Add auto_map so AutoTokenizer.from_pretrained works with trust_remote_code=True
Browse files- tokenizer_config.json +11 -56
tokenizer_config.json
CHANGED
|
@@ -1,61 +1,15 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
-
"0": {
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "[CLS]",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "[SEP]",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"4": {
|
| 36 |
-
"content": "[MASK]",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
},
|
| 43 |
-
"5": {
|
| 44 |
-
"content": "[BOS]",
|
| 45 |
-
"lstrip": false,
|
| 46 |
-
"normalized": false,
|
| 47 |
-
"rstrip": false,
|
| 48 |
-
"single_word": false,
|
| 49 |
-
"special": true
|
| 50 |
-
},
|
| 51 |
-
"6": {
|
| 52 |
-
"content": "[EOS]",
|
| 53 |
-
"lstrip": false,
|
| 54 |
-
"normalized": false,
|
| 55 |
-
"rstrip": false,
|
| 56 |
-
"single_word": false,
|
| 57 |
-
"special": true
|
| 58 |
-
}
|
| 59 |
},
|
| 60 |
"k": 1,
|
| 61 |
"bos_token": "[BOS]",
|
|
@@ -67,5 +21,6 @@
|
|
| 67 |
"model_max_length": 2048,
|
| 68 |
"pad_token": "[PAD]",
|
| 69 |
"sep_token": "[SEP]",
|
|
|
|
| 70 |
"unk_token": "[UNK]"
|
| 71 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
+
"0": {"content": "[PAD]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
|
| 4 |
+
"1": {"content": "[UNK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
|
| 5 |
+
"2": {"content": "[CLS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
|
| 6 |
+
"3": {"content": "[SEP]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
|
| 7 |
+
"4": {"content": "[MASK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
|
| 8 |
+
"5": {"content": "[BOS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
|
| 9 |
+
"6": {"content": "[EOS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}
|
| 10 |
+
},
|
| 11 |
+
"auto_map": {
|
| 12 |
+
"AutoTokenizer": ["tokenizer.NucEL_Tokenizer", null]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
},
|
| 14 |
"k": 1,
|
| 15 |
"bos_token": "[BOS]",
|
|
|
|
| 21 |
"model_max_length": 2048,
|
| 22 |
"pad_token": "[PAD]",
|
| 23 |
"sep_token": "[SEP]",
|
| 24 |
+
"tokenizer_class": "NucEL_Tokenizer",
|
| 25 |
"unk_token": "[UNK]"
|
| 26 |
}
|