Upload folder using huggingface_hub
Browse files- special_tokens.json +30 -0
- tokenizer.json +2 -2
- tokenizer_config.json +2 -2
special_tokens.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[gMASK]<sop>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|im_end|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<pad>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb5562ccf79706a921cedd2f11ccd745d433510cb10cce132f8432760349a705
|
| 3 |
+
size 17078414
|
tokenizer_config.json
CHANGED
|
@@ -12,7 +12,7 @@
|
|
| 12 |
"special": true
|
| 13 |
},
|
| 14 |
"1": {
|
| 15 |
-
"content": "<
|
| 16 |
"lstrip": false,
|
| 17 |
"normalized": false,
|
| 18 |
"rstrip": false,
|
|
@@ -8004,7 +8004,7 @@
|
|
| 8004 |
"special": true
|
| 8005 |
}
|
| 8006 |
},
|
| 8007 |
-
"bos_token": "<
|
| 8008 |
"clean_up_tokenization_spaces": false,
|
| 8009 |
"eos_token": "<|im_end|>",
|
| 8010 |
"extra_special_tokens": {},
|
|
|
|
| 12 |
"special": true
|
| 13 |
},
|
| 14 |
"1": {
|
| 15 |
+
"content": "[gMASK]<sop>",
|
| 16 |
"lstrip": false,
|
| 17 |
"normalized": false,
|
| 18 |
"rstrip": false,
|
|
|
|
| 8004 |
"special": true
|
| 8005 |
}
|
| 8006 |
},
|
| 8007 |
+
"bos_token": "[gMASK]<sop>",
|
| 8008 |
"clean_up_tokenization_spaces": false,
|
| 8009 |
"eos_token": "<|im_end|>",
|
| 8010 |
"extra_special_tokens": {},
|