Fix tokenizer files
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +8 -12
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -4,32 +4,31 @@
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
7 |
-
"lstrip":
|
8 |
"normalized": false,
|
9 |
-
"rstrip":
|
10 |
"single_word": false,
|
11 |
"special": true
|
12 |
},
|
13 |
"1": {
|
14 |
"content": "<s>",
|
15 |
-
"lstrip":
|
16 |
"normalized": false,
|
17 |
-
"rstrip":
|
18 |
"single_word": false,
|
19 |
"special": true
|
20 |
},
|
21 |
"2": {
|
22 |
"content": "</s>",
|
23 |
-
"lstrip":
|
24 |
"normalized": false,
|
25 |
-
"rstrip":
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
}
|
29 |
},
|
30 |
"additional_special_tokens": [],
|
31 |
"bos_token": "<s>",
|
32 |
-
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
"legacy": true,
|
@@ -38,9 +37,6 @@
|
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
41 |
-
"tokenizer_file": "/workspace/.cache/hf/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/d635d39671aaceec5ef84b745bc21625b324b7f8/tokenizer.json",
|
42 |
-
"trust_remote_code": false,
|
43 |
"unk_token": "<unk>",
|
44 |
-
"use_default_system_prompt": true
|
45 |
-
|
46 |
-
}
|
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
"single_word": false,
|
11 |
"special": true
|
12 |
},
|
13 |
"1": {
|
14 |
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
"single_word": false,
|
19 |
"special": true
|
20 |
},
|
21 |
"2": {
|
22 |
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
"normalized": false,
|
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,
|
|
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
40 |
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": true
|
42 |
+
}
|
|