From ae6201c2d816767a0c758e0c24bb86af17c4dce7 Mon Sep 17 00:00:00 2001
From: "Menezes, Luke J (PG/T - Comp Sci & Elec Eng)" <lm01906@surrey.ac.uk>
Date: Thu, 23 May 2024 11:21:19 +0000
Subject: [PATCH] Upload New File
---
SciBERT-finetuned-NER/tokenizer_config.json | 57 +++++++++++++++++++++
1 file changed, 57 insertions(+)
create mode 100644 SciBERT-finetuned-NER/tokenizer_config.json
diff --git a/SciBERT-finetuned-NER/tokenizer_config.json b/SciBERT-finetuned-NER/tokenizer_config.json
new file mode 100644
index 0000000..feeb7cb
--- /dev/null
+++ b/SciBERT-finetuned-NER/tokenizer_config.json
@@ -0,0 +1,57 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "101": {
+ "content": "[UNK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "102": {
+ "content": "[CLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "103": {
+ "content": "[SEP]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "104": {
+ "content": "[MASK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "[CLS]",
+ "do_basic_tokenize": true,
+ "do_lower_case": true,
+ "mask_token": "[MASK]",
+ "model_max_length": 1000000000000000019884624838656,
+ "never_split": null,
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "strip_accents": null,
+ "tokenize_chinese_chars": true,
+ "tokenizer_class": "BertTokenizer",
+ "unk_token": "[UNK]"
+}
--
GitLab