Commit
•
9b0d18a
1
Parent(s):
5bd42f3
Upload tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": "<|endoftext|>",
|
| 3 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 4 |
"unk_token": "<|endoftext|>"
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token": "<|endoftext|>",
|
| 3 |
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
"unk_token": "<|endoftext|>"
|
| 6 |
}
|
tokenizer_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
-
"model_max_length":
|
| 7 |
"tokenizer_class": "GPTNeoXTokenizer",
|
| 8 |
"unk_token": "<|endoftext|>"
|
| 9 |
}
|
|
|
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 8192,
|
| 7 |
"tokenizer_class": "GPTNeoXTokenizer",
|
| 8 |
"unk_token": "<|endoftext|>"
|
| 9 |
}
|