update model

README.md

@@ -0,0 +1,40 @@
+---
+language: 
+- zh
+- bo
+- kk
+- ko
+- mn
+- ug
+- yue
+license: "apache-2.0"
+---
+
+## CINO: Pre-trained Language Models for Chinese Minority Languages（中国少数民族预训练模型）
+
+Multilingual Pre-trained Language Model, such as mBERT, XLM-R, provide multilingual and cross-lingual ability for language understanding.
+We have seen rapid progress on building multilingual PLMs in recent year.
+However, there is a lack of contributions on building PLMs on Chines minority languages, which hinders researchers from building powerful NLP systems.
+
+To address the absence of Chinese minority PLMs, Joint Laboratory of HIT and iFLYTEK Research (HFL) proposes CINO (Chinese-miNOrity pre-trained language model), which is built on XLM-R with additional pre-training using Chinese minority corpus, such as 
+- Chinese，中文（zh）
+- Tibetan，藏语（bo）
+- Mongolian (Uighur form)，蒙语（mn）
+- Uyghur，维吾尔语（ug）
+- Kazakh (Arabic form)，哈萨克语（kk）
+- Korean，朝鲜语（ko）
+- Zhuang，壮语
+- Cantonese，粤语（yue）
+
+Please read our GitHub repository for more details (Chinese): https://github.com/ymcui/Chinese-Minority-PLM
+
+You may also interested in,
+
+Chinese MacBERT: https://github.com/ymcui/MacBERT  
+Chinese BERT series: https://github.com/ymcui/Chinese-BERT-wwm  
+Chinese ELECTRA: https://github.com/ymcui/Chinese-ELECTRA  
+Chinese XLNet: https://github.com/ymcui/Chinese-XLNet  
+Knowledge Distillation Toolkit - TextBrewer: https://github.com/airaria/TextBrewer  
+
+More resources by HFL: https://github.com/ymcui/HFL-Anthology
+

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "./",
+  "architectures": [
+    "XLMRobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 135359
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:028717bbb109b3564e3d787d532d839ce1ff300c65117c757e30db03189c8fe9
+size 760610795

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abec8706178924453be115cd2da858ef32de70ba60d0c10300822a732a868cf7
+size 2814898

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1cc8ebe9bbc6fa271dff8a67e81b26401cd22d8c74fc72b93f8632d4472dd57
+size 1178227684

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": ".", "tokenizer_class": "XLMRobertaTokenizer"}