Hugging Face's logo

Smilyai-labs
/
Sam-3.0-2

Safetensors
Model card Files
xet
Community
Keeby-smilyai commited on
Commit
35eb489
·
1 Parent(s): 30f673d

Upload 7 files

Browse files
Files changed (7) hide show
  1. added_tokens.json +8 -0
  2. config.json +11 -0
  3. merges.txt +0 -0
  4. special_tokens_map.json +50 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +77 -0
  7. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 50260,
3
+ "<|bos|>": 50257,
4
+ "<|eot|>": 50258,
5
+ "<|system|>": 50261,
6
+ "<|think|>": 50262,
7
+ "<|user|>": 50259
8
+ }
config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 50263,
3
+ "d_model": 384,
4
+ "n_layers": 10,
5
+ "n_heads": 6,
6
+ "ff_mult": 4.0,
7
+ "dropout": 0.1,
8
+ "input_modality": "text",
9
+ "head_type": "causal_lm",
10
+ "version": "0.1"
11
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|bos|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|eot|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|user|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<|assistant|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<|system|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<|think|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ }
45
+ ],
46
+ "bos_token": "<|endoftext|>",
47
+ "eos_token": "<|endoftext|>",
48
+ "pad_token": "<|endoftext|>",
49
+ "unk_token": "<|endoftext|>"
50
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<|bos|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "<|eot|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "<|user|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50260": {
37
+ "content": "<|assistant|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50261": {
45
+ "content": "<|system|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50262": {
53
+ "content": "<|think|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "additional_special_tokens": [
62
+ "<|bos|>",
63
+ "<|eot|>",
64
+ "<|user|>",
65
+ "<|assistant|>",
66
+ "<|system|>",
67
+ "<|think|>"
68
+ ],
69
+ "bos_token": "<|endoftext|>",
70
+ "clean_up_tokenization_spaces": false,
71
+ "eos_token": "<|endoftext|>",
72
+ "extra_special_tokens": {},
73
+ "model_max_length": 1024,
74
+ "pad_token": "<|endoftext|>",
75
+ "tokenizer_class": "GPT2Tokenizer",
76
+ "unk_token": "<|endoftext|>"
77
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff