Upload tokenizer
Browse files- special_tokens_map.json +7 -1
- tokenizer.json +1 -6
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -13,7 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 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 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
tokenizer_config.json
CHANGED
|
@@ -125,7 +125,7 @@
|
|
| 125 |
"model_max_length": 131072,
|
| 126 |
"pad_token": "<|endoftext|>",
|
| 127 |
"padding": true,
|
| 128 |
-
"padding_side": "
|
| 129 |
"sp_model_kwargs": {},
|
| 130 |
"tokenizer_class": "LlamaTokenizer",
|
| 131 |
"truncation": true,
|
|
|
|
| 125 |
"model_max_length": 131072,
|
| 126 |
"pad_token": "<|endoftext|>",
|
| 127 |
"padding": true,
|
| 128 |
+
"padding_side": "left",
|
| 129 |
"sp_model_kwargs": {},
|
| 130 |
"tokenizer_class": "LlamaTokenizer",
|
| 131 |
"truncation": true,
|