Model save
Browse files- .gitignore +1 -0
- config.json +183 -0
- gaudi_config.json +37 -0
- merges.txt +0 -0
- preprocessor_config.json +27 -0
- pytorch_model.bin +3 -0
- runs/Jun28_09-52-53_sysid552968gaudi2/1687945996.750963/events.out.tfevents.1687945996.sysid552968gaudi2.17755.1 +3 -0
- runs/Jun28_09-52-53_sysid552968gaudi2/events.out.tfevents.1687945996.sysid552968gaudi2.17755.0 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": "0e15d648ae27b0a8cf94b61ddc731ddca76f6ee2",
|
3 |
+
"_name_or_path": "BridgeTower/bridgetower-large-itm-mlm-itc",
|
4 |
+
"architectures": [
|
5 |
+
"BridgeTowerForContrastiveLearning"
|
6 |
+
],
|
7 |
+
"contrastive_hidden_size": 512,
|
8 |
+
"drop_rate": 0.1,
|
9 |
+
"head_hidden_scale": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"init_layernorm_from_vision_encoder": false,
|
13 |
+
"initializer_factor": 1,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"link_tower_type": "add",
|
16 |
+
"logit_scale_init_value": 2.6592,
|
17 |
+
"model_type": "bridgetower",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 6,
|
20 |
+
"share_cross_modal_transformer_layers": true,
|
21 |
+
"share_link_tower_layers": false,
|
22 |
+
"text_config": {
|
23 |
+
"_name_or_path": "",
|
24 |
+
"add_cross_attention": false,
|
25 |
+
"architectures": [
|
26 |
+
"BridgeTowerTextModel"
|
27 |
+
],
|
28 |
+
"attention_probs_dropout_prob": 0.1,
|
29 |
+
"bad_words_ids": null,
|
30 |
+
"begin_suppress_tokens": null,
|
31 |
+
"bos_token_id": 0,
|
32 |
+
"chunk_size_feed_forward": 0,
|
33 |
+
"classifier_dropout": null,
|
34 |
+
"cross_attention_hidden_size": null,
|
35 |
+
"decoder_start_token_id": null,
|
36 |
+
"diversity_penalty": 0.0,
|
37 |
+
"do_sample": false,
|
38 |
+
"early_stopping": false,
|
39 |
+
"encoder_no_repeat_ngram_size": 0,
|
40 |
+
"eos_token_id": 2,
|
41 |
+
"exponential_decay_length_penalty": null,
|
42 |
+
"finetuning_task": null,
|
43 |
+
"forced_bos_token_id": null,
|
44 |
+
"forced_eos_token_id": null,
|
45 |
+
"hidden_act": "gelu",
|
46 |
+
"hidden_dropout_prob": 0.1,
|
47 |
+
"hidden_size": 1024,
|
48 |
+
"id2label": {
|
49 |
+
"0": "LABEL_0",
|
50 |
+
"1": "LABEL_1"
|
51 |
+
},
|
52 |
+
"initializer_factor": 1,
|
53 |
+
"initializer_range": 0.02,
|
54 |
+
"intermediate_size": 4096,
|
55 |
+
"is_decoder": false,
|
56 |
+
"is_encoder_decoder": false,
|
57 |
+
"label2id": {
|
58 |
+
"LABEL_0": 0,
|
59 |
+
"LABEL_1": 1
|
60 |
+
},
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"length_penalty": 1.0,
|
63 |
+
"max_length": 20,
|
64 |
+
"max_position_embeddings": 514,
|
65 |
+
"min_length": 0,
|
66 |
+
"model_type": "bridgetower_text_model",
|
67 |
+
"no_repeat_ngram_size": 0,
|
68 |
+
"num_attention_heads": 16,
|
69 |
+
"num_beam_groups": 1,
|
70 |
+
"num_beams": 1,
|
71 |
+
"num_hidden_layers": 24,
|
72 |
+
"num_return_sequences": 1,
|
73 |
+
"output_attentions": false,
|
74 |
+
"output_hidden_states": false,
|
75 |
+
"output_scores": false,
|
76 |
+
"pad_token_id": 1,
|
77 |
+
"position_embedding_type": "absolute",
|
78 |
+
"prefix": null,
|
79 |
+
