Upload model files.

README.md

@@ -0,0 +1,22 @@
+---
+language:
+- zh
+thumbnail: https://ckip.iis.sinica.edu.tw/files/ckip_logo.png
+tags:
+- pytorch
+- token-classification
+- albert
+- zh
+license: gpl-3.0
+datasets:
+metrics:
+---
+
+# CKIP ALBERT Tiny Chinese — Word Segmentation
+
+## Contributers
+
+* [Mu Yang](https://muyang.pro) at [CKIP](https://ckip.iis.sinica.edu.tw) (Author & Maintainer)
+
+## Attention
+Please Use `BertTokenizer` instead of `AutoTokenizer`!!!

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "AlbertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "B",
+    "1": "I"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 1248,
+  "label2id": {
+    "B": 0,
+    "I": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 4,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "type_vocab_size": 2,
+  "vocab_size": 21128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ededb20956722e26434fcda12b31a1da568e1629228be273cffe53f275b9d94
+size 15949017

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"}