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

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "/mnt/sdb/stt/mata/models/ner_models/train/xlm-roberta-large-finetuned-conll03-english-hug-28-05-2024/xlm-roberta-large",
+  "_num_labels": 8,
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "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": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-LOC",
+    "2": "I-LOC",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-PERSON",
+    "6": "I-PERSON",
+    "7": "B-DATE",
+    "8": "I-DATE",
+    "9": "B-MONEY",
+    "10": "I-MONEY",
+    "11": "B-PERCENT",
+    "12": "I-PERCENT",
+    "13": "B-QUANTITY",
+    "14": "I-QUANTITY",
+    "15": "B-TIME",
+    "16": "I-TIME",
+    "17": "B-PRODUCT",
+    "18": "I-PRODUCT",
+    "19": "B-EVENT",
+    "20": "I-EVENT",
+    "21": "B-WORK_OF_ART",
+    "22": "I-WORK_OF_ART",
+    "23": "B-LANGUAGE",
+    "24": "I-LANGUAGE",
+    "25": "B-CARDINAL",
+    "26": "I-CARDINAL",
+    "27": "B-ORDINAL",
+    "28": "I-ORDINAL",
+    "29": "B-NORP",
+    "30": "I-NORP",
+    "31": "B-FACILITY",
+    "32": "I-FACILITY",
+    "33": "B-LAW",
+    "34": "I-LAW",
+    "35": "B-GPE",
+    "36": "I-GPE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-CARDINAL": 25,
+    "B-DATE": 7,
+    "B-EVENT": 19,
+    "B-FACILITY": 31,
+    "B-GPE": 35,
+    "B-LANGUAGE": 23,
+    "B-LAW": 33,
+    "B-LOC": 1,
+    "B-MONEY": 9,
+    "B-NORP": 29,
+    "B-ORDINAL": 27,
+    "B-ORG": 3,
+    "B-PERCENT": 11,
+    "B-PERSON": 5,
+    "B-PRODUCT": 17,
+    "B-QUANTITY": 13,
+    "B-TIME": 15,
+    "B-WORK_OF_ART": 21,
+    "I-CARDINAL": 26,
+    "I-DATE": 8,
+    "I-EVENT": 20,
+    "I-FACILITY": 32,
+    "I-GPE": 36,
+    "I-LANGUAGE": 24,
+    "I-LAW": 34,
+    "I-LOC": 2,
+    "I-MONEY": 10,
+    "I-NORP": 30,
+    "I-ORDINAL": 28,
+    "I-ORG": 4,
+    "I-PERCENT": 12,
+    "I-PERSON": 6,
+    "I-PRODUCT": 18,
+    "I-QUANTITY": 14,
+    "I-TIME": 16,
+    "I-WORK_OF_ART": 22,
+    "O": 0
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8046ee0fea5bf37918c5bf9bef09352f8c66865288b0f14a0a56c80e9c2e37a5
+size 2235563564

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}