Text Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
Generated from Trainer
language-identification
text-embeddings-inference
Instructions to use polyglot-tagger/multilabel-language-identification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use polyglot-tagger/multilabel-language-identification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="polyglot-tagger/multilabel-language-identification")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("polyglot-tagger/multilabel-language-identification") model = AutoModelForSequenceClassification.from_pretrained("polyglot-tagger/multilabel-language-identification", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 2500
Browse files- config.json +245 -0
- model.safetensors +3 -0
- runs/Apr19_06-28-23_magic01/events.out.tfevents.1776594503.magic01 +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,245 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "EN",
|
| 16 |
+
"1": "ES",
|
| 17 |
+
"2": "FR",
|
| 18 |
+
"3": "DE",
|
| 19 |
+
"4": "IT",
|
| 20 |
+
"5": "PT",
|
| 21 |
+
"6": "NL",
|
| 22 |
+
"7": "VI",
|
| 23 |
+
"8": "TR",
|
| 24 |
+
"9": "LA",
|
| 25 |
+
"10": "ID",
|
| 26 |
+
"11": "MS",
|
| 27 |
+
"12": "AF",
|
| 28 |
+
"13": "SQ",
|
| 29 |
+
"14": "IS",
|
| 30 |
+
"15": "NO",
|
| 31 |
+
"16": "SV",
|
| 32 |
+
"17": "DA",
|
| 33 |
+
"18": "FI",
|
| 34 |
+
"19": "HU",
|
| 35 |
+
"20": "PL",
|
| 36 |
+
"21": "CS",
|
| 37 |
+
"22": "RO",
|
| 38 |
+
"23": "RU",
|
| 39 |
+
"24": "BG",
|
| 40 |
+
"25": "UK",
|
| 41 |
+
"26": "SR",
|
| 42 |
+
"27": "BE",
|
| 43 |
+
"28": "KK",
|
| 44 |
+
"29": "MK",
|
| 45 |
+
"30": "MN",
|
| 46 |
+
"31": "ZH",
|
| 47 |
+
"32": "JA",
|
| 48 |
+
"33": "KO",
|
| 49 |
+
"34": "HI",
|
| 50 |
+
"35": "UR",
|
| 51 |
+
"36": "BN",
|
| 52 |
+
"37": "TA",
|
| 53 |
+
"38": "TE",
|
| 54 |
+
"39": "MR",
|
| 55 |
+
"40": "GU",
|
| 56 |
+
"41": "KN",
|
| 57 |
+
"42": "ML",
|
| 58 |
+
"43": "PA",
|
| 59 |
+
"44": "AS",
|
| 60 |
+
"45": "OR",
|
| 61 |
+
"46": "AR",
|
| 62 |
+
"47": "FA",
|
| 63 |
+
"48": "PS",
|
| 64 |
+
"49": "SD",
|
| 65 |
+
"50": "UG",
|
| 66 |
+
"51": "EL",
|
| 67 |
+
"52": "HE",
|
| 68 |
+
"53": "YI",
|
| 69 |
+
"54": "HY",
|
| 70 |
+
"55": "KA",
|
| 71 |
+
"56": "AM",
|
| 72 |
+
"57": "KM",
|
| 73 |
+
"58": "LO",
|
| 74 |
+
"59": "MY",
|
