ermu2001 commited on
Commit
dbdf958
1 Parent(s): c81ae0c

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image>": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MODELS/llava-v1.6-vicuna-13b-hf",
3
+ "architectures": [
4
+ "MagicForConditionalGeneration"
5
+ ],
6
+ "causal_conv_ks": [
7
+ 3,
8
+ 3,
9
+ 3
10
+ ],
11
+ "causal_conv_pad_mod": "constant",
12
+ "dilation": 1,
13
+ "frame_shape": [
14
+ 24,
15
+ 24
16
+ ],
17
+ "highres": null,
18
+ "ignore_index": -100,
19
+ "image_grid_pinpoints": [
20
+ [
21
+ 336,
22
+ 672
23
+ ],
24
+ [
25
+ 672,
26
+ 336
27
+ ],
28
+ [
29
+ 672,
30
+ 672
31
+ ],
32
+ [
33
+ 1008,
34
+ 336
35
+ ],
36
+ [
37
+ 336,
38
+ 1008
39
+ ]
40
+ ],
41
+ "image_token_index": 32000,
42
+ "model_type": "llava",
43
+ "num_frames": 16,
44
+ "pooling_method": "avg",
45
+ "pooling_shape": [
46
+ 16,
47
+ 12,
48
+ 12
49
+ ],
50
+ "projector_hidden_act": "gelu",
51
+ "register": false,
52
+ "slide_pooling_shape": [
53
+ 16,
54
+ 2,
55
+ 2
56
+ ],
57
+ "stride": 1,
58
+ "text_config": {
59
+ "_name_or_path": "lmsys/vicuna-13b-v1.5",
60
+ "architectures": [
61
+ "LlamaForCausalLM"
62
+ ],
63
+ "gradient_checkpointing": false,
64
+ "hidden_size": 5120,
65
+ "intermediate_size": 13824,
66
+ "max_length": 4096,
67
+ "max_position_embeddings": 4096,
68
+ "model_type": "llama",
69
+ "num_attention_heads": 40,
70
+ "num_hidden_layers": 40,
71
+ "num_key_value_heads": 40,
72
+ "pad_token_id": 0,
73
+ "rms_norm_eps": 1e-05,
74
+ "torch_dtype": "bfloat16",
75
+ "use_cache": false,
76
+ "vocab_size": 32064
77
+ },
78
+ "torch_dtype": "bfloat16",
79
+ "transformers_version": "4.37.1",
80
+ "use_cc": false,
81
+ "use_image_newline_parameter": true,
82
+ "use_pooling": true,
83
+ "use_yi": false,
84
+ "vision_config": {
85
+ "hidden_size": 1024,
86
+ "image_size": 336,
87
+ "intermediate_size": 4096,
88
+ "model_type": "clip_vision_model",
89
+ "num_attention_heads": 16,
90
+ "num_hidden_layers": 24,
91
+ "patch_size": 14,
92
+ "projection_dim": 768,
93
+ "vocab_size": 32000
94
+ },
95
+ "vision_feature_layer": -2,
96
+ "vision_feature_select_strategy": "default",
97
+ "vocab_size": 32064
98
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.37.1"
8
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c68c4fecf974b1a076a99bacbc2a65ff47cfdaf65217f305b45654fc5342470c
3
+ size 4998793320
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f72b829cfd45f5700ef7f224da7a338e52d200c41644f517ce96d3b5d69ff8b6
3
+ size 4954700400
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2faf496e6e3318b679d49fc05bded19fd248339268afec5497b121b981d76c53
3
+ size 4975652168
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80602c3c80d76b8b0c1170baab86f80ff814620d1fa0070c0409481a5952f97c
3
+ size 4975672944
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9f0560f4da42cfdd7b19ef58a22e3019bf5b11fcf2d2e815e1c807417617ecb
3
+ size 4975672936
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4def34833d378c22186799b71bf46440964d9b759db2d162d785e5caba815045
3
+ size 2032348080
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "aspect_ratio_setting": "anyres",
3
+ "crop_size": {
4
+ "height": 336,
5
+ "width": 336
6
+ },
7
+ "do_center_crop": true,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_grid_pinpoints": [
13
+ [
14
+ 336,
15
+ 672
16
+ ],
17
+ [
18
+ 672,
19
+ 336
20
+ ],
21
+ [
22
+ 672,
23
+ 672
24
+ ],
25
+ [
26
+ 1008,
27
+ 336
28
+ ],
29
+ [
30
+ 336,
31
+ 1008
32
+ ]
33
+ ],
34
+ "image_mean": [
35
+ 0.48145466,
36
+ 0.4578275,
37
+ 0.40821073
38
+ ],
39
+ "image_processor_type": "CLIPImageProcessor",
40
+ "image_std": [
41
+ 0.26862954,
42
+ 0.26130258,
43
+ 0.27577711
44
+ ],
45
+ "processor_class": "MagicProcessor",
46
+ "resample": 3,
47
+ "rescale_factor": 0.00392156862745098,
48
+ "size": {
49
+ "shortest_edge": 336
50
+ }
51
+ }
processor_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "center_pad": false,
3
+ "longest_edge": 762,
4
+ "processor_class": "MagicProcessor",
5
+ "shortest_edge": 336
6
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
31
+ "content": "<image>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ }
38
+ },
39
+ "bos_token": "<s>",
40
+ "center_pad": false,
41
+ "clean_up_tokenization_spaces": false,
42
+ "eos_token": "</s>",
43
+ "legacy": false,
44
+ "max_length": null,
45
+ "model_max_length": 4096,
46
+ "pad_to_multiple_of": null,
47
+ "pad_token": "<unk>",
48
+ "pad_token_type_id": 0,
49
+ "padding_side": "right",
50
+ "processor_class": "MagicProcessor",
51
+ "sp_model_kwargs": {},
52
+ "spaces_between_special_tokens": false,
53
+ "tokenizer_class": "LlamaTokenizer",
54
+ "unk_token": "<unk>",
55
+ "use_default_system_prompt": false
56
+ }