Upload 4 files
Browse files- special_tokens_map.json +0 -7
- tokenizer.json +0 -0
- tokenizer_config.json +6 -6
special_tokens_map.json
CHANGED
@@ -13,13 +13,6 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<unk>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
"unk_token": {
|
24 |
"content": "<unk>",
|
25 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
"lstrip": false,
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
-
"add_prefix_space":
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
@@ -28,17 +28,17 @@
|
|
28 |
"special": true
|
29 |
}
|
30 |
},
|
|
|
31 |
"bos_token": "<s>",
|
|
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
-
"legacy":
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
36 |
-
"pad_token":
|
37 |
-
"padding_side": "right",
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
41 |
"unk_token": "<unk>",
|
42 |
-
"use_default_system_prompt": false
|
43 |
-
"chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}"
|
44 |
}
|
|
|
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>",
|
|
|
28 |
"special": true
|
29 |
}
|
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": null,
|
|
|
39 |
"sp_model_kwargs": {},
|
40 |
"spaces_between_special_tokens": false,
|
41 |
"tokenizer_class": "LlamaTokenizer",
|
42 |
"unk_token": "<unk>",
|
43 |
+
"use_default_system_prompt": false
|
|
|
44 |
}
|