Upload tokenizer
Browse files- tokenizer.model +3 -0
- tokenizer_config.json +6 -25
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
|
@@ -25,23 +27,9 @@
|
|
| 25 |
"special": true
|
| 26 |
}
|
| 27 |
},
|
| 28 |
-
"bos_token":
|
| 29 |
-
"__type": "AddedToken",
|
| 30 |
-
"content": "<s>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": true,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false
|
| 35 |
-
},
|
| 36 |
"clean_up_tokenization_spaces": false,
|
| 37 |
-
"eos_token":
|
| 38 |
-
"__type": "AddedToken",
|
| 39 |
-
"content": "</s>",
|
| 40 |
-
"lstrip": false,
|
| 41 |
-
"normalized": true,
|
| 42 |
-
"rstrip": false,
|
| 43 |
-
"single_word": false
|
| 44 |
-
},
|
| 45 |
"legacy": false,
|
| 46 |
"model_max_length": 1000000000000000019884624838656,
|
| 47 |
"pad_token": null,
|
|
@@ -49,13 +37,6 @@
|
|
| 49 |
"sp_model_kwargs": {},
|
| 50 |
"spaces_between_special_tokens": false,
|
| 51 |
"tokenizer_class": "LlamaTokenizer",
|
| 52 |
-
"unk_token":
|
| 53 |
-
|
| 54 |
-
"content": "<unk>",
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"normalized": true,
|
| 57 |
-
"rstrip": false,
|
| 58 |
-
"single_word": false
|
| 59 |
-
},
|
| 60 |
-
"use_default_system_prompt": true
|
| 61 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
|
|
| 27 |
"special": true
|
| 28 |
}
|
| 29 |
},
|
| 30 |
+
"bos_token": "<s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
"legacy": false,
|
| 34 |
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
"pad_token": null,
|
|
|
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
"spaces_between_special_tokens": false,
|
| 39 |
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"unk_token": "<unk>",
|
| 41 |
+
"use_default_system_prompt": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
}
|