updated tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.model +2 -2
- tokenizer_config.json +40 -24
special_tokens_map.json
CHANGED
|
@@ -13,6 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
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:d67cd5bb8170cf2af9d4bce126af808633773a743361aea8b0050d6eb0e5622b
|
| 3 |
+
size 967552
|
tokenizer_config.json
CHANGED
|
@@ -1,34 +1,50 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
},
|
|
|
|
| 12 |
"clean_up_tokenization_spaces": false,
|
| 13 |
-
"eos_token":
|
| 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": 1000000000000000019884624838656,
|
| 23 |
-
"pad_token":
|
| 24 |
"sp_model_kwargs": {},
|
|
|
|
| 25 |
"tokenizer_class": "LlamaTokenizer",
|
| 26 |
-
"unk_token":
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": true,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false
|
| 33 |
-
}
|
| 34 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "[PAD]",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
}
|
| 37 |
},
|
| 38 |
+
"bos_token": "<s>",
|
| 39 |
"clean_up_tokenization_spaces": false,
|
| 40 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
"legacy": false,
|
| 42 |
"model_max_length": 1000000000000000019884624838656,
|
| 43 |
+
"pad_token": "[PAD]",
|
| 44 |
"sp_model_kwargs": {},
|
| 45 |
+
"spaces_between_special_tokens": false,
|
| 46 |
"tokenizer_class": "LlamaTokenizer",
|
| 47 |
+
"unk_token": "<unk>",
|
| 48 |
+
"use_default_system_prompt": false,
|
| 49 |
+
"use_fast": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
}
|