Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +1 -1
tokenizer.json
CHANGED
@@ -2,13 +2,13 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
-
"Fixed":
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 4096,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
+
"Fixed": 4096
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
tokenizer_config.json
CHANGED
@@ -199,7 +199,7 @@
|
|
199 |
"clean_up_tokenization_spaces": false,
|
200 |
"eos_token": "<|im_end|>",
|
201 |
"errors": "replace",
|
202 |
-
"max_length":
|
203 |
"model_max_length": 131072,
|
204 |
"pad_to_multiple_of": null,
|
205 |
"pad_token": "<|endoftext|>",
|
|
|
199 |
"clean_up_tokenization_spaces": false,
|
200 |
"eos_token": "<|im_end|>",
|
201 |
"errors": "replace",
|
202 |
+
"max_length": 4096,
|
203 |
"model_max_length": 131072,
|
204 |
"pad_to_multiple_of": null,
|
205 |
"pad_token": "<|endoftext|>",
|