Undi95 commited on
Commit
e01a265
1 Parent(s): d4139b4

Upload 5 files

Browse files
Files changed (3) hide show
  1. config.json +4 -4
  2. special_tokens_map.json +2 -1
  3. tokenizer_config.json +21 -3
config.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "_name_or_path": "./mistralai_Mixtral-8x7B-Instruct-v0.1",
3
  "architectures": [
4
  "MixtralForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
- "eos_token_id": 2,
9
  "hidden_act": "silu",
10
  "hidden_size": 4096,
11
  "initializer_range": 0.02,
@@ -25,6 +25,6 @@
25
  "tie_word_embeddings": false,
26
  "torch_dtype": "bfloat16",
27
  "transformers_version": "4.37.0.dev0",
28
- "use_cache": true,
29
- "vocab_size": 32000
30
  }
 
1
  {
2
+ "_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
3
  "architectures": [
4
  "MixtralForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
  "hidden_act": "silu",
10
  "hidden_size": 4096,
11
  "initializer_range": 0.02,
 
25
  "tie_word_embeddings": false,
26
  "torch_dtype": "bfloat16",
27
  "transformers_version": "4.37.0.dev0",
28
+ "use_cache": false,
29
+ "vocab_size": 32002
30
  }
special_tokens_map.json CHANGED
@@ -7,12 +7,13 @@
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
  "unk_token": {
17
  "content": "<unk>",
18
  "lstrip": false,
 
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|im_end|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "</s>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -25,19 +25,37 @@
25
  "rstrip": false,
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,
36
  "model_max_length": 1000000000000000019884624838656,
37
- "pad_token": null,
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
  }
 
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
  }
45
  },
46
  "additional_special_tokens": [],
47
  "bos_token": "<s>",
48
  "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 %}",
49
  "clean_up_tokenization_spaces": false,
50
+ "eos_token": "<|im_end|>",
51
  "legacy": true,
52
  "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "</s>",
54
  "sp_model_kwargs": {},
55
  "spaces_between_special_tokens": false,
56
  "tokenizer_class": "LlamaTokenizer",
57
+ "trust_remote_code": false,
58
  "unk_token": "<unk>",
59
+ "use_default_system_prompt": false,
60
+ "use_fast": true
61
  }