Upload tokenizer
Browse files- special_tokens_map.json +3 -21
- tokenizer.json +0 -0
- tokenizer_config.json +0 -3
- vocab.json +0 -0
special_tokens_map.json
CHANGED
@@ -1,23 +1,5 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
"normalized": true,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": true,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"unk_token": {
|
17 |
-
"content": "<|endoftext|>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": true,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
}
|
23 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": false,
|
3 |
"add_prefix_space": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"50256": {
|
@@ -14,9 +13,7 @@
|
|
14 |
"bos_token": "<|endoftext|>",
|
15 |
"clean_up_tokenization_spaces": true,
|
16 |
"eos_token": "<|endoftext|>",
|
17 |
-
"errors": "replace",
|
18 |
"model_max_length": 1024,
|
19 |
-
"pad_token": null,
|
20 |
"tokenizer_class": "GPT2Tokenizer",
|
21 |
"unk_token": "<|endoftext|>"
|
22 |
}
|
|
|
1 |
{
|
|
|
2 |
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
"50256": {
|
|
|
13 |
"bos_token": "<|endoftext|>",
|
14 |
"clean_up_tokenization_spaces": true,
|
15 |
"eos_token": "<|endoftext|>",
|
|
|
16 |
"model_max_length": 1024,
|
|
|
17 |
"tokenizer_class": "GPT2Tokenizer",
|
18 |
"unk_token": "<|endoftext|>"
|
19 |
}
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|