Commit
•
772e45d
1
Parent(s):
148e7fb
Upload tokenizer
Browse files- added_tokens.json +1 -4
- special_tokens_map.json +0 -6
- tokenizer_config.json +1 -7
added_tokens.json
CHANGED
|
@@ -1,7 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"<MS>": 50260,
|
| 3 |
-
"<N>": 50259,
|
| 4 |
"<|pad|>": 50258,
|
| 5 |
-
"<|startoftext|>": 50257
|
| 6 |
-
"VJ": 50261
|
| 7 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"<|pad|>": 50258,
|
| 3 |
+
"<|startoftext|>": 50257
|
|
|
|
| 4 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,10 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<N>",
|
| 4 |
-
"<MS>",
|
| 5 |
-
"RB",
|
| 6 |
-
"VJ"
|
| 7 |
-
],
|
| 8 |
"bos_token": {
|
| 9 |
"content": "<|startoftext|>",
|
| 10 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<|startoftext|>",
|
| 4 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -1,12 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
-
"additional_special_tokens": [
|
| 5 |
-
"<N>",
|
| 6 |
-
"<MS>",
|
| 7 |
-
"RB",
|
| 8 |
-
"VJ"
|
| 9 |
-
],
|
| 10 |
"bos_token": {
|
| 11 |
"__type": "AddedToken",
|
| 12 |
"content": "<|startoftext|>",
|
|
@@ -25,7 +19,7 @@
|
|
| 25 |
},
|
| 26 |
"errors": "replace",
|
| 27 |
"model_max_length": 2048,
|
| 28 |
-
"name_or_path": "
|
| 29 |
"pad_token": {
|
| 30 |
"__type": "AddedToken",
|
| 31 |
"content": "<|pad|>",
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"bos_token": {
|
| 5 |
"__type": "AddedToken",
|
| 6 |
"content": "<|startoftext|>",
|
|
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 2048,
|
| 22 |
+
"name_or_path": "../saved_models/gptNEO_author_RB_epochs15_lr5e-05/tokenizer",
|
| 23 |
"pad_token": {
|
| 24 |
"__type": "AddedToken",
|
| 25 |
"content": "<|pad|>",
|