small-model-all-categories
Browse files- config.json +32 -36
- merges.txt +0 -0
- preprocessor_config.json +9 -11
- pytorch_model.bin +2 -2
- special_tokens_map.json +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- vocab.json +0 -0
config.json
CHANGED
@@ -1,57 +1,55 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"VisionTextDualEncoderModel"
|
4 |
],
|
5 |
"logit_scale_init_value": 2.6592,
|
6 |
"model_type": "vision-text-dual-encoder",
|
7 |
-
"projection_dim":
|
8 |
"text_config": {
|
9 |
-
"_name_or_path": "",
|
10 |
"add_cross_attention": false,
|
11 |
"architectures": [
|
12 |
-
"
|
13 |
],
|
14 |
"attention_probs_dropout_prob": 0.1,
|
15 |
"bad_words_ids": null,
|
16 |
-
"bos_token_id":
|
17 |
"chunk_size_feed_forward": 0,
|
18 |
"classifier_dropout": null,
|
19 |
"cross_attention_hidden_size": null,
|
20 |
"decoder_start_token_id": null,
|
21 |
-
"directionality": "bidi",
|
22 |
"diversity_penalty": 0.0,
|
23 |
"do_sample": false,
|
24 |
"early_stopping": false,
|
25 |
-
"embedding_size": 768,
|
26 |
"encoder_no_repeat_ngram_size": 0,
|
27 |
-
"eos_token_id":
|
28 |
"finetuning_task": null,
|
29 |
"forced_bos_token_id": null,
|
30 |
"forced_eos_token_id": null,
|
31 |
-
"gradient_checkpointing": false,
|
32 |
"hidden_act": "gelu",
|
33 |
"hidden_dropout_prob": 0.1,
|
34 |
-
"hidden_size":
|
35 |
"id2label": {
|
36 |
"0": "LABEL_0",
|
37 |
"1": "LABEL_1"
|
38 |
},
|
39 |
"initializer_range": 0.02,
|
40 |
-
"intermediate_size":
|
41 |
"is_decoder": false,
|
42 |
"is_encoder_decoder": false,
|
43 |
"label2id": {
|
44 |
"LABEL_0": 0,
|
45 |
"LABEL_1": 1
|
46 |
},
|
47 |
-
"layer_norm_eps": 1e-
|
48 |
"length_penalty": 1.0,
|
49 |
"max_length": 20,
|
50 |
"max_position_embeddings": 512,
|
51 |
"min_length": 0,
|
52 |
-
"model_type": "
|
53 |
"no_repeat_ngram_size": 0,
|
54 |
-
"num_attention_heads":
|
55 |
"num_beam_groups": 1,
|
56 |
"num_beams": 1,
|
57 |
"num_hidden_layers": 12,
|
@@ -59,12 +57,7 @@
|
|
59 |
"output_attentions": false,
|
60 |
"output_hidden_states": false,
|
61 |
"output_scores": false,
|
62 |
-
"pad_token_id":
|
63 |
-
"pooler_fc_size": 768,
|
64 |
-
"pooler_num_attention_heads": 12,
|
65 |
-
"pooler_num_fc_layers": 3,
|
66 |
-
"pooler_size_per_head": 128,
|
67 |
-
"pooler_type": "first_token_transform",
|
68 |
"position_embedding_type": "absolute",
|
69 |
"prefix": null,
|
70 |
"problem_type": null,
|
@@ -81,22 +74,24 @@
|
|
81 |
"tokenizer_class": null,
|
82 |
"top_k": 50,
|
83 |
"top_p": 1.0,
|
84 |
-
"torch_dtype":
|
85 |
"torchscript": false,
|
86 |
"transformers_version": "4.17.0",
|
87 |
-
"type_vocab_size":
|
88 |
"typical_p": 1.0,
|
89 |
"use_bfloat16": false,
|
90 |
"use_cache": true,
|
91 |
-
"vocab_size":
|
92 |
},
|
93 |
"torch_dtype": "float32",
|
94 |
"transformers_version": null,
|
95 |
"vision_config": {
|
96 |
-
"_name_or_path": "",
|
97 |
"add_cross_attention": false,
|
98 |
-
"architectures":
|
99 |
-
|
|
|
|
|
100 |
"bad_words_ids": null,
|
101 |
"bos_token_id": null,
|
102 |
"chunk_size_feed_forward": 0,
|
@@ -104,49 +99,50 @@
|
|
104 |
"decoder_start_token_id": null,
|
105 |
"diversity_penalty": 0.0,
|
106 |
"do_sample": false,
|
107 |
-
"dropout": 0.0,
|
108 |
"early_stopping": false,
|
109 |
"encoder_no_repeat_ngram_size": 0,
|
|
|
110 |
"eos_token_id": null,
|
111 |
"finetuning_task": null,
|
112 |
"forced_bos_token_id": null,
|
113 |
"forced_eos_token_id": null,
|
114 |
-
"
|
115 |
-
"
|
116 |
-
"hidden_size":
|
117 |
"id2label": {
|
118 |
"0": "LABEL_0",
