Upload 5 files
Browse files- merges.txt +0 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -21
- vocab.json +0 -0
merges.txt
CHANGED
|
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": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,26 +1,20 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
-
"bos_token":
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
"
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"clean_up_tokenization_spaces": true,
|
| 13 |
-
"eos_token": "<|endoftext|>",
|
| 14 |
-
"errors": "replace",
|
| 15 |
"model_max_length": 2048,
|
| 16 |
-
"
|
| 17 |
-
|
| 18 |
-
"unk_token": {
|
| 19 |
-
"__type": "AddedToken",
|
| 20 |
-
"content": "<|endoftext|>",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": true,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false
|
| 25 |
-
}
|
| 26 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"unk_token": "<unk>",
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"additional_special_tokens": [
|
| 10 |
+
"<code>",
|
| 11 |
+
"</code>",
|
| 12 |
+
"<error_message>",
|
| 13 |
+
"</error_message>",
|
| 14 |
+
"<description>",
|
| 15 |
+
"</description>"
|
| 16 |
+
],
|
| 17 |
"clean_up_tokenization_spaces": true,
|
|
|
|
|
|
|
| 18 |
"model_max_length": 2048,
|
| 19 |
+
"tokenizer_class": "GPT2Tokenizer"
|
| 20 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|