Xenova HF staff commited on
Commit
1177833
·
verified ·
1 Parent(s): 22a3cf4

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "IDEA-Research/grounding-dino-tiny",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "GroundingDinoForObjectDetection"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auxiliary_loss": false,
10
+ "backbone": null,
11
+ "backbone_config": {
12
+ "model_type": "swin",
13
+ "out_features": [
14
+ "stage2",
15
+ "stage3",
16
+ "stage4"
17
+ ],
18
+ "out_indices": [
19
+ 2,
20
+ 3,
21
+ 4
22
+ ]
23
+ },
24
+ "backbone_kwargs": null,
25
+ "bbox_cost": 5.0,
26
+ "bbox_loss_coefficient": 5.0,
27
+ "class_cost": 1.0,
28
+ "d_model": 256,
29
+ "decoder_attention_heads": 8,
30
+ "decoder_bbox_embed_share": true,
31
+ "decoder_ffn_dim": 2048,
32
+ "decoder_layers": 6,
33
+ "decoder_n_points": 4,
34
+ "disable_custom_kernels": false,
35
+ "dropout": 0.1,
36
+ "embedding_init_target": true,
37
+ "encoder_attention_heads": 8,
38
+ "encoder_ffn_dim": 2048,
39
+ "encoder_layers": 6,
40
+ "encoder_n_points": 4,
41
+ "focal_alpha": 0.25,
42
+ "fusion_dropout": 0.0,
43
+ "fusion_droppath": 0.1,
44
+ "giou_cost": 2.0,
45
+ "giou_loss_coefficient": 2.0,
46
+ "init_std": 0.02,
47
+ "is_encoder_decoder": true,
48
+ "layer_norm_eps": 1e-05,
49
+ "max_text_len": 256,
50
+ "model_type": "grounding-dino",
51
+ "num_feature_levels": 4,
52
+ "num_queries": 900,
53
+ "position_embedding_type": "sine",
54
+ "positional_embedding_temperature": 20,
55
+ "query_dim": 4,
56
+ "text_config": {
57
+ "model_type": "bert"
58
+ },
59
+ "text_enhancer_dropout": 0.0,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.48.0.dev0",
62
+ "two_stage": true,
63
+ "two_stage_bbox_embed_share": false,
64
+ "use_pretrained_backbone": false,
65
+ "use_timm_backbone": false
66
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:267c8b00d269dc2dda0d8592812d3027abd5fb59f1cabf8e3d56f8fdf07f68ec
3
+ size 718761381
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdaccc102dc248c65a8a6190369b624a1d26042a7d3be45aedf4619cb46d3557
3
+ size 218129274
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04c18d2db35569f11c47732f2e05ed3a71559a8903823fc581e90b0e3168c9ff
3
+ size 360393267
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bff430de583461ab3c1e8b99b19508f4fb238bf0fea0cde2c45f840a0082a26
3
+ size 203824481
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ed98a91b75f00d325c7581bee83b92b5b98460981772edf5ed844370ac25c11
3
+ size 227229745
onnx/model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48435b57e5a5ca01792596b9c64277260b734c10aed320109505c8e71238d6ac
3
+ size 151069879
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70bf2d3310d1ae73769c96a71e00cbf2861eb33a1f4d97d84a108a7bf02c03c9
3
+ size 203824675
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70bf2d3310d1ae73769c96a71e00cbf2861eb33a1f4d97d84a108a7bf02c03c9
3
+ size 203824675
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_annotations": true,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "format": "coco_detection",
8
+ "image_mean": [
9
+ 0.485,
10
+ 0.456,
11
+ 0.406
12
+ ],
13
+ "image_processor_type": "GroundingDinoImageProcessor",
14
+ "image_std": [
15
+ 0.229,
16
+ 0.224,
17
+ 0.225
18
+ ],
19
+ "pad_size": null,
20
+ "processor_class": "GroundingDinoProcessor",
21
+ "resample": 2,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 1333,
25
+ "shortest_edge": 800
26
+ }
27
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "processor_class": "GroundingDinoProcessor",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff