Mitchell Wortsman commited on
Commit
26d0b54
1 Parent(s): 40b5c7a

pytorch_model bin upload

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
  open_clip_pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
  open_clip_pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
36
+ pytorch_model-00001-of-00002.bin filter=lfs diff=lfs merge=lfs -text
37
+ pytorch_model-00002-of-00002.bin filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -1,176 +1,180 @@
1
  {
2
- "architectures": [
3
- "CLIPModel"
4
- ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "initializer_factor": 1.0,
6
- "logit_scale_init_value": 2.6592,
7
- "model_type": "clip",
8
- "projection_dim": 1280,
9
- "text_config": {
10
- "_name_or_path": "",
11
- "add_cross_attention": false,
12
- "architectures": null,
13
- "attention_dropout": 0.0,
14
- "bad_words_ids": null,
15
- "bos_token_id": 0,
16
- "chunk_size_feed_forward": 0,
17
- "cross_attention_hidden_size": null,
18
- "decoder_start_token_id": null,
19
- "diversity_penalty": 0.0,
20
- "do_sample": false,
21
- "dropout": 0.0,
22
- "early_stopping": false,
23
- "encoder_no_repeat_ngram_size": 0,
24
- "eos_token_id": 2,
25
- "exponential_decay_length_penalty": null,
26
- "finetuning_task": null,
27
- "forced_bos_token_id": null,
28
- "forced_eos_token_id": null,
29
- "hidden_act": "gelu",
30
- "hidden_size": 1280,
31
- "id2label": {
32
- "0": "LABEL_0",
33
- "1": "LABEL_1"
34
- },
35
- "initializer_factor": 1.0,
36
- "initializer_range": 0.02,
37
- "intermediate_size": 5120,
38
- "is_decoder": false,
39
- "is_encoder_decoder": false,
40
- "label2id": {
41
- "LABEL_0": 0,
42
- "LABEL_1": 1
43
- },
44
- "layer_norm_eps": 1e-05,
45
- "length_penalty": 1.0,
46
- "max_length": 20,
47
- "max_position_embeddings": 77,
48
- "min_length": 0,
49
- "model_type": "clip_text_model",
50
- "no_repeat_ngram_size": 0,
51
- "num_attention_heads": 20,
52
- "num_beam_groups": 1,
53
- "num_beams": 1,
54
- "num_hidden_layers": 32,
55
- "num_return_sequences": 1,
56
- "output_attentions": false,
57
- "output_hidden_states": false,
58
- "output_scores": false,
59
- "pad_token_id": 1,
60
- "prefix": null,
61
- "problem_type": null,
62
- "pruned_heads": {},
63
- "remove_invalid_values": false,
64
- "repetition_penalty": 1.0,
65
- "return_dict": true,
66
- "return_dict_in_generate": false,
67
- "sep_token_id": null,
68
- "task_specific_params": null,
69
- "temperature": 1.0,
70
- "tf_legacy_loss": false,
71
- "tie_encoder_decoder": false,
72
- "tie_word_embeddings": true,
73
- "tokenizer_class": null,
74
- "top_k": 50,
75
- "top_p": 1.0,
76
- "torch_dtype": null,
77
- "torchscript": false,
78
- "transformers_version": "4.21.3",
79
- "typical_p": 1.0,
80
- "use_bfloat16": false,
81
- "vocab_size": 49408
82
  },
83
- "text_config_dict": {
84
- "hidden_act": "gelu",
85
- "hidden_size": 1280,
86
- "intermediate_size": 5120,
87
- "num_attention_heads": 20,
88
- "num_hidden_layers": 32
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89
  },
90
- "torch_dtype": "float32",
91
- "transformers_version": null,
92
- "vision_config": {
93
- "_name_or_path": "",
94
- "add_cross_attention": false,
95
- "architectures": null,
96
- "attention_dropout": 0.0,
97
- "bad_words_ids": null,
98
- "bos_token_id": null,
99
- "chunk_size_feed_forward": 0,
100
- "cross_attention_hidden_size": null,
101
- "decoder_start_token_id": null,
102
- "diversity_penalty": 0.0,
103
- "do_sample": false,
104
- "dropout": 0.0,
105
- "early_stopping": false,
106
- "encoder_no_repeat_ngram_size": 0,
107
- "eos_token_id": null,
108
- "exponential_decay_length_penalty": null,
109
- "finetuning_task": null,
110
- "forced_bos_token_id": null,
111
- "forced_eos_token_id": null,
112
- "hidden_act": "gelu",
113
- "hidden_size": 1664,
114
- "id2label": {
115
- "0": "LABEL_0",
116
- "1": "LABEL_1"
117
- },
118
- "image_size": 224,
119
- "initializer_factor": 1.0,
120
- "initializer_range": 0.02,
121
- "intermediate_size": 8192,
122
- "is_decoder": false,
123
- "is_encoder_decoder": false,
124
- "label2id": {
125
- "LABEL_0": 0,
126
- "LABEL_1": 1
127
- },
128
- "layer_norm_eps": 1e-05,
129
- "length_penalty": 1.0,
130
- "max_length": 20,
131
- "min_length": 0,
132
- "model_type": "clip_vision_model",
133
- "no_repeat_ngram_size": 0,
134
- "num_attention_heads": 16,
135
- "num_beam_groups": 1,
136
- "num_beams": 1,
137
- "num_channels": 3,
138
- "num_hidden_layers": 48,
139
- "num_return_sequences": 1,
140
- "output_attentions": false,
141
- "output_hidden_states": false,
142
- "output_scores": false,
143
- "pad_token_id": null,
144
- "patch_size": 14,
145
- "prefix": null,
146
- "problem_type": null,
147
- "pruned_heads": {},
148
- "remove_invalid_values": false,
149
- "repetition_penalty": 1.0,
150
- "return_dict": true,
151
- "return_dict_in_generate": false,
152
- "sep_token_id": null,
153
- "task_specific_params": null,
154
- "temperature": 1.0,
155
- "tf_legacy_loss": false,
156
- "tie_encoder_decoder": false,
157
- "tie_word_embeddings": true,
158
- "tokenizer_class": null,
159
- "top_k": 50,
160
- "top_p": 1.0,
161
- "torch_dtype": null,
162
- "torchscript": false,
163
- "transformers_version": "4.21.3",
164
- "typical_p": 1.0,
165
- "use_bfloat16": false
166
  },
167
- "vision_config_dict": {
168
- "hidden_act": "gelu",
169
- "hidden_size": 1664,
170
- "intermediate_size": 8192,
171
- "num_attention_heads": 16,
172
- "num_hidden_layers": 48,
173
- "patch_size": 14
174
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
175
  }
176
-
 
