Commit
•
a0b9d53
1
Parent(s):
0b9709b
Upload folder using huggingface_hub
Browse files- config.json +49 -0
- model.safetensors +3 -0
- preprocessor_config.json +23 -0
- processor_config.json +9 -0
- special_tokens_map.json +13 -0
- tokenizer.json +0 -0
- tokenizer_config.json +146 -0
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"aligner_config": {
|
3 |
+
"cls": "MlpProjector",
|
4 |
+
"model_type": "aligner",
|
5 |
+
"params": {
|
6 |
+
"depth": 2,
|
7 |
+
"input_dim": 1024,
|
8 |
+
"n_embed": 2048,
|
9 |
+
"projector_type": "mlp_gelu"
|
10 |
+
}
|
11 |
+
},
|
12 |
+
"architectures": [
|
13 |
+
"MultiModalityCausalLM"
|
14 |
+
],
|
15 |
+
"language_config": {
|
16 |
+
"hidden_size": 2048,
|
17 |
+
"intermediate_size": 5632,
|
18 |
+
"max_position_embeddings": 16384,
|
19 |
+
"model_type": "llama",
|
20 |
+
"num_attention_heads": 16,
|
21 |
+
"num_hidden_layers": 24,
|
22 |
+
"num_key_value_heads": 16,
|
23 |
+
"torch_dtype": "float16",
|
24 |
+
"vocab_size": 102400
|
25 |
+
},
|
26 |
+
"model_type": "multi_modality",
|
27 |
+
"torch_dtype": "float16",
|
28 |
+
"transformers_version": "4.38.2",
|
29 |
+
"vision_config": {
|
30 |
+
"cls": "CLIPVisionTower",
|
31 |
+
"model_type": "vision",
|
32 |
+
"params": {
|
33 |
+
"image_size": 384,
|
34 |
+
"model_name": "siglip_large_patch16_384",
|
35 |
+
"pixel_mean": [
|
36 |
+
0.5,
|
37 |
+
0.5,
|
38 |
+
0.5
|
39 |
+
],
|
40 |
+
"pixel_std": [
|
41 |
+
0.5,
|
42 |
+
0.5,
|
43 |
+
0.5
|
44 |
+
],
|
45 |
+
"select_feature": "same",
|
46 |
+
"select_layer": -1
|
47 |
+
}
|
48 |
+
}
|
49 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1c382c6dcecbc3e17c1648253e5086523626719e05e52e905fbfd113694e65e
|
3 |
+
size 3950537560
|
preprocessor_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"background_color": [
|
3 |
+
127,
|
4 |
+
127,
|
5 |
+
127
|
6 |
+
],
|
7 |
+
"do_normalize": false,
|
8 |
+
"image_mean": [
|
9 |
+
0.5,
|
10 |
+
0.5,
|
11 |
+
0.5
|
12 |
+
],
|
13 |
+
"image_processor_type": "VLMImageProcessor",
|
14 |
+
"image_size": 384,
|
15 |
+
"image_std": [
|
16 |
+
0.5,
|
17 |
+
0.5,
|
18 |
+
0.5
|
19 |
+
],
|
20 |
+
"min_size": 14,
|
21 |
+
"processor_class": "VLChatProcessor",
|
22 |
+
"rescale_factor": 0.00392156862745098
|
23 |
+
}
|
processor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_special_token": false,
|
3 |
+
"ignore_id": -100,
|
4 |
+
"image_tag": "<image_placeholder>",
|
5 |
+
"mask_prompt": true,
|
6 |
+
"num_image_tokens": 576,
|
7 |
+
"processor_class": "VLChatProcessor",
|
8 |
+
"sft_format": "deepseek"
|
9 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<image_placeholder>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
}
|
10 |
+
],
|
11 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
12 |
+
"eos_token": "<|end▁of▁sentence|>"
|
13 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"100000": {
|
6 |
+
"content": "<|begin▁of▁sentence|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"100001": {
|
14 |
+
"content": "<|end▁of▁sentence|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"100002": {
|
22 |
+
"content": "ø",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"100003": {
|
30 |
+
"content": "ö",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": false
|
36 |
+
},
|
37 |
+
"100004": {
|
38 |
+
"content": "ú",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": false
|
44 |
+
},
|
45 |
+
"100005": {
|
46 |
+
"content": "ÿ",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": true,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": false
|
52 |
+
},
|
53 |
+
"100006": {
|
54 |
+
"content": "õ",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": true,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": false
|
60 |
+
},
|
61 |
+
"100007": {
|
62 |
+
"content": "÷",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": true,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": false
|
68 |
+
},
|
69 |
+
"100008": {
|
70 |
+
"content": "û",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": true,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": false
|
76 |
+
},
|
77 |
+
"100009": {
|
78 |
+
"content": "ý",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": true,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": false
|
84 |
+
},
|
85 |
+
"100010": {
|
86 |
+
"content": "À",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": true,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": false
|
92 |
+
},
|
93 |
+
"100011": {
|
94 |
+
"content": "ù",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": true,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": false
|
100 |
+
},
|
101 |
+
"100012": {
|
102 |
+
"content": "Á",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": true,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": false
|
108 |
+
},
|
109 |
+
"100013": {
|
110 |
+
"content": "þ",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": true,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": false
|
116 |
+
},
|
117 |
+
"100014": {
|
118 |
+
"content": "ü",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": true,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"100015": {
|
126 |
+
"content": "<image_placeholder>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": true
|
132 |
+
}
|
133 |
+
},
|
134 |
+
"additional_special_tokens": [
|
135 |
+
"<image_placeholder>"
|
136 |
+
],
|
137 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
138 |
+
"clean_up_tokenization_spaces": false,
|
139 |
+
"eos_token": "<|end▁of▁sentence|>",
|
140 |
+
"model_max_length": 16384,
|
141 |
+
"pad_token": null,
|
142 |
+
"processor_class": "VLChatProcessor",
|
143 |
+
"tokenizer_class": "LlamaTokenizer",
|
144 |
+
"unk_token": null,
|
145 |
+
"use_default_system_prompt": false
|
146 |
+
}
|