|
119 |
"1": "LABEL_1"
|
120 |
},
|
121 |
"image_size": 224,
|
122 |
-
"initializer_factor": 1.0,
|
123 |
"initializer_range": 0.02,
|
124 |
-
"intermediate_size":
|
125 |
"is_decoder": false,
|
126 |
"is_encoder_decoder": false,
|
127 |
"label2id": {
|
128 |
"LABEL_0": 0,
|
129 |
"LABEL_1": 1
|
130 |
},
|
131 |
-
"layer_norm_eps": 1e-
|
132 |
"length_penalty": 1.0,
|
133 |
"max_length": 20,
|
134 |
"min_length": 0,
|
135 |
-
"model_type": "
|
136 |
"no_repeat_ngram_size": 0,
|
137 |
-
"num_attention_heads":
|
138 |
"num_beam_groups": 1,
|
139 |
"num_beams": 1,
|
|
|
140 |
"num_hidden_layers": 12,
|
141 |
"num_return_sequences": 1,
|
142 |
"output_attentions": false,
|
143 |
"output_hidden_states": false,
|
144 |
"output_scores": false,
|
145 |
"pad_token_id": null,
|
146 |
-
"patch_size":
|
147 |
"prefix": null,
|
148 |
"problem_type": null,
|
149 |
"pruned_heads": {},
|
|
|
150 |
"remove_invalid_values": false,
|
151 |
"repetition_penalty": 1.0,
|
152 |
"return_dict": true,
|
@@ -159,7 +155,7 @@
|
|
159 |
"tokenizer_class": null,
|
160 |
"top_k": 50,
|
161 |
"top_p": 1.0,
|
162 |
-
"torch_dtype":
|
163 |
"torchscript": false,
|
164 |
"transformers_version": "4.17.0",
|
165 |
"typical_p": 1.0,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "../Models/dual_encoder_pretrained",
|
3 |
"architectures": [
|
4 |
"VisionTextDualEncoderModel"
|
5 |
],
|
6 |
"logit_scale_init_value": 2.6592,
|
7 |
"model_type": "vision-text-dual-encoder",
|
8 |
+
"projection_dim": 256,
|
9 |
"text_config": {
|
10 |
+
"_name_or_path": "lassl/roberta-ko-small",
|
11 |
"add_cross_attention": false,
|
12 |
"architectures": [
|
13 |
+
"RobertaForMaskedLM"
|
14 |
],
|
15 |
"attention_probs_dropout_prob": 0.1,
|
16 |
"bad_words_ids": null,
|
17 |
+
"bos_token_id": 0,
|
18 |
"chunk_size_feed_forward": 0,
|
19 |
"classifier_dropout": null,
|
20 |
"cross_attention_hidden_size": null,
|
21 |
"decoder_start_token_id": null,
|
|
|
22 |
"diversity_penalty": 0.0,
|
23 |
"do_sample": false,
|
24 |
"early_stopping": false,
|
|
|
25 |
"encoder_no_repeat_ngram_size": 0,
|
26 |
+
"eos_token_id": 2,
|
27 |
"finetuning_task": null,
|
28 |
"forced_bos_token_id": null,
|
29 |
"forced_eos_token_id": null,
|
|
|
30 |
"hidden_act": "gelu",
|
31 |
"hidden_dropout_prob": 0.1,
|
32 |
+
"hidden_size": 256,
|
33 |
"id2label": {
|
34 |
"0": "LABEL_0",
|
35 |
"1": "LABEL_1"
|
36 |
},
|
37 |
"initializer_range": 0.02,
|
38 |
+
"intermediate_size": 1024,
|
39 |
"is_decoder": false,
|
40 |
"is_encoder_decoder": false,
|
41 |
"label2id": {
|
42 |
"LABEL_0": 0,
|
43 |
"LABEL_1": 1
|
44 |
},
|
45 |
+
"layer_norm_eps": 1e-05,
|
46 |
"length_penalty": 1.0,
|
47 |
"max_length": 20,
|
48 |
"max_position_embeddings": 512,
|
49 |
"min_length": 0,
|
50 |
+
"model_type": "roberta",
|
51 |
"no_repeat_ngram_size": 0,
|
52 |
+
"num_attention_heads": 4,
|
53 |
"num_beam_groups": 1,
|
54 |
"num_beams": 1,
|
55 |
"num_hidden_layers": 12,
|
|
|
57 |
"output_attentions": false,
|
58 |
"output_hidden_states": false,
|
59 |
"output_scores": false,
|
60 |
+
"pad_token_id": 1,
|
|
|
|
|
|
|
|
|
|
|
61 |
"position_embedding_type": "absolute",
|
62 |
"prefix": null,
|
63 |
"problem_type": null,
|
|
|
74 |
"tokenizer_class": null,
|
75 |
"top_k": 50,
|
76 |
"top_p": 1.0,
|
77 |
+
"torch_dtype": "float32",
|
78 |
"torchscript": false,
|
79 |
"transformers_version": "4.17.0",
|
80 |
+
"type_vocab_size": 1,
|
81 |
"typical_p": 1.0,
|
82 |
"use_bfloat16": false,
|
83 |
"use_cache": true,
|
84 |
+
"vocab_size": 51200
|
85 |
},
|
86 |
"torch_dtype": "float32",
|
87 |
"transformers_version": null,
|
88 |
"vision_config": {
|
89 |
+
"_name_or_path": "facebook/dino-vits8",
|
90 |
"add_cross_attention": false,
|
91 |
+
"architectures": [
|
92 |
+
"ViTModel"
|
93 |
+
],
|
94 |
+
"attention_probs_dropout_prob": 0.0,
|
95 |
"bad_words_ids": null,
|
96 |
"bos_token_id": null,
|
97 |
"chunk_size_feed_forward": 0,
|
|
|
99 |
"decoder_start_token_id": null,
|
100 |
"diversity_penalty": 0.0,
|
101 |
"do_sample": false,
|
|
|
102 |
"early_stopping": false,
|
103 |
"encoder_no_repeat_ngram_size": 0,
|
104 |
+
"encoder_stride": 16,
|
105 |
"eos_token_id": null,
|
106 |
"finetuning_task": null,
|
107 |
"forced_bos_token_id": null,
|
108 |
"forced_eos_token_id": null,
|
109 |
+
"hidden_act": "gelu",
|
110 |
+
"hidden_dropout_prob": 0.0,
|
111 |
+
"hidden_size": 384,
|
112 |
"id2label": {
|
113 |
"0": "LABEL_0",
|
114 |
"1": "LABEL_1"
|
115 |
},
|
116 |
"image_size": 224,
|
|
|
117 |
"initializer_range": 0.02,
|
118 |
+
"intermediate_size": 1536,
|
119 |
"is_decoder": false,
|
120 |
"is_encoder_decoder": false,
|
121 |
"label2id": {
|
122 |
"LABEL_0": 0,
|
123 |
"LABEL_1": 1
|
124 |
},
|
125 |
+
"layer_norm_eps": 1e-12,
|
126 |
"length_penalty": 1.0,
|
127 |
"max_length": 20,
|
128 |
"min_length": 0,
|
129 |
+
"model_type": "vit",
|
130 |
"no_repeat_ngram_size": 0,
|
131 |
+
"num_attention_heads": 6,
|
132 |
"num_beam_groups": 1,
|
133 |
"num_beams": 1,
|
134 |
+
"num_channels": 3,
|
135 |
"num_hidden_layers": 12,
|
136 |
"num_return_sequences": 1,
|
137 |
"output_attentions": false,
|
138 |
"output_hidden_states": false,
|
139 |
"output_scores": false,
|
140 |
"pad_token_id": null,
|
141 |
+
"patch_size": 8,
|
142 |
"prefix": null,
|
143 |
"problem_type": null,
|
144 |
"pruned_heads": {},
|
145 |
+
"qkv_bias": true,
|
146 |
"remove_invalid_values": false,
|
147 |
"repetition_penalty": 1.0,
|
148 |
"return_dict": true,
|
|
|
155 |
"tokenizer_class": null,
|
156 |
"top_k": 50,
|
157 |
"top_p": 1.0,
|
158 |
+
"torch_dtype": "float32",
|
159 |
"torchscript": false,
|
160 |
"transformers_version": "4.17.0",
|
161 |
"typical_p": 1.0,
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
CHANGED
@@ -1,20 +1,18 @@
|
|
1 |
{
|
2 |
-
"crop_size": 224,
|
3 |
-
"do_center_crop": true,
|
4 |
"do_normalize": true,
|
5 |
-
"do_resize":
|
6 |
-
"feature_extractor_type": "
|
7 |
"image_mean": [
|
8 |
-
0.
|
9 |
-
0.
|
10 |
-
0.
|
11 |
],
|
12 |
"image_std": [
|
13 |
-
0.
|
14 |
-
0.
|
15 |
-
0.
|
16 |
],
|
17 |
"processor_class": "VisionTextDualEncoderProcessor",
|
18 |
-
"resample":
|
19 |
"size": 224
|
20 |
}
|
|
|
1 |
{
|
|
|
|
|
2 |
"do_normalize": true,
|
3 |
+
"do_resize": true,
|
4 |
+
"feature_extractor_type": "ViTFeatureExtractor",
|
5 |
"image_mean": [
|
6 |
+
0.485,
|
7 |
+
0.456,
|
8 |
+
0.406
|
9 |
],
|
10 |
"image_std": [
|
11 |
+
0.229,
|
12 |
+
0.224,
|
13 |
+
0.225
|
14 |
],
|
15 |
"processor_class": "VisionTextDualEncoderProcessor",
|
16 |
+
"resample": 2,
|
17 |
"size": 224
|
18 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef1fe083f3fdf763d528e0872ce828b6ccc4be872598a9575a38413572095587
|
3 |
+
size 179228443
|
special_tokens_map.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"unk_token": "
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "../Models/dual_encoder_pretrained", "processor_class": "VisionTextDualEncoderProcessor", "tokenizer_class": "RobertaTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|