Upload tokenizer
Browse files- tokenizer.model +2 -2
- tokenizer_config.json +9 -4
tokenizer.model
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 sha256:4be54af290d93c113bcbf421115ae9eed9d6340408f564898f1e966dc738ef01
|
| 3 |
+
size 1136699
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token":
|
| 3 |
"add_eos_token": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"bos_token": {
|
| 5 |
"__type": "AddedToken",
|
| 6 |
"content": "<s>",
|
|
@@ -18,11 +24,10 @@
|
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
-
"model_max_length":
|
| 22 |
"pad_token": null,
|
| 23 |
-
"padding_side": "right",
|
| 24 |
"sp_model_kwargs": {},
|
| 25 |
-
"tokenizer_class": "
|
| 26 |
"unk_token": {
|
| 27 |
"__type": "AddedToken",
|
| 28 |
"content": "<unk>",
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
"add_eos_token": false,
|
| 4 |
+
"auto_map": {
|
| 5 |
+
"AutoTokenizer": [
|
| 6 |
+
"baichuan-inc/baichuan-7B--tokenization_baichuan.BaiChuanTokenizer",
|
| 7 |
+
null
|
| 8 |
+
]
|
| 9 |
+
},
|
| 10 |
"bos_token": {
|
| 11 |
"__type": "AddedToken",
|
| 12 |
"content": "<s>",
|
|
|
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false
|
| 26 |
},
|
| 27 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 28 |
"pad_token": null,
|
|
|
|
| 29 |
"sp_model_kwargs": {},
|
| 30 |
+
"tokenizer_class": "BaiChuanTokenizer",
|
| 31 |
"unk_token": {
|
| 32 |
"__type": "AddedToken",
|
| 33 |
"content": "<unk>",
|