Upload tokenizer
Browse files- special_tokens_map.json +3 -3
- tokenizer_config.json +6 -4
special_tokens_map.json
CHANGED
|
@@ -60,14 +60,14 @@
|
|
| 60 |
"bos_token": {
|
| 61 |
"content": "<s>",
|
| 62 |
"lstrip": false,
|
| 63 |
-
"normalized":
|
| 64 |
"rstrip": false,
|
| 65 |
"single_word": false
|
| 66 |
},
|
| 67 |
"eos_token": {
|
| 68 |
"content": "</s>",
|
| 69 |
"lstrip": false,
|
| 70 |
-
"normalized":
|
| 71 |
"rstrip": false,
|
| 72 |
"single_word": false
|
| 73 |
},
|
|
@@ -75,7 +75,7 @@
|
|
| 75 |
"unk_token": {
|
| 76 |
"content": "<unk>",
|
| 77 |
"lstrip": false,
|
| 78 |
-
"normalized":
|
| 79 |
"rstrip": false,
|
| 80 |
"single_word": false
|
| 81 |
}
|
|
|
|
| 60 |
"bos_token": {
|
| 61 |
"content": "<s>",
|
| 62 |
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
"rstrip": false,
|
| 65 |
"single_word": false
|
| 66 |
},
|
| 67 |
"eos_token": {
|
| 68 |
"content": "</s>",
|
| 69 |
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
"rstrip": false,
|
| 72 |
"single_word": false
|
| 73 |
},
|
|
|
|
| 75 |
"unk_token": {
|
| 76 |
"content": "<unk>",
|
| 77 |
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
"rstrip": false,
|
| 80 |
"single_word": false
|
| 81 |
}
|
tokenizer_config.json
CHANGED
|
@@ -1,9 +1,11 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"__type": "AddedToken",
|
| 4 |
"content": "<s>",
|
| 5 |
"lstrip": false,
|
| 6 |
-
"normalized":
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false
|
| 9 |
},
|
|
@@ -12,12 +14,12 @@
|
|
| 12 |
"__type": "AddedToken",
|
| 13 |
"content": "</s>",
|
| 14 |
"lstrip": false,
|
| 15 |
-
"normalized":
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false
|
| 18 |
},
|
| 19 |
"legacy": false,
|
| 20 |
-
"model_max_length":
|
| 21 |
"pad_token": null,
|
| 22 |
"sp_model_kwargs": {},
|
| 23 |
"tokenizer_class": "LlamaTokenizer",
|
|
@@ -25,7 +27,7 @@
|
|
| 25 |
"__type": "AddedToken",
|
| 26 |
"content": "<unk>",
|
| 27 |
"lstrip": false,
|
| 28 |
-
"normalized":
|
| 29 |
"rstrip": false,
|
| 30 |
"single_word": false
|
| 31 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"bos_token": {
|
| 5 |
"__type": "AddedToken",
|
| 6 |
"content": "<s>",
|
| 7 |
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "</s>",
|
| 16 |
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
"legacy": false,
|
| 22 |
+
"model_max_length": 2048,
|
| 23 |
"pad_token": null,
|
| 24 |
"sp_model_kwargs": {},
|
| 25 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 27 |
"__type": "AddedToken",
|
| 28 |
"content": "<unk>",
|
| 29 |
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false
|
| 33 |
}
|