Upload tokenizer
Browse files- added_tokens.json +6 -0
- special_tokens_map.json +11 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"xEffect": 32001,
|
| 3 |
+
"xIntent": 32002,
|
| 4 |
+
"xNeed": 32000,
|
| 5 |
+
"xReact": 32003
|
| 6 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"xNeed",
|
| 4 |
+
"xEffect",
|
| 5 |
+
"xIntent",
|
| 6 |
+
"xReact"
|
| 7 |
+
],
|
| 8 |
+
"eos_token": "</s>",
|
| 9 |
+
"pad_token": "</s>",
|
| 10 |
+
"unk_token": "<unk>"
|
| 11 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33ce6c35a3f5a3028975f75c05eeda077e6ac96e49894778b19296280566132d
|
| 3 |
+
size 812016
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [],
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"name_or_path": "output_gpt2_3epoch",
|
| 5 |
+
"sp_model_kwargs": {},
|
| 6 |
+
"special_tokens_map_file": "/home/t-ide/.cache/huggingface/hub/models--nlp-waseda--gpt2-small-japanese/snapshots/2d14ed0652612483b331291b7b25731e5cd70d76/special_tokens_map.json",
|
| 7 |
+
"tokenizer_class": "ReformerTokenizer",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|