Commit
•
e476087
1
Parent(s):
8c49e87
Upload tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +6 -1
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -6,5 +6,6 @@
|
|
| 6 |
],
|
| 7 |
"bos_token": "<s>",
|
| 8 |
"eos_token": "</s>",
|
|
|
|
| 9 |
"unk_token": "<unk>"
|
| 10 |
}
|
|
|
|
| 6 |
],
|
| 7 |
"bos_token": "<s>",
|
| 8 |
"eos_token": "</s>",
|
| 9 |
+
"pad_token": "<unk>",
|
| 10 |
"unk_token": "<unk>"
|
| 11 |
}
|
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": "Left",
|
| 5 |
+
"max_length": 4096,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
tokenizer_config.json
CHANGED
|
@@ -36,7 +36,7 @@
|
|
| 36 |
"eos_token": "</s>",
|
| 37 |
"legacy": true,
|
| 38 |
"model_max_length": 1000000000000000019884624838656,
|
| 39 |
-
"pad_token":
|
| 40 |
"sp_model_kwargs": {},
|
| 41 |
"spaces_between_special_tokens": false,
|
| 42 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 36 |
"eos_token": "</s>",
|
| 37 |
"legacy": true,
|
| 38 |
"model_max_length": 1000000000000000019884624838656,
|
| 39 |
+
"pad_token": "<unk>",
|
| 40 |
"sp_model_kwargs": {},
|
| 41 |
"spaces_between_special_tokens": false,
|
| 42 |
"tokenizer_class": "LlamaTokenizer",
|