Commit
·
e709386
1
Parent(s):
6bd34a7
Upload tokenizer
Browse files- tokenizer.json +16 -2
- tokenizer_config.json +0 -7
tokenizer.json
CHANGED
|
@@ -1,7 +1,21 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 38,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 38
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 50256,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "<|endoftext|>"
|
| 18 |
+
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -20,9 +20,7 @@
|
|
| 20 |
},
|
| 21 |
"errors": "replace",
|
| 22 |
"full_tokenizer_file": null,
|
| 23 |
-
"max_length": 38,
|
| 24 |
"model_max_length": 1000000000000000019884624838656,
|
| 25 |
-
"pad_to_multiple_of": null,
|
| 26 |
"pad_token": {
|
| 27 |
"__type": "AddedToken",
|
| 28 |
"content": "<|endoftext|>",
|
|
@@ -31,12 +29,7 @@
|
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false
|
| 33 |
},
|
| 34 |
-
"pad_token_type_id": 0,
|
| 35 |
-
"padding_side": "right",
|
| 36 |
-
"stride": 0,
|
| 37 |
"tokenizer_class": "GPT2Tokenizer",
|
| 38 |
-
"truncation_side": "right",
|
| 39 |
-
"truncation_strategy": "longest_first",
|
| 40 |
"unk_token": {
|
| 41 |
"__type": "AddedToken",
|
| 42 |
"content": "<|endoftext|>",
|
|
|
|
| 20 |
},
|
| 21 |
"errors": "replace",
|
| 22 |
"full_tokenizer_file": null,
|
|
|
|
| 23 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 24 |
"pad_token": {
|
| 25 |
"__type": "AddedToken",
|
| 26 |
"content": "<|endoftext|>",
|
|
|
|
| 29 |
"rstrip": false,
|
| 30 |
"single_word": false
|
| 31 |
},
|
|
|
|
|
|
|
|
|
|
| 32 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
|
|
| 33 |
"unk_token": {
|
| 34 |
"__type": "AddedToken",
|
| 35 |
"content": "<|endoftext|>",
|