Upload tokenizer
Browse files- added_tokens.json +13 -0
- merges.txt +0 -0
- special_tokens_map.json +18 -0
- tokenizer.json +0 -0
- tokenizer_config.json +10 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
">>ABSTRACT<<": 50258,
|
| 3 |
+
">>ANSWER<<": 50262,
|
| 4 |
+
">>COMMENT<<": 50261,
|
| 5 |
+
">>DOMAIN<<": 50264,
|
| 6 |
+
">>INTRODUCTION<<": 50259,
|
| 7 |
+
">>MIDDLE<<": 50267,
|
| 8 |
+
">>PREFIX<<": 50265,
|
| 9 |
+
">>QUESTION<<": 50263,
|
| 10 |
+
">>SUFFIX<<": 50266,
|
| 11 |
+
">>SUMMARY<<": 50260,
|
| 12 |
+
">>TITLE<<": 50257
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
">>TITLE<<",
|
| 4 |
+
">>ABSTRACT<<",
|
| 5 |
+
">>INTRODUCTION<<",
|
| 6 |
+
">>SUMMARY<<",
|
| 7 |
+
">>COMMENT<<",
|
| 8 |
+
">>ANSWER<<",
|
| 9 |
+
">>QUESTION<<",
|
| 10 |
+
">>DOMAIN<<",
|
| 11 |
+
">>PREFIX<<",
|
| 12 |
+
">>SUFFIX<<",
|
| 13 |
+
">>MIDDLE<<"
|
| 14 |
+
],
|
| 15 |
+
"bos_token": "<|endoftext|>",
|
| 16 |
+
"eos_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": "<|endoftext|>"
|
| 18 |
+
}
|
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_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 1024,
|
| 6 |
+
"name_or_path": "gpt2",
|
| 7 |
+
"special_tokens_map_file": null,
|
| 8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 9 |
+
"unk_token": "<|endoftext|>"
|
| 10 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|