commit files to HF hub

.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 +1,59 @@
+---
+language: zh
+tags:
+- wobert
+inference: False
+---
+## 介绍
+### tf版本 
+https://github.com/ZhuiyiTechnology/WoBERT
+### pytorch版本 
+https://github.com/JunnYu/WoBERT_pytorch
+
+## 安装(主要为了安装WoBertTokenizer)
+```bash
+pip install git+https://github.com/JunnYu/WoBERT_pytorch.git
+```
+
+## 使用
+```python
+import torch
+from transformers import BertForMaskedLM as WoBertForMaskedLM
+from wobert import WoBertTokenizer
+
+pretrained_model_or_path_list = [
+    "junnyu/wobert_chinese_plus_base", "junnyu/wobert_chinese_base"
+]
+for path in pretrained_model_or_path_list:
+    text = "今天[MASK]很好，我[MASK]去公园玩。"
+    tokenizer = WoBertTokenizer.from_pretrained(path)
+    model = WoBertForMaskedLM.from_pretrained(path)
+    inputs = tokenizer(text, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model(**inputs).logits[0]
+    outputs_sentence = ""
+    for i, id in enumerate(tokenizer.encode(text)):
+        if id == tokenizer.mask_token_id:
+            tokens = tokenizer.convert_ids_to_tokens(outputs[i].topk(k=5)[1])
+            outputs_sentence += "[" + "||".join(tokens) + "]"
+        else:
+            outputs_sentence += "".join(
+                tokenizer.convert_ids_to_tokens([id],
+                                                skip_special_tokens=True))
+    print(outputs_sentence)
+# RoFormer    今天[天气||天||心情||阳光||空气]很好，我[想||要||打算||准备||喜欢]去公园玩。
+# PLUS WoBERT 今天[天气||阳光||天||心情||空气]很好，我[想||要||打算||准备||就]去公园玩。
+# WoBERT      今天[天气||阳光||天||心情||空气]很好，我[想||要||就||准备||也]去公园玩。
+```
+## 引用
+
+Bibtex：
+
+```tex
+@techreport{zhuiyiwobert,
+  title={WoBERT: Word-based Chinese BERT model - ZhuiyiAI},
+  author={Jianlin Su},
+  year={2020},
+  url="https://github.com/ZhuiyiTechnology/WoBERT",
+}
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "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-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",
+  "transformers_version": "4.5.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6f7ec47fa15b29244d234f4d5c360a16016f7f3bfa39dad946f375af1677a3
+size 497978787

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bebcf0185342ef391ac44689481c69296509821bacf46421ff22fcc31cdefc7b
+size 500428391

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+    "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,
+    "name_or_path": "junnyu/wobert_chinese_plus_base",
+    "tokenizer_class": "RoFormerTokenizer"
+}