Upload model files.

README.md

@@ -0,0 +1,47 @@
+---
+language:
+- zh
+thumbnail: https://ckip.iis.sinica.edu.tw/files/ckip_logo.png
+tags:
+- pytorch
+- token-classification
+- bert
+- zh
+license: gpl-3.0
+datasets:
+metrics:
+---
+
+# CKIP BERT Tiny Chinese
+
+This project provides traditional Chinese transformers models (including ALBERT, BERT, GPT2) and NLP tools (including word segmentation, part-of-speech tagging, named entity recognition).
+
+這個專案提供了繁體中文的 transformers 模型（包含 ALBERT、BERT、GPT2）及自然語言處理工具（包含斷詞、詞性標記、實體辨識）。
+
+## Homepage
+
+* https://github.com/ckiplab/ckip-transformers
+
+## Contributers
+
+* [Mu Yang](https://muyang.pro) at [CKIP](https://ckip.iis.sinica.edu.tw) (Author & Maintainer)
+
+## Usage
+
+Please use BertTokenizerFast as tokenizer instead of AutoTokenizer.
+
+請使用 BertTokenizerFast 而非 AutoTokenizer。
+
+```
+from transformers import (
+  BertTokenizerFast,
+  AutoModel,
+)
+
+tokenizer = BertTokenizerFast.from_pretrained('bert-base-chinese')
+model = AutoModel.from_pretrained('ckiplab/bert-tiny-chinese-ws')
+```
+
+For full usage and more information, please refer to https://github.com/ckiplab/ckip-transformers.
+
+有關完整使用方法及其他資訊，請參見 https://github.com/ckiplab/ckip-transformers 。

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "../../../model/bert-tiny-scratch-lm",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "B",
+    "1": "I"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1248,
+  "label2id": {
+    "B": 0,
+    "I": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "pooler_fc_size": 312,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "tokenizer_class": "BertTokenizerFast",
+  "type_vocab_size": 2,
+  "vocab_size": 21128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29d3ccfe939242b1691e8293d0cd30b5fd6b80333bf11967f22a6a7d5a213189
+size 45802231

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "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, "model_max_length": 512, "name_or_path": "bert-base-chinese"}