alea-institute
commited on
Commit
•
6232bc0
1
Parent(s):
2f53ca1
Upload tokenizer
Browse files- README.md +6 -1
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
README.md
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
tags:
|
|
|
|
|
|
|
|
|
|
|
4 |
date: 2023-12-28
|
5 |
---
|
6 |
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- kl3m
|
5 |
+
- kl3m-003
|
6 |
+
- alea
|
7 |
+
- legal
|
8 |
+
- financial
|
9 |
date: 2023-12-28
|
10 |
---
|
11 |
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|start|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|pad|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|unk|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
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
|
|