABEL_2": 2,
-    "LABEL_3": 3
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "output_past": true,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.46.2",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 250002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:301433b751ac4fb849bf30b12420c78ed039dd384d61fb384d113fc2147a73d9
-size 437964800
+oid sha256:d6249813a6f00098952e1ed83f3f374b2ced66cd8297f10271ec66841f3befe2
+size 1112217312