Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,57 +1,30 @@
 {
-  "_num_labels": 9,
   "add_cross_attention": false,
   "architectures": [
-    "BertModel"
+    "XLMRobertaModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": null,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "directionality": "bidi",
   "dtype": "float32",
-  "eos_token_id": null,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 2,
-  "id2label": {
-    "0": "O",
-    "1": "B-MISC",
-    "2": "I-MISC",
-    "3": "B-PER",
-    "4": "I-PER",
-    "5": "B-ORG",
-    "6": "I-ORG",
-    "7": "B-LOC",
-    "8": "I-LOC"
-  },
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 4,
+  "intermediate_size": 4096,
   "is_decoder": false,
-  "label2id": {
-    "B-LOC": 7,
-    "B-MISC": 1,
-    "B-ORG": 5,
-    "B-PER": 3,
-    "I-LOC": 8,
-    "I-MISC": 2,
-    "I-ORG": 6,
-    "I-PER": 4,
-    "O": 0
-  },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 2,
-  "num_hidden_layers": 2,
-  "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "tie_word_embeddings": true,
   "transformers_version": "5.14.1",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 250002
 }

head.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b997354133d0cfdfa04d05e8243863b033a44341f20721c88956f52de8e3c28
-size 188
+oid sha256:b1a9bf6e91616aef3148f0d5df753b1a685de3a736053fc5fb6d0d47e2e4bf5f
+size 37068

metadata.json

@@ -1,9 +1,15 @@
 {
     "format_version": 2,
     "class_name": "TokenClassifier",
-    "model_name": "sshleifer/tiny-distilbert-base-cased",
+    "model_name": "xlm-roberta-large",
     "label_list": [
         "O",
+        "B-LOC",
+        "I-LOC",
+        "B-MISC",
+        "I-MISC",
+        "B-ORG",
+        "I-ORG",
         "B-PER",
         "I-PER"
     ],
@@ -12,7 +18,7 @@
     "license": "Fluke NC 1.0",
     "license_info": "Fluke NC 1.0",
     "model_args": {
-        "window_size": 508,
+        "window_size": 510,
         "overlap": 127,
         "repair_orphan_tags": true
     }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f95efa9968c82883b07e40f78d5b3844f6d333336bae8123f6ee0539f7eb5423
-size 240528
+oid sha256:4383c8f16be414e58347b9079fa4867c728ae798f52cd8383fdc8dd919b02933
+size 2239607176

tokenizer_config.json

@@ -1,15 +1,16 @@
 {
+  "add_prefix_space": true,
   "backend": "tokenizers",
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "is_local": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": true,
   "local_files_only": false,
-  "mask_token": "[MASK]",
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
 }