Upload tokenizer
Browse files- tokenizer.json +6 -1
- tokenizer_config.json +4 -0
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": "Right",
|
| 5 |
+
"max_length": 512,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
tokenizer_config.json
CHANGED
|
@@ -16,10 +16,14 @@
|
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false
|
| 18 |
},
|
|
|
|
| 19 |
"model_max_length": 1000000000000000019884624838656,
|
| 20 |
"pad_token": null,
|
| 21 |
"sp_model_kwargs": {},
|
|
|
|
| 22 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
| 23 |
"unk_token": {
|
| 24 |
"__type": "AddedToken",
|
| 25 |
"content": "<unk>",
|
|
|
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false
|
| 18 |
},
|
| 19 |
+
"max_length": 512,
|
| 20 |
"model_max_length": 1000000000000000019884624838656,
|
| 21 |
"pad_token": null,
|
| 22 |
"sp_model_kwargs": {},
|
| 23 |
+
"stride": 0,
|
| 24 |
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
+
"truncation_side": "right",
|
| 26 |
+
"truncation_strategy": "longest_first",
|
| 27 |
"unk_token": {
|
| 28 |
"__type": "AddedToken",
|
| 29 |
"content": "<unk>",
|