Commit
•
43a614c
1
Parent(s):
adf9138
Upload tokenizer
Browse files- special_tokens_map.json +8 -23
- tokenizer.model +1 -1
- tokenizer_config.json +6 -0
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,10 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
|
@@ -20,29 +26,8 @@
|
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
-
"
|
| 24 |
-
"content": "
|
| 25 |
-
"lstrip": false,
|
| 26 |
-
"normalized": true,
|
| 27 |
-
"rstrip": false,
|
| 28 |
-
"single_word": false
|
| 29 |
-
},
|
| 30 |
-
"sep_token": {
|
| 31 |
-
"content": "<|sep|>",
|
| 32 |
-
"lstrip": false,
|
| 33 |
-
"normalized": true,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false
|
| 36 |
-
},
|
| 37 |
-
"eot_token": {
|
| 38 |
-
"content": "<|eot|>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": true,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false
|
| 43 |
-
},
|
| 44 |
-
"output_token": {
|
| 45 |
-
"content": "<|output|>",
|
| 46 |
"lstrip": false,
|
| 47 |
"normalized": true,
|
| 48 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|spcout|>",
|
| 4 |
+
"<|sep|>",
|
| 5 |
+
"<|eot|>",
|
| 6 |
+
"<|output|>"
|
| 7 |
+
],
|
| 8 |
"bos_token": {
|
| 9 |
"content": "<s>",
|
| 10 |
"lstrip": false,
|
|
|
|
| 26 |
"rstrip": false,
|
| 27 |
"single_word": false
|
| 28 |
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
"lstrip": false,
|
| 32 |
"normalized": true,
|
| 33 |
"rstrip": false,
|
tokenizer.model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 787400
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc65134e593a8b5aaac1a9b1154165c4d25d896a8b8c26b5bb4faa445715fe2c
|
| 3 |
size 787400
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_eos_token": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"bos_token": {
|
| 5 |
"__type": "AddedToken",
|
| 6 |
"content": "<s>",
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_eos_token": true,
|
| 4 |
+
"additional_special_tokens": [
|
| 5 |
+
"<|spcout|>",
|
| 6 |
+
"<|sep|>",
|
| 7 |
+
"<|eot|>",
|
| 8 |
+
"<|output|>"
|
| 9 |
+
],
|
| 10 |
"bos_token": {
|
| 11 |
"__type": "AddedToken",
|
| 12 |
"content": "<s>",
|