Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +5 -27
tokenizer_config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
"add_bos_token": false,
|
3 |
"add_eos_token": false,
|
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
@@ -9,38 +10,15 @@
|
|
9 |
"rstrip": false,
|
10 |
"single_word": false,
|
11 |
"special": true
|
12 |
-
},
|
13 |
-
"1": {
|
14 |
-
"content": "<|startoftext|>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": false,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false,
|
19 |
-
"special": true
|
20 |
-
},
|
21 |
-
"2": {
|
22 |
-
"content": "<|endoftext|>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": false,
|
25 |
-
"rstrip": false,
|
26 |
-
"single_word": false,
|
27 |
-
"special": true
|
28 |
}
|
29 |
},
|
30 |
-
"bos_token":
|
|
|
31 |
"clean_up_tokenization_spaces": false,
|
32 |
-
"eos_token":
|
33 |
"legacy": true,
|
34 |
-
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<fim_prefix><|img|><fim_suffix>{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
36 |
-
"pad_token":
|
37 |
-
"__type": "AddedToken",
|
38 |
-
"content": "<unk>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": true,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false
|
43 |
-
},
|
44 |
"sp_model_kwargs": {},
|
45 |
"spaces_between_special_tokens": false,
|
46 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
1 |
{
|
2 |
"add_bos_token": false,
|
3 |
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
|
|
10 |
"rstrip": false,
|
11 |
"single_word": false,
|
12 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
}
|
14 |
},
|
15 |
+
"bos_token": null,
|
16 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<fim_prefix><|img|><fim_suffix>{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
17 |
"clean_up_tokenization_spaces": false,
|
18 |
+
"eos_token": null,
|
19 |
"legacy": true,
|
|
|
20 |
"model_max_length": 1000000000000000019884624838656,
|
21 |
+
"pad_token": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
"sp_model_kwargs": {},
|
23 |
"spaces_between_special_tokens": false,
|
24 |
"tokenizer_class": "LlamaTokenizer",
|