| 75 |
+
"60": "TH",
|
| 76 |
+
"61": "SI",
|
| 77 |
+
"62": "BO",
|
| 78 |
+
"63": "DV",
|
| 79 |
+
"64": "TI",
|
| 80 |
+
"65": "SW",
|
| 81 |
+
"66": "EU",
|
| 82 |
+
"67": "TL",
|
| 83 |
+
"68": "XH",
|
| 84 |
+
"69": "CA",
|
| 85 |
+
"70": "GL",
|
| 86 |
+
"71": "OC",
|
| 87 |
+
"72": "BR",
|
| 88 |
+
"73": "GA",
|
| 89 |
+
"74": "GD",
|
| 90 |
+
"75": "CY",
|
| 91 |
+
"76": "SCO",
|
| 92 |
+
"77": "BS",
|
| 93 |
+
"78": "HR",
|
| 94 |
+
"79": "SL",
|
| 95 |
+
"80": "SK",
|
| 96 |
+
"81": "ET",
|
| 97 |
+
"82": "LV",
|
| 98 |
+
"83": "LT",
|
| 99 |
+
"84": "EO",
|
| 100 |
+
"85": "JV",
|
| 101 |
+
"86": "MG",
|
| 102 |
+
"87": "OM",
|
| 103 |
+
"88": "SO",
|
| 104 |
+
"89": "SU",
|
| 105 |
+
"90": "UZ",
|
| 106 |
+
"91": "KU",
|
| 107 |
+
"92": "CKB",
|
| 108 |
+
"93": "NE",
|
| 109 |
+
"94": "MT",
|
| 110 |
+
"95": "LB",
|
| 111 |
+
"96": "RM",
|
| 112 |
+
"97": "TT",
|
| 113 |
+
"98": "KY",
|
| 114 |
+
"99": "TG",
|
| 115 |
+
"100": "BA",
|
| 116 |
+
"101": "YO",
|
| 117 |
+
"102": "ZU",
|
| 118 |
+
"103": "NY",
|
| 119 |
+
"104": "CE"
|
| 120 |
+
},
|
| 121 |
+
"initializer_range": 0.02,
|
| 122 |
+
"intermediate_size": 3072,
|
| 123 |
+
"is_decoder": false,
|
| 124 |
+
"label2id": {
|
| 125 |
+
"AF": 12,
|
| 126 |
+
"AM": 56,
|
| 127 |
+
"AR": 46,
|
| 128 |
+
"AS": 44,
|
| 129 |
+
"BA": 100,
|
| 130 |
+
"BE": 27,
|
| 131 |
+
"BG": 24,
|
| 132 |
+
"BN": 36,
|
| 133 |
+
"BO": 62,
|
| 134 |
+
"BR": 72,
|
| 135 |
+
"BS": 77,
|
| 136 |
+
"CA": 69,
|
| 137 |
+
"CE": 104,
|
| 138 |
+
"CKB": 92,
|
| 139 |
+
"CS": 21,
|
| 140 |
+
"CY": 75,
|
| 141 |
+
"DA": 17,
|
| 142 |
+
"DE": 3,
|
| 143 |
+
"DV": 63,
|
| 144 |
+
"EL": 51,
|
| 145 |
+
"EN": 0,
|
| 146 |
+
"EO": 84,
|
| 147 |
+
"ES": 1,
|
| 148 |
+
"ET": 81,
|
| 149 |
+
"EU": 66,
|
| 150 |
+
"FA": 47,
|
| 151 |
+
"FI": 18,
|
| 152 |
+
"FR": 2,
|
| 153 |
+
"GA": 73,
|
| 154 |
+
"GD": 74,
|
| 155 |
+
"GL": 70,
|
| 156 |
+
"GU": 40,
|
| 157 |
+
"HE": 52,
|
| 158 |
+
"HI": 34,
|
| 159 |
+
"HR": 78,
|
| 160 |
+
"HU": 19,
|
| 161 |
+
"HY": 54,
|
| 162 |
+
"ID": 10,
|
| 163 |
+
"IS": 14,
|
| 164 |
+
"IT": 4,
|
| 165 |
+
"JA": 32,
|
| 166 |
+
"JV": 85,
|
| 167 |
+
"KA": 55,
|
| 168 |
+
"KK": 28,
|
| 169 |
+
"KM": 57,
|
| 170 |
+
"KN": 41,
|
| 171 |
+
"KO": 33,
|
| 172 |
+
"KU": 91,
|
| 173 |
+
"KY": 98,
|
| 174 |
