Upload 9 files

.gitattributes

@@ -1,34 +1,17 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.msgpack filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,90 @@
+---
+language: zh
+widget: 
+- text: "江苏警方通报特斯拉冲进店铺"
+
+---
+
+# Chinese RoBERTa-Base Model for NER
+
+## Model description
+
+The model is used for named entity recognition. You can download the model either from the [UER-py Modelzoo page](https://github.com/dbiir/UER-py/wiki/Modelzoo) (in UER-py format), or via HuggingFace from the link [roberta-base-finetuned-cluener2020-chinese](https://huggingface.co/uer/roberta-base-finetuned-cluener2020-chinese).
+
+## How to use
+
+You can use this model directly with a pipeline for token classification :
+
+```python
+>>> from transformers import AutoModelForTokenClassification,AutoTokenizer,pipeline
+>>> model = AutoModelForTokenClassification.from_pretrained('uer/roberta-base-finetuned-cluener2020-chinese')
+>>> tokenizer = AutoTokenizer.from_pretrained('uer/roberta-base-finetuned-cluener2020-chinese')
+>>> ner = pipeline('ner', model=model, tokenizer=tokenizer)
+>>> ner("江苏警方通报特斯拉冲进店铺")
+    [
+       {'word': '江', 'score': 0.49153077602386475, 'entity': 'B-address', 'index': 1, 'start': 0, 'end': 1}, 
+       {'word': '苏', 'score': 0.6319217681884766, 'entity': 'I-address', 'index': 2, 'start': 1, 'end': 2}, 
+       {'word': '特', 'score': 0.5912262797355652, 'entity': 'B-company', 'index': 7, 'start': 6, 'end': 7},
+       {'word': '斯', 'score': 0.69145667552948, 'entity': 'I-company', 'index': 8, 'start': 7, 'end': 8}, 
+       {'word': '拉', 'score': 0.7054660320281982, 'entity': 'I-company', 'index': 9, 'start': 8, 'end': 9}
+    ]
+```
+
+## Training data
+
+[CLUENER2020](https://github.com/CLUEbenchmark/CLUENER2020) is used as training data. We only use the train set of the dataset.
+
+## Training procedure
+
+The model is fine-tuned by [UER-py](https://github.com/dbiir/UER-py/) on [Tencent Cloud](https://cloud.tencent.com/). We fine-tune five epochs with a sequence length of 512 on the basis of the pre-trained model [chinese_roberta_L-12_H-768](https://huggingface.co/uer/chinese_roberta_L-12_H-768). At the end of each epoch, the model is saved when the best performance on development set is achieved.
+
+```
+python3 run_ner.py --pretrained_model_path models/cluecorpussmall_roberta_base_seq512_model.bin-250000 \
+                   --vocab_path models/google_zh_vocab.txt \
+                   --train_path datasets/cluener2020/train.tsv \
+                   --dev_path datasets/cluener2020/dev.tsv \
+                   --label2id_path datasets/cluener2020/label2id.json \
+                   --output_model_path models/cluener2020_ner_model.bin \
+                   --learning_rate 3e-5 --epochs_num 5 --batch_size 32 --seq_length 512
+```
+
+Finally, we convert the pre-trained model into Huggingface's format:
+
+```
+python3 scripts/convert_bert_token_classification_from_uer_to_huggingface.py --input_model_path models/cluener2020_ner_model.bin \
+                                                                             --output_model_path pytorch_model.bin \
+                                                                             --layers_num 12
+```
+
+### BibTeX entry and citation info
+
+```
+@article{devlin2018bert,
+  title={BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding},
+  author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
+  journal={arXiv preprint arXiv:1810.04805},
+  year={2018}
+}
+
+@article{liu2019roberta,
+  title={Roberta: A robustly optimized bert pretraining approach},
+  author={Liu, Yinhan and Ott, Myle and Goyal, Naman and Du, Jingfei and Joshi, Mandar and Chen, Danqi and Levy, Omer and Lewis, Mike and Zettlemoyer, Luke and Stoyanov, Veselin},
+  journal={arXiv preprint arXiv:1907.11692},
+  year={2019}
+}
+
+@article{xu2020cluener2020,
+  title={CLUENER2020: Fine-grained Name Entity Recognition for Chinese},
+  author={Xu, Liang and Dong, Qianqian and Yu, Cong and Tian, Yin and Liu, Weitang and Li, Lu and Zhang, Xuanwei},
+  journal={arXiv preprint arXiv:2001.04351},
+  year={2020}
+ }
+ 
+@article{zhao2019uer,
+  title={UER: An Open-Source Toolkit for Pre-training Models},
+  author={Zhao, Zhe and Chen, Hui and Zhang, Jinbin and Zhao, Xin and Liu, Tao and Lu, Wei and Chen, Xi and Deng, Haotang and Ju, Qi and Du, Xiaoyong},
+  journal={EMNLP-IJCNLP 2019},
+  pages={241},
+  year={2019}
+}
+```

config.json

@@ -0,0 +1,86 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-address",
+    "2": "I-address",
+    "3": "B-book",
+    "4": "I-book",
+    "5": "B-company",
+    "6": "I-company",
+    "7": "B-game",
+    "8": "I-game",
+    "9": "B-government",
+    "10": "I-government",
+    "11": "B-movie",
+    "12": "I-movie",
+    "13": "B-name",
+    "14": "I-name",
+    "15": "B-organization",
+    "16": "I-organization",
+    "17": "B-position",
+    "18": "I-position",
+    "19": "B-scene",
+    "20": "I-scene",
+    "21": "S-address",
+    "22": "S-book",
+    "23": "S-company",
+    "24": "S-game",
+    "25": "S-government",
+    "26": "S-movie",
+    "27": "S-name",
+    "28": "S-organization",
+    "29": "S-position",
+    "30": "S-scene",
+    "31": "[PAD]"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-address": 1,
+    "B-book": 3,
+    "B-company": 5,
+    "B-game": 7,
+    "B-government": 9,
+    "B-movie": 11,
+    "B-name": 13,
+    "B-organization": 15,
+    "B-position": 17,
+    "B-scene": 19,
+    "I-address": 2,
+    "I-book": 4,
+    "I-company": 6,
+    "I-game": 8,
+    "I-government": 10,
+    "I-movie": 12,
+    "I-name": 14,
+    "I-organization": 16,
+    "I-position": 18,
+    "I-scene": 20,
+    "O": 0,
+    "S-address": 21,
+    "S-book": 22,
+    "S-company": 23,
+    "S-game": 24,
+    "S-government": 25,
+    "S-movie": 26,
+    "S-name": 27,
+    "S-organization": 28,
+    "S-position": 29,
+    "S-scene": 30,
+    "[PAD]": 31
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "vocab_size": 21128
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fcc5a4fdb2a83463bf4f65ea0d60e3ecb31963cf85f4f513f3b48150b522b57
+size 406813802

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b865252516115c46bc508167fa2258f198bcce520eb7a1ac4fbf8d50dc361368
+size 406892015

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b129d0ae906c9579f8d118d9a84df27304676d6e8822389c776e8ea33423feb5
+size 407074912

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null}