danielhanchen
commited on
Commit
•
c40e781
1
Parent(s):
3974de8
Upload tokenizer
Browse files- tokenizer.json +7 -16
- tokenizer_config.json +5 -4
tokenizer.json
CHANGED
@@ -31,23 +31,13 @@
|
|
31 |
"special": true
|
32 |
}
|
33 |
],
|
34 |
-
"normalizer":
|
35 |
-
|
36 |
-
"
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
},
|
41 |
-
{
|
42 |
-
"type": "Replace",
|
43 |
-
"pattern": {
|
44 |
-
"String": " "
|
45 |
-
},
|
46 |
-
"content": "▁"
|
47 |
-
}
|
48 |
-
]
|
49 |
},
|
50 |
-
"pre_tokenizer": null,
|
51 |
"post_processor": {
|
52 |
"type": "TemplateProcessing",
|
53 |
"single": [
|
@@ -134,6 +124,7 @@
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
|
|
137 |
"vocab": {
|
138 |
"<unk>": 0,
|
139 |
"<s>": 1,
|
|
|
31 |
"special": true
|
32 |
}
|
33 |
],
|
34 |
+
"normalizer": null,
|
35 |
+
"pre_tokenizer": {
|
36 |
+
"type": "Metaspace",
|
37 |
+
"replacement": "▁",
|
38 |
+
"prepend_scheme": "first",
|
39 |
+
"split": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
},
|
|
|
41 |
"post_processor": {
|
42 |
"type": "TemplateProcessing",
|
43 |
"single": [
|
|
|
124 |
"end_of_word_suffix": null,
|
125 |
"fuse_unk": true,
|
126 |
"byte_fallback": true,
|
127 |
+
"ignore_merges": false,
|
128 |
"vocab": {
|
129 |
"<unk>": 0,
|
130 |
"<s>": 1,
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
@@ -29,13 +30,13 @@
|
|
29 |
},
|
30 |
"additional_special_tokens": [],
|
31 |
"bos_token": "<s>",
|
32 |
-
"chat_template": "{{
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
-
"legacy":
|
36 |
-
"model_max_length":
|
37 |
"pad_token": "<unk>",
|
38 |
-
"padding_side": "
|
39 |
"sp_model_kwargs": {},
|
40 |
"spaces_between_special_tokens": false,
|
41 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
|
|
30 |
},
|
31 |
"additional_special_tokens": [],
|
32 |
"bos_token": "<s>",
|
33 |
+
"chat_template": "{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n {%- endif %}\n {%- if message['role'] == 'user' %}\n {%- if loop.first and system_message is defined %}\n {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n {%- else %}\n {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n {%- endif %}\n {%- elif message['role'] == 'assistant' %}\n {{- ' ' + message['content'] + eos_token}}\n {%- else %}\n {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n {%- endif %}\n{%- endfor %}\n",
|
34 |
"clean_up_tokenization_spaces": false,
|
35 |
"eos_token": "</s>",
|
36 |
+
"legacy": false,
|
37 |
+
"model_max_length": 1000000000000000019884624838656,
|
38 |
"pad_token": "<unk>",
|
39 |
+
"padding_side": "left",
|
40 |
"sp_model_kwargs": {},
|
41 |
"spaces_between_special_tokens": false,
|
42 |
"tokenizer_class": "LlamaTokenizer",
|