From 8a81c4e2cfdd47cdf9b52141ee050093a44ee3a3 Mon Sep 17 00:00:00 2001
From: "Hafiz, Aqib (PG/T - Comp Sci & Elec Eng)" <ah02821@surrey.ac.uk>
Date: Thu, 23 May 2024 16:05:45 +0000
Subject: [PATCH] Upload New File
---
tokenizer_config.json | 55 +++++++++++++++++++++++++++++++++++++++++++
1 file changed, 55 insertions(+)
create mode 100644 tokenizer_config.json
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..fab1cec
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,55 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "100": {
+ "content": "[UNK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "101": {
+ "content": "[CLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "102": {
+ "content": "[SEP]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "103": {
+ "content": "[MASK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "[CLS]",
+ "do_lower_case": true,
+ "mask_token": "[MASK]",
+ "model_max_length": 512,
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "strip_accents": null,
+ "tokenize_chinese_chars": true,
+ "tokenizer_class": "DistilBertTokenizer",
+ "unk_token": "[UNK]"
+}
--
GitLab