Hugging Face's logo

sbintuitions
/
sarashina2.1-1b

Safetensors
Japanese
English
llama
Model card Files Community
sho-takase commited on
Commit
33911b2
•
1 Parent(s): 233f016

Add model

Browse files
Files changed (6) hide show
  1. .gitattributes +1 -0
  2. config.json +28 -0
  3. generation_config.json +6 -0
  4. model.safetensors +3 -0
  5. tokenizer.model +3 -0
  6. tokenizer_config.json +135 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ model.safetensors filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1792,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 6272,
13
+ "max_position_embeddings": 8192,
14
+ "mlp_bias": false,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 500000,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.40.1",
26
+ "use_cache": true,
27
+ "vocab_size": 102400
28
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.40.1"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e32d4ebb324d16797b4ca1f1902f0d707cf6e5d10a0cadc0d16c10f0ef463dba
3
+ size 2815103168
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:008293028e1a9d9a1038d9b63d989a2319797dfeaa03f171093a57b33a3a8277
3
+ size 1831879
tokenizer_config.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "extra_ids": 0,
3
+ "do_lower_case": false,
4
+ "keep_accents": true,
5
+ "bos_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "unk_token": "<unk>",
8
+ "pad_token": "<pad>",
9
+ "mask_token": "<mask>",
10
+ "cls_token": "<cls>",
11
+ "sep_token": "<sep>",
12
+ "padding_side": "left",
13
+ "sp_model_kwargs": {},
14
+ "special_tokens_map_file": null,
15
+ "tokenizer_class": "LlamaTokenizer",
16
+ "added_tokens_decoder": {
17
+ "4": {
18
+ "content": "<sep>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false,
23
+ "special": false
24
+ },
25
+ "5": {
26
+ "content": "<mask>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false,
31
+ "special": false
32
+ },
33
+ "6": {
34
+ "content": "<cls>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false,
39
+ "special": false
40
+ },
41
+ "7": {
42
+ "content": "<|system|>",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false,
47
+ "special": false
48
+ },
49
+ "8": {
50
+ "content": "<|assistant|>",
51
+ "lstrip": false,
52
+ "normalized": false,
53
+ "rstrip": false,
54
+ "single_word": false,
55
+ "special": false
56
+ },
57
+ "9": {
58
+ "content": "<|user|>",
59
+ "lstrip": false,
60
+ "normalized": false,
61
+ "rstrip": false,
62
+ "single_word": false,
63
+ "special": false
64
+ },
65
+ "10": {
66
+ "content": "<|available_tools|>",
67
+ "lstrip": false,
68
+ "normalized": false,
69
+ "rstrip": false,
70
+ "single_word": false,
71
+ "special": false
72
+ },
73
+ "11": {
74
+ "content": "<|tool_calls|>",
75
+ "lstrip": false,
76
+ "normalized": false,
77
+ "rstrip": false,
78
+ "single_word": false,
79
+ "special": false
80
+ },
81
+ "12": {
82
+ "content": "<|tool_results|>",
83
+ "lstrip": false,
84
+ "normalized": false,
85
+ "rstrip": false,
86
+ "single_word": false,
87
+ "special": false
88
+ },
89
+ "13": {
90
+ "content": "<|code|>",
91
+ "lstrip": false,
92
+ "normalized": false,
93
+ "rstrip": false,
94
+ "single_word": false,
95
+ "special": false
96
+ },
97
+ "14": {
98
+ "content": "<|file|>",
99
+ "lstrip": false,
100
+ "normalized": false,
101
+ "rstrip": false,
102
+ "single_word": false,
103
+ "special": false
104
+ },
105
+ "102397": {
106
+ "content": "<|prefix|>",
107
+ "lstrip": false,
108
+ "normalized": false,
109
+ "rstrip": false,
110
+ "single_word": false,
111
+ "special": false
112
+ },
113
+ "102398": {
114
+ "content": "<|suffix|>",
115
+ "lstrip": false,
116
+ "normalized": false,
117
+ "rstrip": false,
118
+ "single_word": false,
119
+ "special": false
120
+ },
121
+ "102399": {
122
+ "content": "<|middle|>",
123
+ "lstrip": false,
124
+ "normalized": false,
125
+ "rstrip": false,
126
+ "single_word": false,
127
+ "special": false
128
+ }
129
+ },
130
+ "add_prefix_space": false,
131
+ "add_dummy_prefix_space": false,
132
+ "legacy": false,
133
+ "add_bos_token": false,
134
+ "add_eos_token": false
135
+ }