andreaskoepf
commited on
Commit
•
2b04144
1
Parent(s):
7ce34f1
Upload tokenizer
Browse files- special_tokens_map.json +14 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|prefix_end|>",
|
4 |
+
"<|assistant|>",
|
5 |
+
"<|system|>",
|
6 |
+
"<|prompter|>",
|
7 |
+
"<|prefix_begin|>"
|
8 |
+
],
|
9 |
+
"bos_token": "<|endoftext|>",
|
10 |
+
"eos_token": "<|endoftext|>",
|
11 |
+
"pad_token": "<|padding|>",
|
12 |
+
"sep_token": "<|endoftext|>",
|
13 |
+
"unk_token": "<|endoftext|>"
|
14 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|