Upload tokenizer
Browse files- special_tokens_map.json +2 -2
- tokenizer.json +0 -0
- tokenizer.model +2 -2
- tokenizer_config.json +5 -11
special_tokens_map.json
CHANGED
|
@@ -2,14 +2,14 @@
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
-
"normalized":
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
"content": "</s>",
|
| 11 |
"lstrip": false,
|
| 12 |
-
"normalized":
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
"content": "</s>",
|
| 11 |
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
CHANGED
|
@@ -13,7 +13,7 @@
|
|
| 13 |
"1": {
|
| 14 |
"content": "<s>",
|
| 15 |
"lstrip": false,
|
| 16 |
-
"normalized":
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false,
|
| 19 |
"special": true
|
|
@@ -21,29 +21,23 @@
|
|
| 21 |
"2": {
|
| 22 |
"content": "</s>",
|
| 23 |
"lstrip": false,
|
| 24 |
-
"normalized":
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
-
},
|
| 29 |
-
"32000": {
|
| 30 |
-
"content": "<pad>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": true,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": false
|
| 36 |
}
|
| 37 |
},
|
|
|
|
| 38 |
"bos_token": "<s>",
|
| 39 |
"clean_up_tokenization_spaces": false,
|
| 40 |
"eos_token": "</s>",
|
| 41 |
-
"legacy":
|
| 42 |
"max_lenght": 2048,
|
| 43 |
"model_max_length": 1000000000000000019884624838656,
|
| 44 |
"pad_token": "</s>",
|
| 45 |
"padding": true,
|
| 46 |
"sp_model_kwargs": {},
|
|
|
|
| 47 |
"tokenizer_class": "LlamaTokenizer",
|
| 48 |
"unk_token": "<unk>",
|
| 49 |
"use_default_system_prompt": false
|
|
|
|
| 13 |
"1": {
|
| 14 |
"content": "<s>",
|
| 15 |
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false,
|
| 19 |
"special": true
|
|
|
|
| 21 |
"2": {
|
| 22 |
"content": "</s>",
|
| 23 |
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
+
"additional_special_tokens": [],
|
| 31 |
"bos_token": "<s>",
|
| 32 |
"clean_up_tokenization_spaces": false,
|
| 33 |
"eos_token": "</s>",
|
| 34 |
+
"legacy": true,
|
| 35 |
"max_lenght": 2048,
|
| 36 |
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
"pad_token": "</s>",
|
| 38 |
"padding": true,
|
| 39 |
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
"unk_token": "<unk>",
|
| 43 |
"use_default_system_prompt": false
|