Add new SentenceTransformer model.

.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
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false
+}

README.md

@@ -0,0 +1,94 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+
+---
+
+# indiejoseph/bert-cantonese-sts
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+<!--- Describe your model here -->
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('indiejoseph/bert-cantonese-sts')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('indiejoseph/bert-cantonese-sts')
+model = AutoModel.from_pretrained('indiejoseph/bert-cantonese-sts')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=indiejoseph/bert-cantonese-sts)
+
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

added_tokens.json

@@ -0,0 +1,1467 @@
+{
+  "㚻": 21615,
+  "㜺": 22407,
+  "㞗": 21701,
+  "㞘": 22096,
+  "㩒": 21141,
+  "㬎": 21853,
+  "㴓": 22011,
+  "㶞": 22576,
+  "㷫": 21621,
+  "㹢": 22294,
+  "㹴": 21573,
+  "㺢": 22293,
+  "㻋": 22034,
+  "㻗": 22485,
+  "䃟": 21402,
+  "䓪": 21509,
+  "䓬": 22380,
+  "䥑": 21314,
+  "䴉": 22131,
+  "䶄": 22591,
+  "䶮": 22228,
+  "丏": 22210,
+  "乭": 21894,
+  "乸": 21339,
+  "亶": 21411,
+  "亹": 22209,
+  "仡": 21161,
+  "仫": 22198,
+  "仵": 22446,
+  "伋": 21798,
+  "伷": 21932,
+  "佉": 22206,
+  "佮": 22468,
+  "佺": 22396,
+  "佾": 21841,
+  "侂": 21311,
+  "侔": 22023,
+  "侘": 22232,
+  "俁": 21842,
+  "俅": 22539,
+  "俣": 21190,
+  "俵": 21504,
+  "俶": 21661,
+  "倣": 21421,
+  "倧": 22346,
+  "倮": 21955,
+  "倻": 21972,
+  "偲": 21625,
+  "傈": 21942,
+  "傕": 21372,
+  "僆": 22181,
+  "僉": 21887,
+  "僊": 21703,
+  "僞": 21510,
+  "僰": 22441,
+  "僳": 21943,
+  "儁": 21375,
+  "儇": 21639,
+  "儔": 21967,
+  "儸": 21950,
+  "儺": 22508,
+  "兗": 21155,
+  "兪": 22321,
+  "冑": 21306,
+  "冚": 21249,
+  "冧": 21283,
+  "冫": 22410,
+  "冴": 21399,
+  "凖": 22443,
+  "凫": 21833,
+  "凵": 22229,
+  "凼": 22371,
+  "刋": 22394,
+  "剡": 22377,
+  "劄": 21333,
+  "劻": 22046,
+  "勅": 21939,
+  "勔": 22360,
+  "勗": 21581,
+  "勣": 21795,
+  "勰": 22078,
+  "勱": 22055,
+  "勲": 21865,
+  "勷": 21675,
+  "匂": 22185,
+  "匏": 21455,
+  "匚": 22419,
+  "匸": 22488,
+  "卌": 21148,
+  "卐": 22517,
+  "卬": 22285,
+  "卹": 21320,
+  "卽": 21292,
+  "厏": 22559,
+  "厓": 22151,
+  "厠": 22329,
+  "厰": 22383,
+  "叄": 22298,
+  "吔": 21215,
+  "吲": 21547,
+  "吿": 21202,
+  "呑": 21533,
+  "呔": 21901,
+  "呪": 21910,
+  "咇": 22004,
+  "哙": 22578,
+  "哚": 22213,
+  "唂": 21759,
+  "唞": 21514,
+  "唥": 21279,
+  "唨": 22094,
+  "唪": 21278,
+  "唻": 22170,
+  "啹": 22054,
+  "喐": 21599,
+  "喥": 21534,
+  "喦": 22255,
+  "喼": 21786,
+  "喾": 21692,
+  "嗉": 21130,
+  "嗌": 21128,
+  "嗩": 22496,
+  "嗮": 21144,
+  "嗱": 21216,
+  "嘏": 22147,
+  "嘥": 21218,
+  "噉": 21133,
+  "噍": 21529,
+  "噏": 21530,
+  "噚": 22063,
+  "噝": 22028,
+  "噣": 22589,
+  "噯": 21214,
+  "噲": 21964,
+  "嚈": 22033,
+  "嚙": 21528,
+  "嚜": 21355,
+  "嚡": 22572,
+  "嚤": 21169,
+  "嚦": 22424,
+  "嚫": 21600,
+  "嚳": 22006,
+  "嚿": 21245,
+  "囓": 21914,
+  "囘": 21686,
+  "圀": 22256,
+  "圉": 22240,
+  "圮": 22241,
+  "圯": 21927,
+  "圹": 22237,
+  "坌": 21989,
+  "坧": 22416,
+  "坩": 21731,
+  "坭": 21522,
+  "坻": 22191,
+  "垌": 21937,
+  "垓": 21271,
+  "垟": 22582,
+  "垧": 22465,
+  "垸": 21769,
+  "垻": 21928,
+  "埈": 22190,
+  "埐": 22376,
+  "埒": 21971,
+  "埜": 21921,
+  "埞": 21377,
+  "埡": 22352,
+  "埭": 21844,
+  "埲": 21835,
+  "埴": 21542,
+  "堉": 22068,
+  "堊": 21720,
+  "堝": 21732,
+  "堞": 21724,
+  "堠": 22402,
+  "塙": 21505,
+  "塡": 22124,
+  "塱": 21152,
+  "塲": 21714,
+  "塹": 21519,
+  "塽": 21926,
+  "墬": 22177,
+  "壎": 21765,
+  "壙": 21793,
+  "壠": 22276,
+  "壱": 21444,
+  "夂": 22509,
+  "夤": 22203,
+  "夨": 22359,
+  "夬": 22413,
+  "奀": 21913,
+  "奭": 21772,
+  "妫": 21941,
+  "姈": 22592,
+  "姮": 22274,
+  "姵": 22105,
+  "娸": 21851,
+  "媯": 22378,
+  "媺": 21407,
+  "嫗": 21503,
+  "嫪": 21396,
+  "嫺": 22164,
+  "嫿": 21291,
+  "嬈": 22277,
+  "嬋": 21936,
+  "嬲": 21211,
+  "孋": 22518,
+  "孭": 21532,
+  "孲": 21467,
+  "孻": 21452,
+  "宀": 21655,
+  "宍": 21898,
+  "寔": 21349,
+  "寳": 21734,
+  "尅": 21741,
+  "尐": 21217,
+  "尙": 21521,
+  "尢": 21242,
+  "尪": 22104,
+  "屘": 21883,
+  "屙": 21426,
+  "屭": 22471,
+  "屻": 22021,
+  "岃": 22533,
+  "峄": 22403,
+  "峠": 21134,
+  "崃": 22482,
+  "崟": 22356,
+  "崢": 21248,
+  "崤": 21984,
+  "嵗": 21713,
+  "嵴": 21722,
+  "嶗": 22433,
+  "嶝": 22411,
+  "嶠": 21536,
+  "嶷": 21969,
+  "嶸": 22340,
+  "巂": 22267,
+  "巋": 22490,
+  "帙": 22244,
+  "幗": 21592,
+  "幪": 21228,
+  "幷": 22058,
+  "庑": 21461,
+  "庥": 22372,
+  "庯": 22431,
+  "廄": 21172,
+  "廆": 21499,
+  "廍": 21993,
+  "廐": 22261,
+  "廙": 22150,
+  "廡": 21740,
+  "廨": 21325,
+  "廩": 21440,
+  "廪": 21264,
+  "廸": 21863,
+  "廻": 21327,
+  "廼": 22521,
+  "弇": 21412,
+  "弐": 22473,
+  "弢": 22350,
+  "彊": 21312,
+  "彔": 22444,
+  "彖": 21157,
+  "彘": 21255,
+  "彜": 22252,
+  "彡": 21448,
+  "彣": 22174,
+  "徂": 21408,
+  "徫": 21871,
+  "徭": 21872,
+  "忞": 21464,
+  "怛": 22219,
+  "恂": 22212,
+  "恊": 21775,
+  "恽": 21459,
+  "悝": 22342,
+  "惗": 21885,
+  "惣": 21403,
+  "惲": 21525,
+  "惻": 21329,
+  "愃": 22070,
+  "愎": 21506,
+  "愔": 21999,
+  "愨": 21379,
+  "愬": 21330,
+  "愴": 21821,
+  "慇": 22357,
+  "慜": 22553,
+  "慤": 21609,
+  "憓": 21420,
+  "憙": 22367,
+  "懌": 21884,
+  "懽": 22035,
+  "戇": 21524,
+  "戉": 21987,
+  "戔": 21603,
+  "戙": 21628,
+  "戢": 21137,
+  "戥": 21439,
+  "戩": 21864,
+  "戯": 21648,
+  "扞": 22000,
+  "扺": 22214,
+  "抌": 21537,
+  "抺": 21469,
+  "拃": 21288,
+  "拏": 21757,
+  "拶": 21651,
+  "挐": 21659,
+  "挿": 21447,
+  "捜": 21647,
+  "捫": 21165,
+  "捹": 21435,
+  "捽": 21540,
+  "掄": 22439,
+  "掕": 21225,
+  "掟": 21234,
+  "掹": 21381,
+  "掾": 21405,
+  "揈": 21869,
+  "揞": 21991,
+  "揼": 21416,
+  "揾": 21224,
+  "搆": 21173,
+  "搣": 22183,
+  "搦": 21388,
+  "搧": 22012,
+  "搲": 21992,
+  "搾": 21847,
+  "摑": 21918,
+  "摭": 21970,
+  "摱": 21568,
+  "摶": 21596,
+  "摷": 22196,
+  "撘": 22250,