+
"LA": 9,
|
| 175 |
+
"LB": 95,
|
| 176 |
+
"LO": 58,
|
| 177 |
+
"LT": 83,
|
| 178 |
+
"LV": 82,
|
| 179 |
+
"MG": 86,
|
| 180 |
+
"MK": 29,
|
| 181 |
+
"ML": 42,
|
| 182 |
+
"MN": 30,
|
| 183 |
+
"MR": 39,
|
| 184 |
+
"MS": 11,
|
| 185 |
+
"MT": 94,
|
| 186 |
+
"MY": 59,
|
| 187 |
+
"NE": 93,
|
| 188 |
+
"NL": 6,
|
| 189 |
+
"NO": 15,
|
| 190 |
+
"NY": 103,
|
| 191 |
+
"OC": 71,
|
| 192 |
+
"OM": 87,
|
| 193 |
+
"OR": 45,
|
| 194 |
+
"PA": 43,
|
| 195 |
+
"PL": 20,
|
| 196 |
+
"PS": 48,
|
| 197 |
+
"PT": 5,
|
| 198 |
+
"RM": 96,
|
| 199 |
+
"RO": 22,
|
| 200 |
+
"RU": 23,
|
| 201 |
+
"SCO": 76,
|
| 202 |
+
"SD": 49,
|
| 203 |
+
"SI": 61,
|
| 204 |
+
"SK": 80,
|
| 205 |
+
"SL": 79,
|
| 206 |
+
"SO": 88,
|
| 207 |
+
"SQ": 13,
|
| 208 |
+
"SR": 26,
|
| 209 |
+
"SU": 89,
|
| 210 |
+
"SV": 16,
|
| 211 |
+
"SW": 65,
|
| 212 |
+
"TA": 37,
|
| 213 |
+
"TE": 38,
|
| 214 |
+
"TG": 99,
|
| 215 |
+
"TH": 60,
|
| 216 |
+
"TI": 64,
|
| 217 |
+
"TL": 67,
|
| 218 |
+
"TR": 8,
|
| 219 |
+
"TT": 97,
|
| 220 |
+
"UG": 50,
|
| 221 |
+
"UK": 25,
|
| 222 |
+
"UR": 35,
|
| 223 |
+
"UZ": 90,
|
| 224 |
+
"VI": 7,
|
| 225 |
+
"XH": 68,
|
| 226 |
+
"YI": 53,
|
| 227 |
+
"YO": 101,
|
| 228 |
+
"ZH": 31,
|
| 229 |
+
"ZU": 102
|
| 230 |
+
},
|
| 231 |
+
"layer_norm_eps": 1e-05,
|
| 232 |
+
"max_position_embeddings": 514,
|
| 233 |
+
"model_type": "xlm-roberta",
|
| 234 |
+
"num_attention_heads": 12,
|
| 235 |
+
"num_hidden_layers": 12,
|
| 236 |
+
"output_past": true,
|
| 237 |
+
"pad_token_id": 1,
|
| 238 |
+
"position_embedding_type": "absolute",
|
| 239 |
+
"problem_type": "multi_label_classification",
|
| 240 |
+
"tie_word_embeddings": true,
|
| 241 |
+
"transformers_version": "5.5.4",
|
| 242 |
+
"type_vocab_size": 1,
|
| 243 |
+
"use_cache": false,
|
| 244 |
+
"vocab_size": 250002
|
| 245 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9dbcf46fc300daaf0b5b3bb553b706e2b981f62b9962a8b738e2df5ea84843ea
|
| 3 |
+
size 1112521812
|
runs/Apr19_06-28-23_magic01/events.out.tfevents.1776594503.magic01
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60092997bc1ce05b6fe37345828798bc67e7d31a500862adbbe386b85a6ccf37
|
| 3 |
+
size 12862
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c58abd36bff753b4801af7c72bd4232a77a6af17c644afb347fc931f0c45cedd
|
| 3 |
+
size 5201
|