"problem_type": null,
|
80 |
+
"pruned_heads": {},
|
81 |
+
"remove_invalid_values": false,
|
82 |
+
"repetition_penalty": 1.0,
|
83 |
+
"return_dict": true,
|
84 |
+
"return_dict_in_generate": false,
|
85 |
+
"sep_token_id": null,
|
86 |
+
"suppress_tokens": null,
|
87 |
+
"task_specific_params": null,
|
88 |
+
"temperature": 1.0,
|
89 |
+
"tf_legacy_loss": false,
|
90 |
+
"tie_encoder_decoder": false,
|
91 |
+
"tie_word_embeddings": true,
|
92 |
+
"tokenizer_class": null,
|
93 |
+
"top_k": 50,
|
94 |
+
"top_p": 1.0,
|
95 |
+
"torch_dtype": null,
|
96 |
+
"torchscript": false,
|
97 |
+
"transformers_version": "4.28.1",
|
98 |
+
"type_vocab_size": 1,
|
99 |
+
"typical_p": 1.0,
|
100 |
+
"use_bfloat16": false,
|
101 |
+
"use_cache": true,
|
102 |
+
"vocab_size": 50265
|
103 |
+
},
|
104 |
+
"tie_word_embeddings": false,
|
105 |
+
"torch_dtype": "float32",
|
106 |
+
"transformers_version": null,
|
107 |
+
"vision_config": {
|
108 |
+
"_name_or_path": "",
|
109 |
+
"add_cross_attention": false,
|
110 |
+
"architectures": [
|
111 |
+
"BridgeTowerVisionModel"
|
112 |
+
],
|
113 |
+
"bad_words_ids": null,
|
114 |
+
"begin_suppress_tokens": null,
|
115 |
+
"bos_token_id": null,
|
116 |
+
"chunk_size_feed_forward": 0,
|
117 |
+
"cross_attention_hidden_size": null,
|
118 |
+
"decoder_start_token_id": null,
|
119 |
+
"diversity_penalty": 0.0,
|
120 |
+
"do_sample": false,
|
121 |
+
"early_stopping": false,
|
122 |
+
"encoder_no_repeat_ngram_size": 0,
|
123 |
+
"eos_token_id": null,
|
124 |
+
"exponential_decay_length_penalty": null,
|
125 |
+
"finetuning_task": null,
|
126 |
+
"forced_bos_token_id": null,
|
127 |
+
"forced_eos_token_id": null,
|
128 |
+
"hidden_size": 1024,
|
129 |
+
"id2label": {
|
130 |
+
"0": "LABEL_0",
|
131 |
+
"1": "LABEL_1"
|
132 |
+
},
|
133 |
+
"image_size": 294,
|
134 |
+
"initializer_factor": 1,
|
135 |
+
"is_decoder": false,
|
136 |
+
"is_encoder_decoder": false,
|
137 |
+
"label2id": {
|
138 |
+
"LABEL_0": 0,
|
139 |
+
"LABEL_1": 1
|
140 |
+
},
|
141 |
+
"layer_norm_eps": 1e-05,
|
142 |
+
"length_penalty": 1.0,
|
143 |
+
"max_length": 20,
|
144 |
+
"min_length": 0,
|
145 |
+
"model_type": "bridgetower_vision_model",
|
146 |
+
"no_repeat_ngram_size": 0,
|
147 |
+
"num_beam_groups": 1,
|
148 |
+
"num_beams": 1,
|
149 |
+
"num_channels": 3,
|
150 |
+
"num_hidden_layers": 24,
|
151 |
+
"num_return_sequences": 1,
|
152 |
+
"output_attentions": false,
|
153 |
+
"output_hidden_states": false,
|
154 |
+
"output_scores": false,
|
155 |
+
"pad_token_id": null,
|
156 |
+
"patch_size": 14,
|
157 |
+
"prefix": null,
|
158 |
+
"problem_type": null,
|
159 |
+
"pruned_heads": {},
|
160 |
+
"remove_invalid_values": false,
|
161 |
+
"remove_last_layer": false,
|
162 |
+
"repetition_penalty": 1.0,
|
163 |
+
"return_dict": true,
|
164 |
+
"return_dict_in_generate": false,
|
165 |
+
"sep_token_id": null,
|
166 |
+
"share_layernorm": true,
|
167 |
+
"stop_gradient": false,
|
168 |
+
"suppress_tokens": null,
|
169 |
+
"task_specific_params": null,
|
170 |
+
"temperature": 1.0,
|
171 |
+
"tf_legacy_loss": false,
|
172 |
+
"tie_encoder_decoder": false,
|
173 |
+
"tie_word_embeddings": true,
|
174 |
+
"tokenizer_class": null,
|
175 |
+
"top_k": 50,
|
176 |
+
"top_p": 1.0,
|
177 |
+
"torch_dtype": null,
|
178 |
+
"torchscript": false,
|
179 |
+
"transformers_version": "4.28.1",
|
180 |
+
"typical_p": 1.0,
|
181 |
+
"use_bfloat16": false
|
182 |
+
}
|
183 |
+
}
|
gaudi_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"hmp_bf16_ops": [
|
3 |
+
"add",
|
4 |
+
"addmm",
|
5 |
+
"bmm",
|
6 |
+
"div",
|
7 |
+
"dropout",
|
8 |
+
"gelu",
|
9 |
+
"iadd",
|
10 |
+
"linear",
|
11 |
+
"layer_norm",
|
12 |
+
"matmul",
|
13 |
+
"mm",
|
14 |
+
"rsub",
|
15 |
+
"softmax",
|
16 |
+
"truediv",
|
17 |
+
"conv2d",
|
18 |
+
"dot",
|
19 |
+
"mul",
|
20 |
+
"mean"
|
21 |
+
],
|
22 |
+
"hmp_fp32_ops": [
|
23 |
+
"embedding",
|
24 |
+
"nll_loss",
|
25 |
+
"log_softmax",
|
26 |
+
"cross_entropy",
|
27 |
+
"binary_cross_entropy"
|
28 |
+
],
|
29 |
+
"hmp_is_verbose": false,
|
30 |
+
"hmp_opt_level": "O1",
|
31 |
+
"optimum_version": "1.8.8",
|
32 |
+
"transformers_version": "4.28.1",
|
33 |
+
"use_fused_adam": true,
|
34 |
+
"use_fused_clip_norm": true,
|
35 |
+
"use_habana_mixed_precision": true,
|
36 |
+
"use_torch_autocast": false
|
37 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_center_crop": true,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_pad": true,
|
5 |
+
"do_rescale": true,
|
6 |
+
"do_resize": true,
|
7 |
+
"image_mean": [
|
8 |
+
0.48145466,
|
9 |
+
0.4578275,
|
10 |
+
0.40821073
|
11 |
+
],
|
12 |
+
"image_processor_type": "BridgeTowerImageProcessor",
|
13 |
+
"image_std": [
|
14 |
+
0.26862954,
|
15 |
+
0.26130258,
|
16 |
+
0.27577711
|
17 |
+
],
|
18 |
+
"max_text_len": 50,
|
19 |
+
"resample": 3,
|
20 |
+
"rescale_factor": 0.00392156862745098,
|
21 |
+
"size": {
|
22 |
+
"shortest_edge": 294
|
23 |
+
},
|
24 |
+
"size_divisor": 32,
|
25 |
+
"tokenizer": "roberta-large",
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62abfac87aa4f7b8410754ffeeb15cd7f99be310f31657af4a63f0777c928eb4
|
3 |
+
size 3462621995
|
runs/Jun28_09-52-53_sysid552968gaudi2/1687945996.750963/events.out.tfevents.1687945996.sysid552968gaudi2.17755.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37c946450c1eae911357889ef8d7496b126c007324e5fdb56293de2c9228584b
|
3 |
+
size 6573
|
runs/Jun28_09-52-53_sysid552968gaudi2/events.out.tfevents.1687945996.sysid552968gaudi2.17755.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f119f381eb40b64d716dbe922ffe9d82dcbb3882ab0b901b38fd4562519856a9
|
3 |
+
size 14598
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "<s>",
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"errors": "replace",
|
8 |
+
"mask_token": "<mask>",
|
9 |
+
"model_max_length": 1000000000000000019884624838656,
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "</s>",
|
12 |
+
"tokenizer_class": "RobertaTokenizer",
|
13 |
+
"trim_offsets": true,
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:730e4b2d41af19537ec88a58d9f10a75570d4537647219458b96d879e15a61d6
|
3 |
+
size 4027
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|