+  "撣": 21748,
+  "撳": 21142,
+  "撾": 21688,
+  "擧": 21538,
+  "擸": 22370,
+  "攆": 22408,
+  "攋": 21179,
+  "攰": 21390,
+  "攴": 22330,
+  "攷": 21129,
+  "斉": 21543,
+  "斕": 22347,
+  "旄": 22279,
+  "旉": 21788,
+  "旒": 22339,
+  "旚": 21770,
+  "旛": 22186,
+  "旣": 21685,
+  "旯": 21199,
+  "旼": 21886,
+  "昃": 21762,
+  "昑": 22069,
+  "昚": 21450,
+  "昞": 21299,
+  "昪": 21583,
+  "昫": 21975,
+  "昰": 21276,
+  "昺": 21275,
+  "晄": 22188,
+  "晈": 22355,
+  "晧": 22464,
+  "暎": 21297,
+  "暘": 21177,
+  "暠": 21401,
+  "暦": 22362,
+  "曌": 22022,
+  "曩": 22281,
+  "曱": 21345,
+  "曷": 21611,
+  "曺": 21771,
+  "曽": 22322,
+  "朊": 22292,
+  "朏": 21231,
+  "朶": 22472,
+  "杘": 21867,
+  "杧": 22385,
+  "杲": 21781,
+  "枓": 21498,
+  "枞": 22266,
+  "柊": 21938,
+  "柙": 22192,
+  "柝": 21681,
+  "柰": 21438,
+  "柷": 21733,
+  "栢": 21269,
+  "栱": 22039,
+  "栲": 21149,
+  "栴": 22502,
+  "桄": 22269,
+  "桕": 21665,
+  "桫": 21905,
+  "桴": 21976,
+  "桷": 22037,
+  "梔": 21451,
+  "梘": 21387,
+  "梠": 21855,
+  "梣": 22451,
+  "棐": 21500,
+  "棓": 22161,
+  "棨": 22180,
+  "棻": 21210,
+  "椏": 22216,
+  "椤": 22060,
+  "椥": 22320,
+  "椴": 22373,
+  "楙": 22008,
+  "楢": 21766,
+  "楯": 21180,
+  "榊": 21957,
+  "榎": 21513,
+  "榘": 21678,
+  "榣": 22436,
+  "榧": 22247,
+  "槊": 21303,
+  "槙": 21654,
+  "槨": 22384,
+  "樅": 22040,
+  "樋": 21512,
+  "樖": 21219,
+  "樗": 21239,
+  "樘": 21580,
+  "樛": 22525,
+  "樨": 21836,
+  "樴": 21796,
+  "橈": 22409,
+  "橚": 21497,
+  "橛": 21226,
+  "檠": 22086,
+  "檨": 22420,
+  "櫈": 21468,
+  "櫓": 21579,
+  "櫟": 21558,
+  "櫳": 21502,
+  "欅": 22513,
+  "欏": 21906,
+  "欤": 21755,
+  "歟": 21963,
+  "歿": 21601,
+  "殂": 21398,
+  "殄": 21548,
+  "殛": 22119,
+  "殮": 21689,
+  "殻": 21690,
+  "毌": 21822,
+  "毐": 21397,
+  "毖": 21589,
+  "毬": 21571,
+  "氂": 21262,
+  "氕": 21475,
+  "氘": 21476,
+  "氚": 21479,
+  "氩": 21470,
+  "氬": 22146,
+  "氼": 22392,
+  "汊": 21768,
+  "汚": 21649,
+  "汜": 21373,
+  "汭": 21944,
+  "沆": 21705,
+  "沊": 21627,
+  "沔": 21663,
+  "沚": 21909,
+  "沩": 22199,
+  "泂": 21916,
+  "泅": 21253,
+  "泚": 21334,
+  "洎": 21756,
+  "洢": 22084,
+  "洧": 21591,
+  "洭": 22435,
+  "洺": 21787,
+  "浈": 21837,
+  "浍": 22049,
+  "浛": 21812,
+  "浞": 21791,
+  "浠": 21549,
+  "涑": 22550,
+  "淏": 21233,
+  "淛": 21382,
+  "淝": 21272,
+  "淥": 22111,
+  "淯": 21947,
+  "淸": 21227,
+  "渌": 22470,
+  "渕": 21826,
+  "渟": 22227,
+  "湉": 21432,
+  "湎": 22391,
+  "湓": 22226,
+  "湜": 21815,
+  "湞": 21811,
+  "湣": 22042,
+  "湴": 21739,
+  "湼": 22366,
+  "溆": 21244,
+  "溦": 22249,
+  "滉": 21456,
+  "滎": 21445,
+  "滏": 22537,
+  "滘": 21266,
+  "滹": 22301,
+  "漖": 22184,
+  "漚": 22453,
+  "漼": 21945,
+  "潁": 21616,
+  "潯": 21828,
+  "潽": 21296,
+  "澁": 22179,
+  "澂": 21175,
+  "澇": 21282,
+  "澌": 21742,
+  "澔": 21195,
+  "澠": 21959,
+  "澪": 21535,
+  "澯": 22159,
+  "澶": 21684,
+  "濉": 22287,
+  "濊": 22504,
+  "濞": 21919,
+  "濰": 21974,
+  "濶": 21880,
+  "瀍": 22369,
+  "瀦": 22501,
+  "灃": 21434,
