Upload XLMRobertaForTokenClassification

config.json

@@ -1,12 +1,14 @@
 {
-  "activation": "gelu",
   "architectures": [
-    "DistilBertForTokenClassification"
+    "XLMRobertaForTokenClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "O",
     "1": "B-PER",
@@ -17,6 +19,7 @@
     "6": "I-LOC"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "B-LOC": 5,
     "B-ORG": 3,
@@ -26,17 +29,17 @@
     "I-PER": 2,
     "O": 0
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "output_past": true,
-  "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
-  "vocab_size": 28996
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f572fbd608d8a164db08678e4dfbd9181c345b8ccb7e52aab91627501e6736
-size 260797516
+oid sha256:d536b7577e4ad125ccd05b54e1c4a19f1563c3f9bc1136c28d555bbb3bcf0cb8
+size 1109857804