upload

README.md

@@ -0,0 +1,35 @@
+## 介绍
+tf版本 https://github.com/ZhuiyiTechnology/WoBERT
+pytorch版本 https://github.com/JunnYu/WoBERT_pytorch
+
+## 使用
+```python
+git clone https://github.com/JunnYu/WoBERT_pytorch
+cd WoBERT_pytorch
+import torch
+from transformers import BertForMaskedLM as WoBertForMaskedLM
+from tokenization_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)
+# 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。
+```

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": 33586
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3ad5bcafdb4e76ba2b0937dd8b74de7bdb2906c1cd2572fb42f70170e65937
+size 449938919