Commit
•
e14c52f
1
Parent(s):
1813047
synchronizing tokenizer config
Browse files- tokenizer_config.json +7 -2
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
-
"clean_up_tokenization_spaces": true,
|
| 4 |
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"model_max_length": 2048,
|
|
|
|
|
|
|
| 6 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 7 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
|
|
|
| 3 |
"eos_token": "<|endoftext|>",
|
| 4 |
+
"model_input_names": [
|
| 5 |
+
"input_ids",
|
| 6 |
+
"attention_mask"
|
| 7 |
+
],
|
| 8 |
"model_max_length": 2048,
|
| 9 |
+
"name_or_path": "tiiuae/falcon_tokenizer",
|
| 10 |
+
"special_tokens_map_file": null,
|
| 11 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 12 |
+
}
|