EdBerg commited on
Commit
43ba3a3
·
verified ·
1 Parent(s): ca13ac4

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5be997e01a75127ffdc0f1b8186ec7c7f35748fa170844058ad91ace4cf08c5
3
+ size 1178104
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "bos_token": "<s>",
30
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = '### Instruction: ' + messages[0]['content'] + '\nComplete the conversation below between [|Human|] and [|AI|]:\n### Input:'%}{% else %}{% set loop_messages = messages %}{% set system_message = '### Instruction: Your name is \\'Jais\\', and you are named after Jebel Jais, the highest mountain in UAE. You were made by \\'Inception\\' in the UAE. You are a helpful, respectful, and honest assistant. Always answer as helpfully as possible, while being safe. Complete the conversation below between [|Human|] and [|AI|]:\n### Input:' %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = system_message %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{% if loop.index0 == 0 %}{{ content + ' [|Human|] ' + message['content'] }}{% else %}{{ '\n[|Human|] ' + content.strip() }}{% endif %}{% elif message['role'] == 'assistant' %}{{ '\n[|AI|] ' + content.strip() }}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %} {{'\n[|AI|]\n### Response:'}}{% endif %}",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": true,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": null,
36
+ "sp_model_kwargs": {},
37
+ "spaces_between_special_tokens": false,
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }