Upload tokenizer (#1)
Browse files- Upload tokenizer (f84d2fe400a7bc474dd84d6967ab694ed1278fba)
Co-authored-by: Younes Belkada <ybelkada@users.noreply.huggingface.co>
- special_tokens_map.json +5 -1
- tokenizer_config.json +5 -1
special_tokens_map.json
CHANGED
|
@@ -1 +1,5 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,9 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"clean_up_tokenization_spaces": true,
|
|
|
|
| 3 |
"model_max_length": 1000000000000000019884624838656,
|
| 4 |
-
"tokenizer_class": "
|
|
|
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 8 |
+
"unk_token": "<|endoftext|>"
|
| 9 |
}
|