Upload folder using huggingface_hub
Browse files- YunMin-tokenizer-96k.model +3 -0
- YunMin-tokenizer-96k.vocab +0 -0
- config.json +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +8 -0
YunMin-tokenizer-96k.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15a4e5ab876585a64071833b33ceab083c9e3ad3b2e43cfa719e2067540a34d8
|
| 3 |
+
size 2139282
|
YunMin-tokenizer-96k.vocab
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "bert"
|
| 3 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"unk_token": "<unk>",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"pad_token": "<pad>"
|
| 6 |
+
}
|
| 7 |
+
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "sentencepiece",
|
| 3 |
+
"unk_token": "<unk>",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"pad_token": "<pad>"
|
| 7 |
+
}
|
| 8 |
+
|