chengregy commited on
Commit
97d0d3a
·
verified ·
1 Parent(s): d99e747

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

special_tokens_map.json CHANGED
@@ -1,30 +1,6 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
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,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "eos_token": "<|im_end|>",
4
+ "pad_token": "<unk>",
5
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
tokenizer.json CHANGED
@@ -23,7 +23,7 @@
23
  },
24
  {
25
  "id": 2,
26
- "content": "</s>",
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
@@ -138,7 +138,7 @@
138
  "vocab": {
139
  "<unk>": 0,
140
  "<s>": 1,
141
- "</s>": 2,
142
  "<0x00>": 3,
143
  "<0x01>": 4,
144
  "<0x02>": 5,
 
23
  },
24
  {
25
  "id": 2,
26
+ "content": "<|im_end|>",
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
 
138
  "vocab": {
139
  "<unk>": 0,
140
  "<s>": 1,
141
+ "<|im_end|>": 2,
142
  "<0x00>": 3,
143
  "<0x01>": 4,
144
  "<0x02>": 5,
tokenizer_config.json CHANGED
@@ -19,7 +19,7 @@
19
  "special": true
20
  },
21
  "2": {
22
- "content": "</s>",
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
@@ -28,16 +28,13 @@
28
  }
29
  },
30
  "bos_token": "<s>",
31
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'].strip() %}{% else %}{% set loop_messages = messages %}{% set system_message = '你是人工智慧助理,以下是用戶和人工智能助理之間的對話。你要對用戶的問題提供有用、安全、詳細和禮貌的回答。' %}{% endif %}{{system_message + eos_token}}{% for message in loop_messages %}{% if message['role'] == 'user' %}USER: {{ message['content'].strip() + eos_token }}{% elif message['role'] == 'system' %}{{message['content'].strip() + eos_token}}{% elif message['role'] == 'assistant' %}ASSISTANT: {{ message['content'].strip() + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{'ASSISTANT:'}}{% endif %}",
32
  "clean_up_tokenization_spaces": false,
33
- "eos_token": "</s>",
34
- "legacy": false,
35
- "model_max_length": 4096,
36
  "pad_token": "<unk>",
37
- "padding_side": "left",
38
- "sp_model_kwargs": {},
39
- "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
41
  "unk_token": "<unk>",
42
- "use_default_system_prompt": true
43
  }
 
19
  "special": true
20
  },
21
  "2": {
22
+ "content": "<|im_end|>",
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
 
28
  }
29
  },
30
  "bos_token": "<s>",
31
+ "chat_template": "{{ bos_token }}{{ 'You are a helpful assistant to the user\n' }}{% for message in messages %}{% if message['from'] == 'human' %}{{ '>>> User: ' + message['value'] + '\n' }}{% elif message['from'] == 'gpt' %}{{ '>>> Assistant: ' + message['value'] + eos_token + '\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '>>> Assistant: ' }}{% endif %}",
32
  "clean_up_tokenization_spaces": false,
33
+ "eos_token": "<|im_end|>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
  "pad_token": "<unk>",
 
 
 
37
  "tokenizer_class": "LlamaTokenizer",
38
  "unk_token": "<unk>",
39
+ "use_default_system_prompt": false
40
  }