jchevallard commited on
Commit
4e938c6
·
verified ·
1 Parent(s): 7b93cf0

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. README.md +6 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +23 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +0 -0
  6. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ ---
4
+
5
+ Cloned from [Xenova/Mistral-Nemo-Instruct-Tokenizer](https://huggingface.co/Xenova/Mistral-Nemo-Instruct-Tokenizer)
6
+
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff