Switch from PreTrainedTokenizerFast to GPT2TokenizerFast and add eos_token & bos_token (#15)
Browse files- Switch from PreTrainedTokenizerFast to GPT2TokenizerFast and add eos_token & bos_token (d63779a667c4e0bd0d06f385b407c0c649b36454)
- tokenizer_config.json +4 -2
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"errors": "replace",
|
| 3 |
-
"tokenizer_class": "
|
|
|
|
|
|
|
| 4 |
"model_max_length": 2048
|
| 5 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
"errors": "replace",
|
| 3 |
+
"tokenizer_class": "GPT2TokenizerFast",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
"model_max_length": 2048
|
| 7 |
+
}
|