gwkrsrch commited on
Commit
af47105
1 Parent(s): 688d3db

initial commit

Browse files
config.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "apple/OpenELM-1_1B-Instruct",
3
+ "activation_fn_name": "swish",
4
+ "architectures": [
5
+ "LlavaOpenELMForCausalLM"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_openelm.OpenELMConfig",
9
+ "AutoModelForCausalLM": "modeling_openelm.OpenELMForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "ffn_dim_divisor": 256,
14
+ "ffn_multipliers": [
15
+ 0.5,
16
+ 0.63,
17
+ 0.76,
18
+ 0.89,
19
+ 1.02,
20
+ 1.15,
21
+ 1.28,
22
+ 1.41,
23
+ 1.54,
24
+ 1.67,
25
+ 1.8,
26
+ 1.93,
27
+ 2.06,
28
+ 2.19,
29
+ 2.31,
30
+ 2.44,
31
+ 2.57,
32
+ 2.7,
33
+ 2.83,
34
+ 2.96,
35
+ 3.09,
36
+ 3.22,
37
+ 3.35,
38
+ 3.48,
39
+ 3.61,
40
+ 3.74,
41
+ 3.87,
42
+ 4.0
43
+ ],
44
+ "ffn_with_glu": true,
45
+ "freeze_mm_mlp_adapter": false,
46
+ "head_dim": 64,
47
+ "hidden_size": 2048,
48
+ "image_aspect_ratio": "anyres",
49
+ "image_grid_pinpoints": [[224, 224], [224, 448], [448, 224], [448, 448], [448, 672], [672, 448], [672, 672], [672, 896], [896, 672]],
50
+ "initializer_range": 0.02,
51
+ "max_context_length": 2048,
52
+ "mm_hidden_size": 768,
53
+ "mm_patch_merge_type": "spatial",
54
+ "mm_projector_lr": null,
55
+ "mm_projector_type": "mlp2x_gelu",
56
+ "mm_use_im_patch_token": false,
57
+ "mm_use_im_start_end": false,
58
+ "mm_vision_select_feature": "patch",
59
+ "mm_vision_select_layer": -2,
60
+ "mm_vision_tower": "gwkrsrch/elva-encoder-base-patch32",
61
+ "mm_vision_tower_lr": null,
62
+ "model_dim": 2048,
63
+ "model_type": "llava_openelm",
64
+ "normalization_layer_name": "rms_norm",
65
+ "normalize_qk_projections": true,
66
+ "num_gqa_groups": 4,
67
+ "num_kv_heads": [
68
+ 4,
69
+ 4,
70
+ 4,
71
+ 5,
72
+ 5,
73
+ 5,
74
+ 5,
75
+ 5,
76
+ 5,
77
+ 5,
78
+ 6,
79
+ 6,
80
+ 6,
81
+ 6,
82
+ 6,
83
+ 6,
84
+ 6,
85
+ 6,
86
+ 7,
87
+ 7,
88
+ 7,
89
+ 7,
90
+ 7,
91
+ 7,
92
+ 8,
93
+ 8,
94
+ 8,
95
+ 8
96
+ ],
97
+ "num_query_heads": [
98
+ 16,
99
+ 16,
100
+ 16,
101
+ 20,
102
+ 20,
103
+ 20,
104
+ 20,
105
+ 20,
106
+ 20,
107
+ 20,
108
+ 24,
109
+ 24,
110
+ 24,
111
+ 24,
112
+ 24,
113
+ 24,
114
+ 24,
115
+ 24,
116
+ 28,
117
+ 28,
118
+ 28,
119
+ 28,
120
+ 28,
121
+ 28,
122
+ 32,
123
+ 32,
124
+ 32,
125
+ 32
126
+ ],
127
+ "num_transformer_layers": 28,
128
+ "qkv_multipliers": [
129
+ 0.5,
130
+ 1.0
131
+ ],
132
+ "rope_freq_constant": 10000,
133
+ "rope_max_length": 4096,
134
+ "share_input_output_layers": true,
135
+ "tokenizer_model_max_length": 2048,
136
+ "tokenizer_padding_side": "right",
137
+ "torch_dtype": "bfloat16",
138
+ "transformers_version": "4.42.4",
139
+ "tune_mm_mlp_adapter": false,
140
+ "use_cache": true,
141
+ "use_mm_proj": true,
142
+ "vocab_size": 32000
143
+ }
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": "4.42.4"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4684f20e08e2ab4998a2c50abacf0c9c7c3b9ed9c24653f11b0e92902eec718
3
+ size 2346295736
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 2048,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }