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
+luo-pos/tokenizer.json filter=lfs diff=lfs merge=lfs -text

luo-pos/config.json

@@ -0,0 +1,259 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": ",",
+    "1": ".",
+    "2": "ABBR",
+    "3": "AD V",
+    "4": "ADJ",
+    "5": "ADO",
+    "6": "ADP",
+    "7": "ADV",
+    "8": "ADp",
+    "9": "ADv",
+    "10": "AP",
+    "11": "AUX",
+    "12": "Aadv",
+    "13": "Ad",
+    "14": "AdJ",
+    "15": "AdV",
+    "16": "Adcv",
+    "17": "Adj",
+    "18": "Adj+NN+Adj",
+    "19": "Adj+Prep",
+    "20": "Adj+V",
+    "21": "Adj.",
+    "22": "Adp",
+    "23": "Adsv",
+    "24": "Adv",
+    "25": "Adv+NN",
+    "26": "Adv+V",
+    "27": "Adv.",
+    "28": "Aj",
+    "29": "C",
+    "30": "CO",
+    "31": "COJ",
+    "32": "CONG",
+    "33": "CONJ",
+    "34": "CONJ.",
+    "35": "Cinj",
+    "36": "Coinj",
+    "37": "Con",
+    "38": "ConJ",
+    "39": "Conj",
+    "40": "Conj+NN",
+    "41": "Conj+NN+Adj",
+    "42": "Conj+PRON",
+    "43": "Conj+V",
+    "44": "Conj.",
+    "45": "D",
+    "46": "DET",
+    "47": "DeT",
+    "48": "Der",
+    "49": "Det",
+    "50": "Det+Prep",
+    "51": "Det.",
+    "52": "DetV",
+    "53": "Detr",
+    "54": "INTENS",
+    "55": "INTER",
+    "56": "MM",
+    "57": "N",
+    "58": "N N",
+    "59": "NN",
+    "60": "NN /ADJ",
+    "61": "NN+Adj",
+    "62": "NN+Conj",
+    "63": "NN+Det",
+    "64": "NN+Prep",
+    "65": "NNADP",
+    "66": "NNN",
+    "67": "NNV",
+    "68": "NU",
+    "69": "NU M",
+    "70": "NUM",
+    "71": "NUMB",
+    "72": "NUMM",
+    "73": "NUm",
+    "74": "Nn",
+    "75": "Num",
+    "76": "P",
+    "77": "PART",
+    "78": "PR",
+    "79": "PRE",
+    "80": "PRO",
+    "81": "PROIN",
+    "82": "PRON",
+    "83": "PRONV",
+    "84": "PROn",
+    "85": "PU",
+    "86": "PUCT",
+    "87": "PUNCT",
+    "88": "PUNCt",
+    "89": "PUNT",
+    "90": "Prep",
+    "91": "Prep+NN",
+    "92": "Pron",
+    "93": "Punct",
+    "94": "QADP",
+    "95": "S",
+    "96": "SPEC",
+    "97": "V",
+    "98": "V+Adv",
+    "99": "V+NN",
+    "100": "VADP",
+    "101": "VV",
+    "102": "X",
+    "103": "XX",
+    "104": "aAdj",
+    "105": "adj",
+    "106": "adp",
+    "107": "conj",
+    "108": "conj.",
+    "109": "cv",
+    "110": "nn",
+    "111": "punct",
+    "112": "v",
+    "113": "x"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    ",": 0,
+    ".": 1,
+    "ABBR": 2,
+    "AD V": 3,
+    "ADJ": 4,
+    "ADO": 5,
+    "ADP": 6,
+    "ADV": 7,
+    "ADp": 8,
+    "ADv": 9,
+    "AP": 10,
+    "AUX": 11,
+    "Aadv": 12,
+    "Ad": 13,
+    "AdJ": 14,
+    "AdV": 15,
+    "Adcv": 16,
+    "Adj": 17,
+    "Adj+NN+Adj": 18,
+    "Adj+Prep": 19,
+    "Adj+V": 20,
+    "Adj.": 21,
+    "Adp": 22,
+    "Adsv": 23,
+    "Adv": 24,
+    "Adv+NN": 25,
+    "Adv+V": 26,
+    "Adv.": 27,
+    "Aj": 28,
+    "C": 29,
+    "CO": 30,
+    "COJ": 31,
+    "CONG": 32,
+    "CONJ": 33,
+    "CONJ.": 34,
+    "Cinj": 35,
+    "Coinj": 36,
+    "Con": 37,
+    "ConJ": 38,
+    "Conj": 39,
+    "Conj+NN": 40,
+    "Conj+NN+Adj": 41,
+    "Conj+PRON": 42,
+    "Conj+V": 43,
+    "Conj.": 44,
+    "D": 45,
+    "DET": 46,
+    "DeT": 47,
+    "Der": 48,
+    "Det": 49,
+    "Det+Prep": 50,
+    "Det.": 51,
+    "DetV": 52,
+    "Detr": 53,
+    "INTENS": 54,
+    "INTER": 55,
+    "MM": 56,
+    "N": 57,
+    "N N": 58,
+    "NN": 59,
+    "NN /ADJ": 60,
+    "NN+Adj": 61,
+    "NN+Conj": 62,
+    "NN+Det": 63,
+    "NN+Prep": 64,
+    "NNADP": 65,
+    "NNN": 66,
+    "NNV": 67,
+    "NU": 68,
+    "NU M": 69,
+    "NUM": 70,
+    "NUMB": 71,
+    "NUMM": 72,
+    "NUm": 73,
+    "Nn": 74,
+    "Num": 75,
+    "P": 76,
+    "PART": 77,
+    "PR": 78,
+    "PRE": 79,
+    "PRO": 80,
+    "PROIN": 81,
+    "PRON": 82,
+    "PRONV": 83,
+    "PROn": 84,
+    "PU": 85,
+    "PUCT": 86,
+    "PUNCT": 87,
+    "PUNCt": 88,
+    "PUNT": 89,
+    "Prep": 90,
+    "Prep+NN": 91,
+    "Pron": 92,
+    "Punct": 93,
+    "QADP": 94,
+    "S": 95,
+    "SPEC": 96,
+    "V": 97,
+    "V+Adv": 98,
+    "V+NN": 99,
+    "VADP": 100,
+    "VV": 101,
+    "X": 102,
+    "XX": 103,
+    "aAdj": 104,
+    "adj": 105,
+    "adp": 106,
+    "conj": 107,
+    "conj.": 108,
+    "cv": 109,
+    "nn": 110,
+    "punct": 111,
+    "v": 112,
+    "x": 113
+  },
+  "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",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

luo-pos/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e41d6f76bd270b6936d3550063951ea68a6e258150e892072a230840f0d2f610
+size 2235879264

luo-pos/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
+  }
+}

luo-pos/tokenizer.json

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

luo-pos/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "unk_token": "<unk>"
+}

luo-pos/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402c67eb466751ce81177fdf50cf51e9adba27c7ff752a31707a0743a6a4c1d4
+size 5432