Hugging Face's logo

Smilyai-labs
/
Sam-2.5-4

Text Generation
Transformers
Safetensors
English
Model card Files
xet
Community
Keeby-smilyai commited on
Commit
8ea8006
·
verified ·
1 Parent(s): 4f2cd42

Upload 9 files

Browse files
Files changed (9) hide show
  1. added_tokens.json +7 -0
  2. config.json +11 -0
  3. merges.txt +0 -0
  4. model.safetensors +3 -0
  5. sam-train-2-5-3-cont.log +0 -0
  6. special_tokens_map.json +37 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +75 -0
  9. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 50260,
3
+ "<|bos|>": 50257,
4
+ "<|eot|>": 50258,
5
+ "<|system|>": 50261,
6
+ "<|user|>": 50259
7
+ }
config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 50262,
3
+ "d_model": 384,
4
+ "n_layers": 6,
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
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e4d1fd9c3f9ec08c1837f1beb5ed68f9a089672ad8e85a2344eef478933a363
3
+ size 211053376
sam-train-2-5-3-cont.log ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|bos|>",
4
+ "<|eot|>",
5
+ "<|user|>",
6
+ "<|assistant|>",
7
+ "<|system|>"
8
+ ],
9
+ "bos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
53
+ "additional_special_tokens": [
54
+ "<|bos|>",
55
+ "<|eot|>",
56
+ "<|user|>",
57
+ "<|assistant|>",
58
+ "<|system|>"
59
+ ],
60
+ "bos_token": "<|endoftext|>",
61
+ "clean_up_tokenization_spaces": false,
62
+ "eos_token": "<|endoftext|>",
63
+ "extra_special_tokens": {},
64
+ "max_length": 512,
65
+ "model_max_length": 1024,
66
+ "pad_to_multiple_of": null,
67
+ "pad_token": "<|endoftext|>",
68
+ "pad_token_type_id": 0,
69
+ "padding_side": "right",
70
+ "stride": 0,
71
+ "tokenizer_class": "GPT2Tokenizer",
72
+ "truncation_side": "right",
73
+ "truncation_strategy": "longest_first",
74
+ "unk_token": "<|endoftext|>"
75
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff