change lfs file to normal file (#4)

- change file mode (07aeb114d80bea1f264ec7f5b82bcbecea4dbf9d)

.gitattributes

@@ -30,10 +30,4 @@ saved_model/**/* 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
-config.json filter=lfs diff=lfs merge=lfs -text
 pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
-special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
-tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
-vocab.txt filter=lfs diff=lfs merge=lfs -text
-word_pronunciation.json filter=lfs diff=lfs merge=lfs -text
-word_shape.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,3 +1,39 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8e27676e5340a801a9e9a8503fca5d9ec0070cca07ad5555a747232e30079485
-size 1070
+{
+  "_name_or_path": "weiweishi/roc-bert-base-zh",
+  "architectures": [
+    "RoCBertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "concat_input": true,
+  "directionality": "bidi",
+  "enable_cls": true,
+  "enable_pronunciation": true,
+  "enable_shape": true,
+  "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": "roc_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",
+  "pronunciation_embed_dim": 768,
+  "pronunciation_vocab_size": 910,
+  "shape_embed_dim": 512,
+  "shape_vocab_size": 24858,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

special_tokens_map.json

@@ -1,3 +1,7 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b6d346be366a7d1d48332dbc9fdf3bf8960b5d879522b7799ddba59e76237ee3
-size 125
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1,3 +1,16 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:741610a7422466d1a9d83e290e2fcc32b67d97f656d107702b8cf6798140d5b1
-size 412
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "weiweishi/roc-bert-base-zh",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "RoCBertTokenizer",
+  "unk_token": "[UNK]"
+}