Safetensors
wolfgangblack commited on
Commit
ae230f8
1 Parent(s): d594981

Upload 18 files

Browse files
models/baseresNet18/best_model_params.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a3620131e9933ba55c1489ad363b4101eb922e04113cc5b53ef77a0fb39811c
3
+ size 44796394
models/baseresNet50/best_model_params.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e22799c79cd7b23cab930ed73e04f1a65f86c2588118359370f92e483fdc3fe
3
+ size 94393946
models/bestresNet50/best_model_params.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e8e5dd4e6152e3cc37d935c9ebdc716c9aaf5096b5e337f60ca126f1b1e2e48
3
+ size 94393946
models/promptMovieBert/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "PG",
13
+ "1": "PG13",
14
+ "2": "R",
15
+ "3": "X",
16
+ "4": "XXX"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "PG": 0,
21
+ "PG13": 1,
22
+ "R": 2,
23
+ "X": 3,
24
+ "XXX": 4
25
+ },
26
+ "max_position_embeddings": 512,
27
+ "model_type": "distilbert",
28
+ "n_heads": 12,
29
+ "n_layers": 6,
30
+ "pad_token_id": 0,
31
+ "problem_type": "single_label_classification",
32
+ "qa_dropout": 0.1,
33
+ "seq_classif_dropout": 0.2,
34
+ "sinusoidal_pos_embds": false,
35
+ "tie_weights_": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.39.3",
38
+ "vocab_size": 30522
39
+ }
models/promptMovieBert/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30c6642ca63222b3d93a646214d678aa07163aa69d825ac71223598d9538da4a
3
+ size 267841796
models/promptMovieBert/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
models/promptMovieBert/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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
models/promptMovieBert/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fc7cb72b3945fe78a8cd61ce4a8b1b016ac35384f4738a5ac14eaab8bc5a624
3
+ size 4920
models/promptMovieBert/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
models/promptMovieRoberta/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/roberta-large-mnli",
3
+ "_num_labels": 3,
4
+ "architectures": [
5
+ "RobertaForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "PG",
16
+ "1": "PG13",
17
+ "2": "R",
18
+ "3": "X",
19
+ "4": "XXX"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 4096,
23
+ "label2id": {
24
+ "PG": 0,
25
+ "PG13": 1,
26
+ "R": 2,
27
+ "X": 3,
28
+ "XXX": 4
29
+ },
30
+ "layer_norm_eps": 1e-05,
31
+ "max_position_embeddings": 514,
32
+ "model_type": "roberta",
33
+ "num_attention_heads": 16,
34
+ "num_hidden_layers": 24,
35
+ "pad_token_id": 1,
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.39.3",
40
+ "type_vocab_size": 1,
41
+ "use_cache": true,
42
+ "vocab_size": 50265
43
+ }
models/promptMovieRoberta/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
models/promptMovieRoberta/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb81cf3b3eb07f17f9922a072e95f983d265a38fc0ee0ae87567bccc612d5886
3
+ size 1421507716
models/promptMovieRoberta/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
models/promptMovieRoberta/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
models/promptMovieRoberta/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
models/promptMovieRoberta/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89214cef336b7fea946c45ddebf2834faa6d5072d1db9c28b9a32eb2700b2c0d
3
+ size 4920
models/promptMovieRoberta/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
models/readme.md ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## Dataset
2
+
3
+ These models are trained on the 13k images dataset from the community images sourced 4/8/24. The 13k images had to have >2 reviewed labels with >50% community agreement. The dataset consists of prompts, tags, and images - although at this time the tags were neglected since there are considerable post-generation additions by the community and moderator, and this data would not be available at the time of scoring.
4
+
5
+ ## Training details
6
+
7
+ model: baseresNet18
8
+ - epochs: 39
9
+ - stopped due to early stopping
10
+ - train_test_split: .85/.15
11
+ - augmentations: None
12
+
13
+ model: baseresNet50
14
+ - epochs: 39
15
+ - stopped due to early stopping
16
+ - train_test_split: .85/.15
17
+ - augmentations: None
18
+
19
+ model: bestresNet50
20
+ - epochs: 25
21
+ - stopped due to max epochs
22
+ - train_test_split: .8/.2
23
+ - augmentations: RandomRotation, RandomHorizontalFlip, RandomResizedCrop
24
+
25
+ model: promptMovieBert
26
+ - epochs: 10
27
+ - test_train_split: .9/.1
28
+
29
+ model: promptMovieRoberta
30
+ - epochs: 10
31
+ - test_train_split: .9/.1