+  "灕": 21940,
+  "灤": 21176,
+  "炆": 21630,
+  "炘": 21232,
+  "炟": 22100,
+  "炤": 22139,
+  "烚": 21717,
+  "烜": 21995,
+  "烝": 22101,
+  "烱": 21978,
+  "烴": 21477,
+  "烺": 21174,
+  "焌": 21268,
+  "焓": 21931,
+  "煇": 21404,
+  "煚": 22052,
+  "煠": 22556,
+  "煬": 21414,
+  "熜": 21814,
+  "熲": 21929,
+  "熺": 21790,
+  "燏": 22202,
+  "燐": 22197,
+  "燬": 21516,
+  "燶": 21881,
+  "燾": 21300,
+  "爨": 21911,
+  "爿": 22299,
+  "牀": 21290,
+  "牁": 22462,
+  "牂": 22278,
+  "牖": 22231,
+  "牘": 21711,
+  "犂": 22343,
+  "犛": 22030,
+  "犰": 21715,
+  "狁": 22515,
+  "狍": 21954,
+  "狓": 22295,
+  "狛": 22566,
+  "狳": 21716,
+  "狷": 22157,
+  "猁": 22201,
+  "猇": 21960,
+  "猊": 22386,
+  "猞": 22200,
+  "猢": 22144,
+  "猻": 22145,
+  "獁": 22296,
+  "獏": 22567,
+  "獬": 22044,
+  "獴": 21559,
+  "玆": 21640,
+  "玕": 21604,
+  "玗": 22095,
+  "玘": 22225,
+  "玢": 22527,
+  "玹": 21858,
+  "珓": 21691,
+  "珧": 22017,
+  "珽": 21642,
+  "琚": 21460,
+  "琤": 21656,
+  "琹": 21671,
+  "琿": 21431,
+  "瑂": 21376,
+  "瑈": 22067,
+  "瑭": 21582,
+  "瑷": 21428,
+  "璆": 22260,
+  "璈": 22325,
+  "璘": 21384,
+  "璠": 21670,
+  "璣": 21550,
+  "璥": 22579,
+  "璦": 21277,
+  "璩": 21792,
+  "璫": 21393,
+  "瓌": 21457,
+  "瓔": 22053,
+  "瓘": 21644,
+  "瓚": 21614,
+  "瓠": 21263,
+  "甂": 22160,
+  "甑": 21994,
+  "甪": 21920,
+  "甴": 21346,
+  "畈": 21669,
+  "畋": 21949,
+  "畚": 22172,
+  "畠": 21602,
+  "畧": 21436,
+  "畬": 22495,
+  "畯": 22258,
+  "畵": 22300,
+  "疃": 22445,
+  "疋": 21888,
+  "疍": 22010,
+  "疎": 21700,
+  "疴": 21441,
+  "痲": 21415,
+  "痾": 21763,
+  "瘰": 21488,
+  "癆": 21222,
+  "癩": 21489,
+  "癰": 21386,
+  "皝": 21156,
+  "皞": 21363,
+  "眛": 22065,
+  "眜": 21698,
+  "眭": 21902,
+  "睍": 21751,
+  "睚": 21168,
+  "睺": 21552,
+  "睼": 21617,
+  "瞽": 22474,
+  "砀": 21695,
+  "砈": 21802,
+  "砟": 22169,
+  "砦": 22390,
+  "砫": 22374,
+  "砬": 21973,
+  "砵": 21235,
+  "砹": 22235,
+  "砻": 21623,
+  "硃": 22001,
+  "硇": 21834,
+  "硏": 21380,
+  "硖": 22270,
+  "硚": 21735,
+  "硤": 21465,
+  "碭": 21270,
+  "碲": 21189,
+  "磔": 22224,
+  "磧": 21797,
+  "磴": 21406,
+  "磾": 21258,
+  "礒": 21198,
+  "礬": 21710,
+  "礮": 21725,
+  "礽": 21287,
+  "祆": 21205,
+  "祏": 22351,
+  "祓": 22234,
+  "祔": 21328,
+  "祘": 22071,
+  "祧": 22176,
+  "祼": 21607,
+  "禑": 21746,
+  "禔": 22072,
+  "禕": 21425,
+  "禟": 21285,
+  "禡": 22230,
+  "禤": 21646,
+  "禥": 21852,
+  "禩": 21284,
+  "禰": 21702,
+  "禳": 22222,
+  "禵": 21286,
+  "秈": 22194,
+  "稃": 22193,
+  "稈": 21587,
+  "稙": 21981,
+  "穏": 21501,
+  "穡": 22120,
+  "穰": 21694,
+  "窣": 21321,
+  "窰": 21358,
+  "竈": 21882,
+  "竉": 21565,
+  "竑": 21672,
+  "竦": 22280,
+  "竪": 21442,
+  "笄": 22175,
+  "笘": 22538,
+  "笪": 21143,
+  "笭": 22415,
+  "笮": 21997,
+  "笳": 21613,
+  "筅": 22577,
+  "筧": 22236,
+  "筮": 21825,
+  "筴": 21708,
+  "箓": 22405,
+  "箧": 22271,
+  "箬": 21135,
+  "篋": 22122,
+  "篦": 21577,
+  "篾": 22016,
+  "簋": 22358,
+  "簒": 21539,
+  "簕": 22015,
+  "簣": 22061,
+  "籀": 22290,
+  "籙": 22205,
+  "籣": 21575,
+  "籾": 22519,
+  "粢": 21745,
+  "糌": 22575,
+  "糭": 21352,
+  "糴": 22116,
+  "糶": 22526,
+  "紇": 21658,
+  "紈": 22282,
+  "紥": 21723,
+  "紬": 22506,
+  "絀": 21626,
+  "絛": 22511,
+  "絜": 22059,
+  "綉": 21206,
+  "綝": 21823,
+  "綟": 22087,
+  "綣": 21750,
+  "綰": 21344,
+  "綷": 22141,
+  "緡": 21491,
+  "緱": 22167,
+  "緲": 22543,
+  "縉": 21326,
+  "縊": 21166,
+  "縐": 21677,
+  "縞": 21935,
+  "縠": 22400,
+  "縻": 21160,
+  "繑": 22558,
+  "繒": 22500,
+  "繖": 22368,
+  "繙": 21350,
+  "繯": 21360,
+  "繻": 22257,
+  "繾": 21749,
+  "纈": 22388,
+  "纘": 21636,
+  "纛": 21712,
+  "纥": 21892,
+  "绹": 22551,
+  "缬": 22583,
+  "缵": 21378,
+  "缶": 22238,
+  "罃": 22331,
+  "罅": 21622,
+  "罈": 21817,
+  "罉": 21657,
+  "罘": 22317,
+  "罟": 21737,
+  "罾": 22425,
+  "羋": 21895,
+  "羕": 21953,
+  "羗": 22253,
+  "羰": 21251,
+  "翀": 22426,
+  "翕": 21687,
+  "翥": 22353,
+  "翬": 22272,
+  "耖": 21590,
+  "耜": 22032,
+  "聃": 22154,
+  "聡": 21816,
+  "聵": 21988,
+  "肟": 22291,
+  "肼": 21912,
+  "胂": 22097,
+  "胐": 21985,
+  "胪": 22024,
+  "胼": 22323,
+  "脒": 22522,
+  "脧": 22211,
+  "脷": 21433,
+  "腍": 21335,
+  "腧": 22467,
+  "膣": 22544,
+  "膥": 21544,
+  "膶": 22477,
+  "臏": 21907,
+  "臚": 22242,
+  "舘": 21494,
+  "舢": 21848,
+  "舨": 21849,
+  "艉": 22540,
+  "艏": 21588,
+  "艶": 21650,
+  "艸": 22246,
+  "芗": 22204,
+  "苅": 22158,
+  "苌": 22265,
+  "苎": 21668,
+  "苧": 21699,
+  "苳": 21676,
+  "苴": 21238,
+  "苾": 22442,
+  "茆": 22208,
+  "茌": 22450,
+  "茘": 21213,
+  "茛": 21437,
+  "荑": 21572,
+  "莜": 22036,
+  "莨": 21774,
+  "莼": 21574,
+  "菉": 22510,
+  "菫": 22106,
+  "菰": 22478,
+  "菴": 21948,
+  "菻": 22469,
+  "萇": 21170,
+  "萜": 21785,
+  "萣": 22438,
+  "葰": 22178,
+  "葶": 21391,
+  "蒗": 22284,
+  "蒯": 21323,
+  "蒴": 21385,
+  "蒽": 22447,
+  "蓀": 21576,
+  "蓍": 22379,
+  "蓥": 21485,
+  "蔞": 21728,
+  "蔦": 21827,
+  "蔴": 21209,
+  "蕓": 21197,
+  "蕰": 21832,
+  "蕷": 21727,
+  "蕹": 22530,
+  "薜": 22289,
+  "薤": 21196,
+  "薫": 22397,
+  "薮": 22149,
+  "薺": 21545,
+  "藁": 21736,
+  "藪": 21162,
+  "藶": 21392,
+  "藷": 21637,
+  "藺": 21394,
+  "蘄": 22401,
+  "蘅": 21641,
+  "蘖": 21818,
+  "蘢": 22489,
+  "虯": 21551,
+  "虺": 21517,
+  "蚋": 22134,
+  "蚧": 22005,
+  "蚶": 22418,
+  "蚺": 22328,
+  "蛄": 21178,
+  "蛉": 22138,
+  "蛞": 21566,
+  "蛸": 22056,
+  "蛺": 22014,
+  "蜉": 21632,
+  "蜑": 21359,
+  "蜞": 22421,
+  "蜩": 21896,
+  "蝓": 21567,
+  "蝣": 21633,
+  "蝮": 21418,
+  "蝰": 22127,
+  "蝽": 21419,
+  "蝾": 22273,
+  "螄": 22571,
+  "螅": 21449,
+  "螈": 21487,
+  "螟": 22389,
+  "螣": 22536,
+  "螫": 22090,
+  "螭": 22319,
+  "螻": 21595,
+  "螽": 22494,
+  "蟌": 22574,
+  "蟜": 21364,
+  "蟧": 22316,
+  "蟳": 22542,
+  "蠄": 22315,
+  "蠊": 22549,
+  "蠏": 21598,
+  "蠑": 21486,
+  "蠖": 22115,
+  "蠲": 22102,
+  "蠵": 21721,
+  "衊": 21980,
+  "衎": 21458,
+  "衕": 22143,
+  "衚": 22142,
+  "衽": 21308,
+  "袛": 21752,
+  "袢": 21899,
+  "袴": 22099,
+  "裇": 21322,
+  "褘": 22561,
+  "褦": 21289,
+  "褸": 21204,
+  "襖": 21371,
+  "襦": 22399,
+  "覈": 21854,
+  "覡": 22118,
+  "覲": 21483,
+  "觚": 21153,
+  "觜": 21951,
+  "觳": 22432,
+  "觴": 21256,
+  "訃": 21923,
+  "訇": 21952,
+  "訌": 21374,
+  "訐": 21784,
+  "訢": 21429,
+  "訾": 21368,
+  "詁": 21240,
+  "詈": 22263,
+  "詎": 22332,
+  "詏": 21301,
+  "詒": 21704,
+  "詝": 21427,
+  "詧": 21638,
+  "諂": 22156,
+  "諉": 21518,
+  "諍": 22088,
+  "諛": 21761,
+  "諤": 21389,
+  "諶": 21893,
+  "謇": 22045,
+  "謖": 21962,
+  "謚": 21265,
+  "謡": 21857,
+  "謫": 21507,
+  "謳": 21259,
+  "譞": 21430,
+  "譟": 21776,
+  "讃": 22520,
+  "讉": 22107,
+  "讒": 22103,
+  "讖": 21618,
+  "讣": 22248,
+  "诂": 21652,
+  "诒": 21462,
+  "谡": 22547,
+  "谿": 21422,
+  "豕": 21236,
+  "豨": 22341,
+  "豳": 22173,
+  "豸": 22313,
+  "貉": 21482,
+  "貊": 21958,
+  "貍": 21310,
+  "賒": 21904,
+  "賛": 22239,
+  "賾": 22375,
+  "贄": 21496,
+  "贇": 22075,
+  "贔": 21247,
+  "贗": 22554,
+  "贽": 21508,
+  "赉": 21145,
+  "赟": 22076,
+  "跗": 22162,
+  "跣": 21341,
+  "踎": 21295,
+  "踭": 21147,
+  "踰": 21783,
+  "蹕": 21309,
+  "蹠": 21917,
+  "躂": 21293,
+  "躄": 21361,
+  "躅": 22110,
+  "躑": 22580,
+  "躝": 21362,
+  "軔": 21977,
+  "軚": 21738,
+  "軛": 21930,
+  "軨": 22486,
+  "軫": 21193,
+  "軭": 22417,
+  "軻": 22215,
+  "輅": 22531,
+  "輋": 21446,
+  "輜": 21996,
+  "輞": 21354,
+  "輦": 21307,
+  "轂": 22108,
+  "轫": 21594,
+  "轸": 22529,
+  "辎": 22165,
+  "迨": 21968,
+  "迳": 22481,
+  "迾": 22514,
+  "逄": 21983,
+  "逋": 21305,
+  "逑": 21719,
+  "逖": 21838,
+  "逯": 22112,
+  "逳": 21229,
+  "逹": 21873,
+  "遯": 22412,
+  "遹": 21683,
+  "邗": 21495,
+  "邙": 22395,
+  "邠": 21831,
+  "邡": 21484,
+  "邴": 22245,
+  "邶": 21243,
+  "邽": 22491,
+  "邾": 21605,
+  "郃": 21903,
+  "郇": 21302,
+  "郏": 21410,
+  "郓": 21753,
+  "郕": 22155,
+  "郗": 21998,
+  "郛": 21453,
+  "郞": 21131,
+  "郯": 21824,
+  "郾": 21789,
+  "郿": 21961,
+  "鄄": 22337,
+  "鄆": 21843,
+  "鄕": 21171,
+  "鄖": 22025,
+  "鄘": 21767,
+  "鄚": 22364,
+  "鄜": 22480,
+  "鄣": 21620,
+  "鄩": 21370,
+  "鄫": 22479,
+  "鄮": 22434,
+  "鄯": 22326,
+  "鄴": 21154,
+  "酃": 22484,
+  "酆": 21208,
+  "酈": 22361,
+  "酎": 22524,
+  "醂": 22019,
+  "醌": 22448,
+  "醢": 22461,
+  "釆": 22286,
+  "釓": 22089,
+  "釔": 22080,
+  "釕": 21862,
+  "釙": 21801,
+  "釤": 22304,
+  "釩": 21541,
+  "釷": 21511,
+  "釹": 21760,
+  "鈁": 22548,
+  "鈇": 21188,
+  "鈈": 21490,
+  "鈐": 21132,
+  "鈧": 22079,
+  "鈮": 21158,
+  "鈰": 21481,
+  "鈳": 22324,
+  "鈷": 21317,
+  "鈸": 21267,
+  "鈹": 21478,
+  "鈽": 21924,
+  "鈿": 21413,
+  "鉆": 21474,
+  "鉈": 21875,
+  "鉍": 21316,
+  "鉕": 21900,
+  "鉝": 21526,
+  "鉞": 21150,
+  "鉢": 21631,
+  "鉦": 22318,
+  "鉨": 22586,
+  "鉬": 21159,
+  "鉭": 21629,
+  "鉲": 22414,
+  "鉸": 21443,
+  "鉺": 22218,
+  "鉼": 22440,
+  "鉾": 21709,
+  "鉿": 21946,
+  "銚": 22187,
+  "銛": 22140,
+  "銠": 21318,
+  "銣": 21185,
+  "銥": 21274,
+  "銦": 21186,
+  "銨": 22026,
+  "銩": 22449,
+  "銪": 22311,
+  "銫": 21183,
+  "銲": 22476,
+  "銶": 21523,
+  "銻": 22098,
+  "銼": 21230,
+  "鋂": 22460,
+  "鋆": 21139,
+  "鋇": 21466,
+  "鋌": 22348,
+  "鋐": 21897,
+  "鋦": 21680,
+  "鋨": 21859,
+  "鋭": 22074,
+  "鋯": 21480,
+  "鋱": 22302,
+  "鋹": 21846,
+  "錀": 22570,
+  "錇": 22475,
+  "錒": 21315,
+  "錕": 21454,
+  "錡": 21527,
+  "錬": 22251,
+  "錸": 22459,
+  "錼": 22457,
+  "鍀": 22568,
+  "鍅": 21679,
+  "鍆": 22499,
+  "鍇": 21673,
+  "鍔": 21337,
+  "鍘": 22585,
+  "鍚": 22073,
+  "鍩": 22466,
+  "鍬": 21563,
+  "鍶": 22308,
+  "鍼": 21840,
+  "鎅": 21515,
+  "鎘": 22264,
+  "鎝": 22456,
+  "鎢": 21813,
+  "鎦": 22458,
+  "鎩": 21891,
+  "鎭": 21298,
+  "鎰": 21747,
+  "鎵": 21184,
+  "鎶": 21187,
+  "鎿": 22588,
+  "鏃": 22109,
+  "鏇": 21546,
+  "鏊": 22503,
+  "鏌": 21555,
+  "鏐": 21331,
+  "鏑": 22013,
+  "鏵": 21597,
+  "鏷": 22455,
+  "鏸": 21340,
+  "鏹": 22406,
+  "鐐": 22009,
+  "鐒": 22483,
+  "鐙": 21830,
+  "鐠": 22303,
+  "鐨": 21860,
+  "鐫": 22217,
+  "鐽": 21861,
+  "鐿": 21874,
+  "鑀": 22535,
+  "鑌": 21782,
+  "鑛": 22528,
+  "鑠": 21304,
+  "鑥": 22573,
+  "鑪": 21624,
+  "鑭": 21662,
+  "鑴": 22268,
+  "鑷": 22381,
+  "钆": 22560,
+  "钇": 21472,
+  "钋": 21876,
+  "钌": 21493,
+  "钍": 21879,
+  "钐": 22309,
+  "钕": 21471,
+  "钚": 22427,
+  "钪": 22306,
+  "钫": 22047,
+  "钬": 22334,
+  "钷": 22307,
+  "钽": 21666,
+  "铈": 21164,
+  "铊": 21877,
+  "铋": 21570,
+  "铌": 22083,
+  "铍": 21667,
+  "铑": 22422,
+  "铒": 22333,
+  "铟": 21192,
+  "铥": 22565,
+  "铪": 22428,
+  "铯": 21163,
+  "铱": 22546,
+  "铳": 21726,
+  "铷": 22454,
+  "铼": 22430,
+  "铽": 22310,
+  "锇": 22523,
+  "锕": 22452,
+  "锗": 21800,
+  "锴": 22152,
+  "锶": 22534,
+  "锷": 22048,
+  "镆": 22365,
+  "镎": 22404,
+  "镒": 22437,
+  "镓": 21191,
+  "镝": 21965,
+  "镠": 22041,
+  "镤": 22429,
+  "镥": 22564,
+  "镧": 21878,
+  "镨": 22305,
+  "閂": 21221,
+  "閆": 22051,
+  "閤": 22189,
+  "閦": 21653,
+  "閪": 21868,
+  "閬": 21619,
+  "閭": 21212,
+  "閰": 22223,
+  "閼": 22114,
+  "闈": 21324,
+  "闋": 22057,
+  "闐": 21585,
+  "闓": 21463,
+  "闞": 22262,
+  "闥": 22003,
+  "闳": 21260,
+  "闼": 21754,
+  "闿": 21664,
+  "阋": 22493,
+  "阗": 22002,
+  "阯": 22171,
+  "陉": 22168,
+  "陔": 21674,
+  "陘": 22064,
+  "陜": 22166,
+  "陬": 22153,
+  "隗": 21365,
+  "隰": 22121,
+  "隷": 21400,
+  "隹": 21693,
+  "雩": 22363,
+  "雫": 22233,
+  "霅": 22398,
+  "靑": 22314,
+  "靺": 21280,
+  "鞨": 21281,
+  "鞮": 21743,
+  "韁": 22207,
+  "韃": 21294,
+  "韙": 22555,
+  "韞": 21593,
+  "韡": 21744,
+  "韮": 21706,
+  "頊": 21367,
+  "頎": 22505,
+  "頦": 21922,
+  "頴": 21645,
+  "頵": 22288,
+  "顒": 21794,
+  "顓": 21366,
+  "顕": 22552,
+  "顗": 21136,
+  "顥": 21682,
+  "顳": 21606,
+  "颙": 22243,
+  "颺": 21635,
+  "飈": 21979,
+  "飭": 22050,
+  "飴": 21250,
+  "餑": 22113,
+  "餬": 22182,
+  "餸": 21223,
+  "餽": 22148,
+  "餿": 22492,
+  "饉": 21866,
+  "馱": 21313,
+  "駖": 22382,
+  "駙": 21758,
+  "駟": 21773,
+  "駡": 22335,
+  "駢": 21839,
+  "駰": 21423,
+  "騒": 21578,
+  "騤": 21915,
+  "騫": 21257,
+  "騭": 21829,
+  "騮": 21200,
+  "騾": 21167,
+  "驁": 21351,
+  "驃": 21473,
+  "驄": 21383,
+  "驤": 21612,
+  "驩": 22085,
+  "驪": 21140,
+  "骘": 22423,
+  "骹": 21237,
+  "髀": 21203,
+  "髁": 22254,
+  "髑": 22031,
+  "髙": 22221,
+  "髡": 22349,
+  "髢": 22507,
+  "髭": 21254,
+  "髹": 22062,
+  "鬅": 21564,
+  "鬘": 22066,
+  "鬨": 21764,
+  "鬩": 22117,
+  "鬪": 21338,
+  "鬬": 21697,
+  "鬭": 21956,
+  "鬯": 21643,
+  "鬲": 21369,
+  "鬻": 21261,
+  "魎": 22463,
+  "魟": 21730,
+  "魨": 21181,
+  "魮": 22128,
+  "魴": 22498,
+  "鮈": 21990,
+  "鮋": 21890,
+  "鮎": 21146,
+  "鮒": 22512,
+  "鮟": 21342,
+  "鮫": 21246,
+  "鯀": 22007,
+  "鯇": 21870,
+  "鯓": 22163,
+  "鯡": 21707,
+  "鯢": 21982,
+  "鯤": 21889,
+  "鯥": 22387,
+  "鯪": 21554,
+  "鯭": 22123,
+  "鯷": 21718,
+  "鯿": 22487,
+  "鰂": 21207,
+  "鰈": 22275,
+  "鰐": 22344,
+  "鰕": 22082,
+  "鰨": 22345,
+  "鰩": 22130,
+  "鰱": 22312,
+  "鰹": 21409,
+  "鰺": 21729,
+  "鱀": 21820,
+  "鱇": 21343,
+  "鱊": 22129,
+  "鱒": 21319,
+  "鱘": 21417,
+  "鱟": 22020,
+  "鱥": 22590,
+  "鱧": 22557,
+  "鱭": 21986,
+  "鱲": 21151,
+  "鲀": 22081,
+  "鲂": 21424,
+  "鲎": 22587,
+  "鲧": 22581,
+  "鲮": 21933,
+  "鲽": 22336,
+  "鳊": 22220,
+  "鳎": 22545,
+  "鳔": 21819,
+  "鳟": 22327,
+  "鳧": 22283,
+  "鳯": 21201,
+  "鳽": 22029,
+  "鴆": 22259,
+  "鴇": 21634,
+  "鴒": 21778,
+  "鴝": 21357,
+  "鴞": 21182,
+  "鴟": 21610,
+  "鴣": 21561,
+  "鴯": 21803,
+  "鴴": 21660,
+  "鴷": 22136,
+  "鵐": 22497,
+  "鵞": 21845,
+  "鵟": 22132,
+  "鵠": 21850,
+  "鵪": 21556,
+  "鵯": 22584,
+  "鶇": 21562,
+  "鶉": 21557,
+  "鶒": 22562,
+  "鶓": 21804,
+  "鶚": 22354,
+  "鶡": 21194,
+  "鶲": 21356,
+  "鶺": 21777,
+  "鶻": 21332,
+  "鶿": 21348,
+  "鷀": 21553,
+  "鷂": 21220,
+  "鷄": 21336,
+  "鷈": 21809,
+  "鷉": 21807,
+  "鷓": 21560,
+  "鷯": 21810,
+  "鷸": 21805,
+  "鷿": 21808,
+  "鸂": 22563,
+  "鸊": 21806,
+  "鸌": 22137,
+  "鸕": 21347,
+  "鸛": 21569,
+  "鸝": 21925,
+  "鸩": 22338,
+  "鸫": 21608,
+  "鸮": 21799,
+  "鸰": 21780,
+  "鹀": 22133,
+  "鹗": 21934,
+  "鹡": 21779,
+  "鹩": 22135,
+  "鹬": 22516,
+  "鹱": 21520,
+  "麖": 22018,
+  "麪": 21252,
+  "麯": 22532,
+  "麹": 21531,
+  "麿": 21492,
+  "黐": 21586,
+  "黟": 21273,
+  "黥": 21696,
+  "黧": 21353,
+  "黷": 22077,
+  "黻": 21138,
+  "黼": 21966,
+  "黽": 22043,
+  "鼆": 22393,
+  "鼇": 21908,
+  "鼍": 22541,
+  "鼩": 22091,
+  "鼯": 22093,
+  "鼱": 22125,
+  "鼴": 22092,
+  "鼷": 22038,
+  "齧": 22126,
+  "齮": 22195,
+  "齶": 22027,
+  "龑": 21584,
+  "龠": 21395,
+  "龢": 21241,
+  "鿕": 22297,
+  "鿫": 21856,
+  "鿬": 22569
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "./sts-cantonese",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 22593
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.33.1",
+    "pytorch": "2.0.1+cu117"
+  }
+}

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ce052c23e7ce6dbb3d17cb88a4d1ad7b0b5686763b8ec209dcb4c1a37f2b544
+size 413635049

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": true
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 437,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}