ingeniumacademy
commited on
Commit
•
ed1fb4f
1
Parent(s):
0268b81
Upload tokenizer
Browse files- README.md +3 -0
- tokenizer.json +2 -1
- tokenizer_config.json +10 -0
README.md
CHANGED
@@ -1 +1,4 @@
|
|
|
|
|
|
|
|
1 |
This a GPT2 tokenizer that was fine-tuned to the reuters dataset.
|
|
|
1 |
+
---
|
2 |
+
{}
|
3 |
+
---
|
4 |
This a GPT2 tokenizer that was fine-tuned to the reuters dataset.
|
tokenizer.json
CHANGED
@@ -9,7 +9,7 @@
|
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
-
"normalized":
|
13 |
"special": true
|
14 |
}
|
15 |
],
|
@@ -40,6 +40,7 @@
|
|
40 |
"end_of_word_suffix": "",
|
41 |
"fuse_unk": false,
|
42 |
"byte_fallback": false,
|
|
|
43 |
"vocab": {
|
44 |
"<|endoftext|>": 0,
|
45 |
"!": 1,
|
|
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
+
"normalized": true,
|
13 |
"special": true
|
14 |
}
|
15 |
],
|
|
|
40 |
"end_of_word_suffix": "",
|
41 |
"fuse_unk": false,
|
42 |
"byte_fallback": false,
|
43 |
+
"ignore_merges": false,
|
44 |
"vocab": {
|
45 |
"<|endoftext|>": 0,
|
46 |
"!": 1,
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,15 @@
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"bos_token": "<|endoftext|>",
|
4 |
"clean_up_tokenization_spaces": true,
|
5 |
"eos_token": "<|endoftext|>",
|
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
"bos_token": "<|endoftext|>",
|
14 |
"clean_up_tokenization_spaces": true,
|
15 |
"eos_token": "<|endoftext|>",
|