halitefe commited on
Commit
2e2d98a
1 Parent(s): c37324c

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|stop|>": 50257,
3
+ "[PAD]": 50258
4
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|stop|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50257": {
14
+ "content": "<|stop|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "50258": {
22
+ "content": "[PAD]",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<|endoftext|>",
31
+ "chat_template": "{% set message_count = messages|length %}{% if message_count >= 4 and messages[-4].role == 'user' %}{% set recent_messages = messages[-4:] %}{% elif message_count > 3 %}{% set recent_messages = messages[-3:] %}{% else %}{% set recent_messages = messages %}{% endif %}{% for message in recent_messages %}{% if message.role == 'user' %}### Kullanıcı:\n{{ message.content }}\n{% elif message.role == 'assistant' %}### Asistan:\n{{ message.content }}\n{% endif %}{% endfor %}{% if messages[-1]['role'] == 'user' %}### Asistan:\n{% endif %}",
32
+ "clean_up_tokenization_spaces": true,
33
+ "eos_token": "<|stop|>",
34
+ "errors": "replace",
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "[PAD]",
37
+ "tokenizer_class": "GPT2Tokenizer",
38
+ "unk_token": "<|endoftext|>"
39
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff