Upload tokenizer
Browse files- special_tokens_map.json +3 -21
- tokenizer.json +2 -14
special_tokens_map.json
CHANGED
|
@@ -1,18 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
"lstrip": false,
|
| 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 |
"pad_token": {
|
| 17 |
"content": "[PAD]",
|
| 18 |
"lstrip": false,
|
|
@@ -20,11 +8,5 @@
|
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
-
"unk_token":
|
| 24 |
-
"content": "<|endoftext|>",
|
| 25 |
-
"lstrip": false,
|
| 26 |
-
"normalized": true,
|
| 27 |
-
"rstrip": false,
|
| 28 |
-
"single_word": false
|
| 29 |
-
}
|
| 30 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"pad_token": {
|
| 5 |
"content": "[PAD]",
|
| 6 |
"lstrip": false,
|
|
|
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false
|
| 10 |
},
|
| 11 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
}
|
tokenizer.json
CHANGED
|
@@ -1,19 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 1024,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": "BatchLongest",
|
| 11 |
-
"direction": "Right",
|
| 12 |
-
"pad_to_multiple_of": null,
|
| 13 |
-
"pad_id": 50257,
|
| 14 |
-
"pad_type_id": 0,
|
| 15 |
-
"pad_token": "[PAD]"
|
| 16 |
-
},
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 50256,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50256,
|