Upload tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +6 -1
- tokenizer_config.json +1 -0
special_tokens_map.json
CHANGED
@@ -13,6 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<|endoftext|>",
|
18 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
"unk_token": {
|
18 |
"content": "<|endoftext|>",
|
19 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 1024,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
tokenizer_config.json
CHANGED
@@ -206,6 +206,7 @@
|
|
206 |
"clean_up_tokenization_spaces": true,
|
207 |
"eos_token": "<|endoftext|>",
|
208 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
209 |
"tokenizer_class": "GPTNeoXTokenizer",
|
210 |
"unk_token": "<|endoftext|>"
|
211 |
}
|
|
|
206 |
"clean_up_tokenization_spaces": true,
|
207 |
"eos_token": "<|endoftext|>",
|
208 |
"model_max_length": 1000000000000000019884624838656,
|
209 |
+
"pad_token": "<|endoftext|>",
|
210 |
"tokenizer_class": "GPTNeoXTokenizer",
|
211 |
"unk_token": "<|endoftext|>"
|
212 |
}
|