Upload 7 files

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": 2000,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bee51db06c6011ecf794488cf9864db159318d7adcadc3f3628d3bbf782e262f
+size 443415264

tokenizer_config.json

@@ -3,11 +3,11 @@
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 2000,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
-  "tokenize_chinese_chars": true,
+  "tokenize_chinese_chars": false,
   "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89e4338dd83ccad3caf47437bbfc3a7024cbc37e696d9ad3dccaea02240b765d
+size 4027