Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +10 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<eos>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"sep_token": "[sep]",
|
| 6 |
+
"unk_token": "<|endoftext|>"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_eos_token": true,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"clean_up_tokenization_spaces": true,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"model_max_length": 2048,
|
| 8 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 9 |
+
"unk_token": "<|endoftext|>"
|
| 10 |
+
}
|