Upload tokenizer
Browse files- special_tokens_map.json +3 -10
- tokenizer.json +0 -27
- tokenizer_config.json +3 -33
special_tokens_map.json
CHANGED
|
@@ -1,11 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<unk>",
|
| 4 |
-
"<s>",
|
| 5 |
-
"</s>",
|
| 6 |
-
"<|assistant|>",
|
| 7 |
-
"<|prompter|>"
|
| 8 |
-
],
|
| 9 |
"bos_token": {
|
| 10 |
"content": "<s>",
|
| 11 |
"lstrip": false,
|
|
@@ -21,10 +14,10 @@
|
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"pad_token": {
|
| 24 |
-
"content": "
|
| 25 |
-
"lstrip":
|
| 26 |
"normalized": false,
|
| 27 |
-
"rstrip":
|
| 28 |
"single_word": false
|
| 29 |
},
|
| 30 |
"unk_token": {
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
|
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"unk_token": {
|
tokenizer.json
CHANGED
|
@@ -29,33 +29,6 @@
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"id": 32000,
|
| 35 |
-
"content": "[PAD]",
|
| 36 |
-
"single_word": false,
|
| 37 |
-
"lstrip": true,
|
| 38 |
-
"rstrip": true,
|
| 39 |
-
"normalized": false,
|
| 40 |
-
"special": true
|
| 41 |
-
},
|
| 42 |
-
{
|
| 43 |
-
"id": 32001,
|
| 44 |
-
"content": "<|assistant|>",
|
| 45 |
-
"single_word": false,
|
| 46 |
-
"lstrip": true,
|
| 47 |
-
"rstrip": true,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"special": true
|
| 50 |
-
},
|
| 51 |
-
{
|
| 52 |
-
"id": 32002,
|
| 53 |
-
"content": "<|prompter|>",
|
| 54 |
-
"single_word": false,
|
| 55 |
-
"lstrip": true,
|
| 56 |
-
"rstrip": true,
|
| 57 |
-
"normalized": false,
|
| 58 |
-
"special": true
|
| 59 |
}
|
| 60 |
],
|
| 61 |
"normalizer": {
|
|
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
}
|
| 33 |
],
|
| 34 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -25,50 +25,20 @@
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
-
},
|
| 29 |
-
"32000": {
|
| 30 |
-
"content": "[PAD]",
|
| 31 |
-
"lstrip": true,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": true,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"32001": {
|
| 38 |
-
"content": "<|assistant|>",
|
| 39 |
-
"lstrip": true,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": true,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
-
},
|
| 45 |
-
"32002": {
|
| 46 |
-
"content": "<|prompter|>",
|
| 47 |
-
"lstrip": true,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": true,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": true
|
| 52 |
}
|
| 53 |
},
|
| 54 |
-
"additional_special_tokens": [
|
| 55 |
-
"<unk>",
|
| 56 |
-
"<s>",
|
| 57 |
-
"</s>",
|
| 58 |
-
"<|assistant|>",
|
| 59 |
-
"<|prompter|>"
|
| 60 |
-
],
|
| 61 |
"bos_token": "<s>",
|
| 62 |
"clean_up_tokenization_spaces": false,
|
| 63 |
"eos_token": "</s>",
|
| 64 |
"legacy": true,
|
| 65 |
"model_max_length": 1000000000000000019884624838656,
|
| 66 |
-
"pad_token": "
|
| 67 |
"sp_model_kwargs": {},
|
| 68 |
"spaces_between_special_tokens": false,
|
| 69 |
"tokenizer_class": "LlamaTokenizer",
|
| 70 |
"trust_remote_code": true,
|
| 71 |
"unk_token": "<unk>",
|
| 72 |
-
"use_default_system_prompt":
|
| 73 |
"use_fast": true
|
| 74 |
}
|
|
|
|
| 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 |
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
+
"pad_token": "</s>",
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
"spaces_between_special_tokens": false,
|
| 39 |
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
"trust_remote_code": true,
|
| 41 |
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false,
|
| 43 |
"use_fast": true
|
| 44 |
}
|