GeorgeIbrahim commited on
Commit
b0406be
·
verified ·
1 Parent(s): 691abcc

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image>": 250100
3
+ }
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Blip2ForConditionalGeneration"
4
+ ],
5
+ "image_text_hidden_size": 256,
6
+ "image_token_index": null,
7
+ "initializer_factor": 1.0,
8
+ "initializer_range": 0.02,
9
+ "is_encoder_decoder": true,
10
+ "model_type": "blip-2",
11
+ "num_query_tokens": 32,
12
+ "qformer_config": {
13
+ "_attn_implementation_autoset": true,
14
+ "attention_probs_dropout_prob": 0.1,
15
+ "classifier_dropout": null,
16
+ "cross_attention_frequency": 2,
17
+ "encoder_hidden_size": 1408,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.1,
20
+ "hidden_size": 768,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "blip_2_qformer",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "position_embedding_type": "absolute",
29
+ "torch_dtype": "float32",
30
+ "use_qformer_text_input": false,
31
+ "vocab_size": 30522
32
+ },
33
+ "text_config": {
34
+ "_name_or_path": "/media/gregor/DATA/projects/wuerzburg/mblip/checkpoints/mt0-xl/07_24_2023_08_03_33-1-79282",
35
+ "architectures": [
36
+ "MT5ForConditionalGeneration"
37
+ ],
38
+ "classifier_dropout": 0.0,
39
+ "d_ff": 5120,
40
+ "d_kv": 64,
41
+ "d_model": 2048,
42
+ "dense_act_fn": "gelu_new",
43
+ "dropout_rate": 0.1,
44
+ "feed_forward_proj": "gated-gelu",
45
+ "initializer_factor": 1.0,
46
+ "is_gated_act": true,
47
+ "layer_norm_epsilon": 1e-06,
48
+ "model_type": "mt5",
49
+ "num_decoder_layers": 24,
50
+ "num_heads": 32,
51
+ "num_layers": 24,
52
+ "output_past": true,
53
+ "relative_attention_max_distance": 128,
54
+ "relative_attention_num_buckets": 32,
55
+ "torch_dtype": "float32",
56
+ "use_cache": true,
57
+ "vocab_size": 250112
58
+ },
59
+ "tie_word_embeddings": false,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.51.0.dev0",
62
+ "use_decoder_only_language_model": false,
63
+ "vision_config": {
64
+ "_attn_implementation_autoset": true,
65
+ "attention_dropout": 0.0,
66
+ "dropout": 0.0,
67
+ "hidden_act": "gelu",
68
+ "hidden_size": 1408,
69
+ "image_size": 224,
70
+ "initializer_factor": 1.0,
71
+ "initializer_range": 1e-10,
72
+ "intermediate_size": 6144,
73
+ "layer_norm_eps": 1e-06,
74
+ "model_type": "blip_2_vision_model",
75
+ "num_attention_heads": 16,
76
+ "num_channels": 3,
77
+ "num_hidden_layers": 39,
78
+ "patch_size": 14,
79
+ "projection_dim": 512,
80
+ "qkv_bias": true,
81
+ "torch_dtype": "float32"
82
+ }
83
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.51.0.dev0"
7
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5457c476c70f7c34b603e1ace64d2f59059b3640a6d376b5b9c2e3818afd62d
3
+ size 4370847928
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec5edd5892ecfd5dd1a22492234f79147c4d6c748acb63f72ea857b3d51ce33
3
+ size 4997795800
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55800eeff90c28f6d4ba7de77848f9b6b0086127e6fc72a7e4f53a934530555b
3
+ size 4992280960
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72bd53cad60c3a23844308443efd35f2df6f8879aa173cb96ed684f455ddd1e6
3
+ size 4999412880
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "BlipImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "processor_class": "Blip2Processor",
18
+ "resample": 3,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ }
24
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "num_query_tokens": null,
3
+ "processor_class": "Blip2Processor"
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e10da31cf1cafe0e7bda647a5b7e37cba8a5acf176bfbf2d7f38dc479486b0c4
3
+ size 16315375
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "250100": {
29
+ "content": "<image>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "additional_special_tokens": [],
38
+ "clean_up_tokenization_spaces": true,
39
+ "eos_token": "</s>",
40
+ "extra_ids": 0,
41
+ "extra_special_tokens": {},
42
+ "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "<pad>",
44
+ "processor_class": "Blip2Processor",
45
+ "sp_model_kwargs": {},
46
+ "tokenizer_class": "T5Tokenizer",
47
+ "unk_token": "<unk>"
48
+ }