rishdotblog
commited on
Commit
•
4298176
1
Parent(s):
dc127ec
Upload tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +26 -0
- tokenizer.json +0 -0
- tokenizer_config.json +31 -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 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|endoftext|>",
|
4 |
+
"<fim_prefix>",
|
5 |
+
"<fim_middle>",
|
6 |
+
"<fim_suffix>",
|
7 |
+
"<fim_pad>",
|
8 |
+
"<filename>",
|
9 |
+
"<gh_stars>",
|
10 |
+
"<issue_start>",
|
11 |
+
"<issue_comment>",
|
12 |
+
"<issue_closed>",
|
13 |
+
"<jupyter_start>",
|
14 |
+
"<jupyter_text>",
|
15 |
+
"<jupyter_code>",
|
16 |
+
"<jupyter_output>",
|
17 |
+
"<empty_output>",
|
18 |
+
"<commit_before>",
|
19 |
+
"<commit_msg>",
|
20 |
+
"<commit_after>",
|
21 |
+
"<reponame>"
|
22 |
+
],
|
23 |
+
"bos_token": "<|endoftext|>",
|
24 |
+
"eos_token": "<|endoftext|>",
|
25 |
+
"unk_token": "<|endoftext|>"
|
26 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"additional_special_tokens": [
|
4 |
+
"<|endoftext|>",
|
5 |
+
"<fim_prefix>",
|
6 |
+
"<fim_middle>",
|
7 |
+
"<fim_suffix>",
|
8 |
+
"<fim_pad>",
|
9 |
+
"<filename>",
|
10 |
+
"<gh_stars>",
|
11 |
+
"<issue_start>",
|
12 |
+
"<issue_comment>",
|
13 |
+
"<issue_closed>",
|
14 |
+
"<jupyter_start>",
|
15 |
+
"<jupyter_text>",
|
16 |
+
"<jupyter_code>",
|
17 |
+
"<jupyter_output>",
|
18 |
+
"<empty_output>",
|
19 |
+
"<commit_before>",
|
20 |
+
"<commit_msg>",
|
21 |
+
"<commit_after>",
|
22 |
+
"<reponame>"
|
23 |
+
],
|
24 |
+
"bos_token": "<|endoftext|>",
|
25 |
+
"clean_up_tokenization_spaces": true,
|
26 |
+
"eos_token": "<|endoftext|>",
|
27 |
+
"model_max_length": 1000000000000000019884624838656,
|
28 |
+
"tokenizer_class": "GPT2Tokenizer",
|
29 |
+
"unk_token": "<|endoftext|>",
|
30 |
+
"vocab_size": 49152
|
31 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|