Hugging Face's logo

MohamedAhmedAE
/
Clip-Roco_Version2_v3

Safetensors
clip
Model card Files Community
MohamedAhmedAE commited on
Commit
dc8fda9
•
1 Parent(s): 24efb8a

Training in progress, step 200

Browse files
Files changed (9) hide show
  1. config.json +46 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +28 -0
  5. special_tokens_map.json +51 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +59 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/.cache/huggingface/hub/Clip-Roco_Version2_v3",
3
+ "architectures": [
4
+ "CLIPModel"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 512,
10
+ "text_config": {
11
+ "_name_or_path": "/kaggle/working/TextModel",
12
+ "architectures": [
13
+ "RobertaModel"
14
+ ],
15
+ "attention_probs_dropout_prob": 0.1,
16
+ "bos_token_id": 0,
17
+ "classifier_dropout": null,
18
+ "eos_token_id": 2,
19
+ "hidden_act": "gelu",
20
+ "hidden_dropout_prob": 0.1,
21
+ "hidden_size": 768,
22
+ "intermediate_size": 3072,
23
+ "max_position_embeddings": 1026,
24
+ "model_type": "clip_text_model",
25
+ "num_attention_heads": 12,
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "type_vocab_size": 1,
29
+ "use_cache": true,
30
+ "vocab_size": 50265
31
+ },
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.42.3",
34
+ "vision_config": {
35
+ "_name_or_path": "openai/clip-vit-large-patch14-336",
36
+ "dropout": 0.0,
37
+ "hidden_size": 1024,
38
+ "image_size": 336,
39
+ "intermediate_size": 4096,
40
+ "model_type": "clip_vision_model",
41
+ "num_attention_heads": 16,
42
+ "num_hidden_layers": 24,
43
+ "patch_size": 14,
44
+ "projection_dim": 768
45
+ }
46
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773cc262203d85ff6a2aa1fe9d91ecbbd524df3111b609cfc0935c4e59b24565
3
+ size 1715561468
preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 336,
4
+ "width": 336
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "processor_class": "CLIPProcessor",
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 336
27
+ }
28
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_len": 512,
52
+ "model_max_length": 1024,
53
+ "pad_token": "<pad>",
54
+ "processor_class": "CLIPProcessor",
55
+ "sep_token": "</s>",
56
+ "tokenizer_class": "CLIPTokenizer",
57
+ "trim_offsets": true,
58
+ "unk_token": "<unk>"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5f77ee2eb256c41436412ee409e9ee9618ee717832327e403d23411e2cb2d9b
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff