Vladimir Malniovskii commited on
Commit
7a26d7a
1 Parent(s): d8d9065

model upload

Browse files
config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./mnt/out",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "in_group_size": 8,
22
+ "linear_weights_not_to_quantize": [
23
+ "model.layers.0.input_layernorm.weight",
24
+ "model.layers.0.post_attention_layernorm.weight",
25
+ "model.layers.1.input_layernorm.weight",
26
+ "model.layers.1.post_attention_layernorm.weight",
27
+ "model.layers.2.input_layernorm.weight",
28
+ "model.layers.2.post_attention_layernorm.weight",
29
+ "model.layers.3.input_layernorm.weight",
30
+ "model.layers.3.post_attention_layernorm.weight",
31
+ "model.layers.4.input_layernorm.weight",
32
+ "model.layers.4.post_attention_layernorm.weight",
33
+ "model.layers.5.input_layernorm.weight",
34
+ "model.layers.5.post_attention_layernorm.weight",
35
+ "model.layers.6.input_layernorm.weight",
36
+ "model.layers.6.post_attention_layernorm.weight",
37
+ "model.layers.7.input_layernorm.weight",
38
+ "model.layers.7.post_attention_layernorm.weight",
39
+ "model.layers.8.input_layernorm.weight",
40
+ "model.layers.8.post_attention_layernorm.weight",
41
+ "model.layers.9.input_layernorm.weight",
42
+ "model.layers.9.post_attention_layernorm.weight",
43
+ "model.layers.10.input_layernorm.weight",
44
+ "model.layers.10.post_attention_layernorm.weight",
45
+ "model.layers.11.input_layernorm.weight",
46
+ "model.layers.11.post_attention_layernorm.weight",
47
+ "model.layers.12.input_layernorm.weight",
48
+ "model.layers.12.post_attention_layernorm.weight",
49
+ "model.layers.13.input_layernorm.weight",
50
+ "model.layers.13.post_attention_layernorm.weight",
51
+ "model.layers.14.input_layernorm.weight",
52
+ "model.layers.14.post_attention_layernorm.weight",
53
+ "model.layers.15.input_layernorm.weight",
54
+ "model.layers.15.post_attention_layernorm.weight",
55
+ "model.layers.16.input_layernorm.weight",
56
+ "model.layers.16.post_attention_layernorm.weight",
57
+ "model.layers.17.input_layernorm.weight",
58
+ "model.layers.17.post_attention_layernorm.weight",
59
+ "model.layers.18.input_layernorm.weight",
60
+ "model.layers.18.post_attention_layernorm.weight",
61
+ "model.layers.19.input_layernorm.weight",
62
+ "model.layers.19.post_attention_layernorm.weight",
63
+ "model.layers.20.input_layernorm.weight",
64
+ "model.layers.20.post_attention_layernorm.weight",
65
+ "model.layers.21.input_layernorm.weight",
66
+ "model.layers.21.post_attention_layernorm.weight",
67
+ "model.layers.22.input_layernorm.weight",
68
+ "model.layers.22.post_attention_layernorm.weight",
69
+ "model.layers.23.input_layernorm.weight",
70
+ "model.layers.23.post_attention_layernorm.weight",
71
+ "model.layers.24.input_layernorm.weight",
72
+ "model.layers.24.post_attention_layernorm.weight",
73
+ "model.layers.25.input_layernorm.weight",
74
+ "model.layers.25.post_attention_layernorm.weight",
75
+ "model.layers.26.input_layernorm.weight",
76
+ "model.layers.26.post_attention_layernorm.weight",
77
+ "model.layers.27.input_layernorm.weight",
78
+ "model.layers.27.post_attention_layernorm.weight",
79
+ "model.layers.28.input_layernorm.weight",
80
+ "model.layers.28.post_attention_layernorm.weight",
81
+ "model.layers.29.input_layernorm.weight",
82
+ "model.layers.29.post_attention_layernorm.weight",
83
+ "model.layers.30.input_layernorm.weight",
84
+ "model.layers.30.post_attention_layernorm.weight",
85
+ "model.layers.31.input_layernorm.weight",
86
+ "model.layers.31.post_attention_layernorm.weight",
87
+ "model.embed_tokens.weight",
88
+ "model.norm.weight",
89
+ "lm_head.weight"
90
+ ],
91
+ "nbits_per_codebook": 8,
92
+ "num_codebooks": 2,
93
+ "out_group_size": 1,
94
+ "quant_method": "aqlm"
95
+ },
96
+ "rms_norm_eps": 1e-05,
97
+ "rope_scaling": null,
98
+ "rope_theta": 10000.0,
99
+ "tie_word_embeddings": false,
100
+ "torch_dtype": "float16",
101
+ "transformers_version": "4.39.3",
102
+ "use_cache": true,
103
+ "vocab_size": 32000
104
+ }
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": "4.39.3"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72970c87f2fd662cc9cb509efc29a66137db9302e8a03b834570cea69c5305d2
3
+ size 2148461304
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
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,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }