Vladimir Malniovskii commited on
Commit
518c749
1 Parent(s): 93c6049

model upload

Browse files
config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./mnt/out",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "quantization_config": {
19
+ "in_group_size": 8,
20
+ "linear_weights_not_to_quantize": [
21
+ "model.layers.0.input_layernorm.weight",
22
+ "model.layers.0.post_attention_layernorm.weight",
23
+ "model.layers.1.input_layernorm.weight",
24
+ "model.layers.1.post_attention_layernorm.weight",
25
+ "model.layers.2.input_layernorm.weight",
26
+ "model.layers.2.post_attention_layernorm.weight",
27
+ "model.layers.3.input_layernorm.weight",
28
+ "model.layers.3.post_attention_layernorm.weight",
29
+ "model.layers.4.input_layernorm.weight",
30
+ "model.layers.4.post_attention_layernorm.weight",
31
+ "model.layers.5.input_layernorm.weight",
32
+ "model.layers.5.post_attention_layernorm.weight",
33
+ "model.layers.6.input_layernorm.weight",
34
+ "model.layers.6.post_attention_layernorm.weight",
35
+ "model.layers.7.input_layernorm.weight",
36
+ "model.layers.7.post_attention_layernorm.weight",
37
+ "model.layers.8.input_layernorm.weight",
38
+ "model.layers.8.post_attention_layernorm.weight",
39
+ "model.layers.9.input_layernorm.weight",
40
+ "model.layers.9.post_attention_layernorm.weight",
41
+ "model.layers.10.input_layernorm.weight",
42
+ "model.layers.10.post_attention_layernorm.weight",
43
+ "model.layers.11.input_layernorm.weight",
44
+ "model.layers.11.post_attention_layernorm.weight",
45
+ "model.layers.12.input_layernorm.weight",
46
+ "model.layers.12.post_attention_layernorm.weight",
47
+ "model.layers.13.input_layernorm.weight",
48
+ "model.layers.13.post_attention_layernorm.weight",
49
+ "model.layers.14.input_layernorm.weight",
50
+ "model.layers.14.post_attention_layernorm.weight",
51
+ "model.layers.15.input_layernorm.weight",
52
+ "model.layers.15.post_attention_layernorm.weight",
53
+ "model.layers.16.input_layernorm.weight",
54
+ "model.layers.16.post_attention_layernorm.weight",
55
+ "model.layers.17.input_layernorm.weight",
56
+ "model.layers.17.post_attention_layernorm.weight",
57
+ "model.layers.18.input_layernorm.weight",
58
+ "model.layers.18.post_attention_layernorm.weight",
59
+ "model.layers.19.input_layernorm.weight",
60
+ "model.layers.19.post_attention_layernorm.weight",
61
+ "model.layers.20.input_layernorm.weight",
62
+ "model.layers.20.post_attention_layernorm.weight",
63
+ "model.layers.21.input_layernorm.weight",
64
+ "model.layers.21.post_attention_layernorm.weight",
65
+ "model.layers.22.input_layernorm.weight",
66
+ "model.layers.22.post_attention_layernorm.weight",
67
+ "model.layers.23.input_layernorm.weight",
68
+ "model.layers.23.post_attention_layernorm.weight",
69
+ "model.layers.24.input_layernorm.weight",
70
+ "model.layers.24.post_attention_layernorm.weight",
71
+ "model.layers.25.input_layernorm.weight",
72
+ "model.layers.25.post_attention_layernorm.weight",
73
+ "model.layers.26.input_layernorm.weight",
74
+ "model.layers.26.post_attention_layernorm.weight",
75
+ "model.layers.27.input_layernorm.weight",
76
+ "model.layers.27.post_attention_layernorm.weight",
77
+ "model.layers.28.input_layernorm.weight",
78
+ "model.layers.28.post_attention_layernorm.weight",
79
+ "model.layers.29.input_layernorm.weight",
80
+ "model.layers.29.post_attention_layernorm.weight",
81
+ "model.layers.30.input_layernorm.weight",
82
+ "model.layers.30.post_attention_layernorm.weight",
83
+ "model.layers.31.input_layernorm.weight",
84
+ "model.layers.31.post_attention_layernorm.weight",
85
+ "model.embed_tokens.weight",
86
+ "model.norm.weight",
87
+ "lm_head.weight"
88
+ ],
89
+ "nbits_per_codebook": 16,
90
+ "num_codebooks": 1,
91
+ "out_group_size": 1,
92
+ "quant_method": "aqlm"
93
+ },
94
+ "rms_norm_eps": 1e-05,
95
+ "rope_theta": 10000.0,
96
+ "sliding_window": 4096,
97
+ "tie_word_embeddings": false,
98
+ "torch_dtype": "float16",
99
+ "transformers_version": "4.39.3",
100
+ "use_cache": true,
101
+ "vocab_size": 32000
102
+ }
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 sha256:27051565cb411cf03557c98a0aca9544e83e4dd0277b0b6e9b2b576284e05c71
3
+ size 2507369944
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }