add tokenizer
Browse files- added_tokens.json +4 -0
- merges.txt +0 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +10 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"newWord": 51200,
|
| 3 |
+
"newWord2": 51201
|
| 4 |
+
}
|
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 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "</s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"name_or_path": "skt/ko-gpt-trinity-1.2B-v0.5",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"special_tokens_map_file": "/root/.cache/huggingface/transformers/c2ab65b9d700d0871fd407d489869d7b93f69fb5f1a58fb1fac796fd43b9ea27.1f5b09bb43973b9fbd2ba75c9fe44ffab036b980c4e6a9d779aa7707913416fe",
|
| 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
|
|
|