arthu1 commited on
Commit
eebc8fe
·
verified ·
1 Parent(s): a30fae8

Upload 5 files

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "head_dim": 32,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 192,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 576,
15
+ "max_position_embeddings": 512,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 6,
19
+ "num_hidden_layers": 10,
20
+ "num_key_value_heads": 6,
21
+ "pad_token_id": 3,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_parameters": {
25
+ "rope_theta": 10000.0,
26
+ "rope_type": "default"
27
+ },
28
+ "tie_word_embeddings": false,
29
+ "transformers_version": "5.12.0",
30
+ "use_cache": true,
31
+ "vocab_size": 1024
32
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 3,
8
+ "transformers_version": "5.12.0",
9
+ "use_cache": true
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf09eb69eaee233bfb79cfd8e1cc8f0db48187c19d29d4d71c194f0a26f56d0b
3
+ size 20768280
tokenizer.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<unk>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<s>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "</s>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<pad>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": null,
44
+ "pre_tokenizer": {
45
+ "type": "Metaspace",
46
+ "replacement": "▁",
47
+ "prepend_scheme": "first",
48
+ "split": false
49
+ },
50
+ "post_processor": {
51
+ "type": "TemplateProcessing",
52
+ "single": [
53
+ {
54
+ "Sequence": {
55
+ "id": "A",
56
+ "type_id": 0
57
+ }
58
+ }
59
+ ],
60
+ "pair": [
61
+ {
62
+ "Sequence": {
63
+ "id": "A",
64
+ "type_id": 0
65
+ }
66
+ },
67
+ {
68
+ "Sequence": {
69
+ "id": "B",
70
+ "type_id": 1
71
+ }
72
+ }
73
+ ],
74
+ "special_tokens": {}
75
+ },
76
+ "decoder": {
77
+ "type": "Sequence",
78
+ "decoders": [
79
+ {
80
+ "type": "Replace",
81
+ "pattern": {
82
+ "String": "▁"
83
+ },
84
+ "content": " "
85
+ },
86
+ {
87
+ "type": "ByteFallback"
88
+ },
89
+ {
90
+ "type": "Fuse"
91
+ },
92
+ {
93
+ "type": "Strip",
94
+ "content": " ",
95
+ "start": 1,
96
+ "stop": 0
97
+ }
98
+ ]
99
+ },
100
+ "model": {
101
+ "type": "BPE",
102
+ "dropout": null,
103
+ "unk_token": null,
104
+ "continuing_subword_prefix": null,
105
+ "end_of_word_suffix": null,
106
+ "fuse_unk": true,
107
+ "byte_fallback": true,
108
+ "ignore_merges": false,
109
+ "vocab": {
110
+ "<unk>": 0,
111
+ "<s>": 1,
112
+ "</s>": 2
113
+ },
114
+ "merges": []
115
+ }
116
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "<pad>",
9
+ "tokenizer_class": "LlamaTokenizer",
10
+ "unk_token": "<unk>",
11
+ "use_default_system_prompt": false
12
+ }