Commit
•
7c40c8a
1
Parent(s):
f09efe5
Upload tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +7 -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 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"mask_token": "<mask>",
|
| 5 |
+
"pad_token": "<pad>",
|
| 6 |
+
"unk_token": "<unk>"
|
| 7 |
+
}
|
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 |
+
"add_special_tokens": true,
|
| 4 |
+
"bos_token": "",
|
| 5 |
+
"eos_token": "",
|
| 6 |
+
"mask_token": "",
|
| 7 |
+
"max_len": 42,
|
| 8 |
+
"model_max_length": 42,
|
| 9 |
+
"name_or_path": "skt/ko-gpt-trinity-1.2B-v0.5",
|
| 10 |
+
"pad_token": "",
|
| 11 |
+
"padding": "max_length",
|
| 12 |
+
"return_tensors": "pt",
|
| 13 |
+
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--skt--ko-gpt-trinity-1.2B-v0.5/snapshots/33f84c0da333d34533f0cfbe8f5972022d681e96/special_tokens_map.json",
|
| 14 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 15 |
+
"truncation": true,
|
| 16 |
+
"unk_token": ""
|
| 17 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|