Commit
•
8359238
1
Parent(s):
8c947cd
Upload tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- vocab.json +0 -0
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"max_length": 32,
|
7 |
+
"model_max_length": 1024,
|
8 |
+
"pad_to_multiple_of": null,
|
9 |
+
"pad_token": "<|endoftext|>",
|
10 |
+
"pad_token_type_id": 0,
|
11 |
+
"padding_side": "left",
|
12 |
+
"stride": 0,
|
13 |
+
"tokenizer_class": "GPT2Tokenizer",
|
14 |
+
"truncation_side": "right",
|
15 |
+
"truncation_strategy": "longest_first",
|
16 |
+
"unk_token": "<|endoftext|>"
|
17 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|