Fix tokenizer config
Browse files- tokenizer_config.json +13 -11
tokenizer_config.json
CHANGED
|
@@ -1,17 +1,19 @@
|
|
| 1 |
{
|
| 2 |
-
"auto_map": {
|
| 3 |
-
"AutoTokenizer": [
|
| 4 |
-
"tokenization_chatglm.ChatGLMTokenizer",
|
| 5 |
-
null
|
| 6 |
-
]
|
| 7 |
-
},
|
| 8 |
-
"do_lower_case": false,
|
| 9 |
-
"model_max_length": 2048,
|
| 10 |
"name_or_path": "THUDM/chatglm-6b",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"pad_token": "<pad>",
|
| 12 |
-
"
|
| 13 |
"remove_space": false,
|
| 14 |
-
"
|
| 15 |
"tokenizer_class": "ChatGLMTokenizer",
|
| 16 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"name_or_path": "THUDM/chatglm-6b",
|
| 3 |
+
"bos_token": "<sop>",
|
| 4 |
+
"eop_token": "<eop>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"gmask_token": "[gMASK]",
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
"pad_token": "<pad>",
|
| 9 |
+
"unk_token": "<unk>",
|
| 10 |
"remove_space": false,
|
| 11 |
+
"do_lower_case": false,
|
| 12 |
"tokenizer_class": "ChatGLMTokenizer",
|
| 13 |
+
"auto_map": {
|
| 14 |
+
"AutoTokenizer": [
|
| 15 |
+
"tokenization_chatglm.ChatGLMTokenizer",
|
| 16 |
+
null
|
| 17 |
+
]
|
| 18 |
+
}
|
| 19 |
}
|