1
  {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "CLIPModel"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 1280,
10
+ "text_config": {
11
+ "_name_or_path": "",
12
+ "add_cross_attention": false,
13
+ "architectures": null,
14
+ "attention_dropout": 0.0,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": 0,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "dropout": 0.0,
24
+ "early_stopping": false,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": 2,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "hidden_act": "gelu",
32
+ "hidden_size": 1280,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
  "initializer_factor": 1.0,
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 5120,
40
+ "is_decoder": false,
41
+ "is_encoder_decoder": false,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  },
46
+ "layer_norm_eps": 1e-05,
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 77,
50
+ "min_length": 0,
51
+ "model_type": "clip_text_model",
52
+ "no_repeat_ngram_size": 0,
53
+ "num_attention_heads": 20,
54
+ "num_beam_groups": 1,
55
+ "num_beams": 1,
56
+ "num_hidden_layers": 32,
57
+ "num_return_sequences": 1,
58
+ "output_attentions": false,
59
+ "output_hidden_states": false,
60
+ "output_scores": false,
61
+ "pad_token_id": 1,
62
+ "prefix": null,
63
+ "problem_type": null,
64
+ "pruned_heads": {},
65
+ "remove_invalid_values": false,
66
+ "repetition_penalty": 1.0,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "sep_token_id": null,
70
+ "suppress_tokens": null,
71
+ "task_specific_params": null,
72
+ "temperature": 1.0,
73
+ "tf_legacy_loss": false,
74
+ "tie_encoder_decoder": false,
75
+ "tie_word_embeddings": true,
76
+ "tokenizer_class": null,
77
+ "top_k": 50,
78
+ "top_p": 1.0,
79
+ "torch_dtype": null,
80
+ "torchscript": false,
81
+ "transformers_version": "4.24.0",
82
+ "typical_p": 1.0,
83
+ "use_bfloat16": false,
84
+ "vocab_size": 49408
85
+ },
86
+ "text_config_dict": {
87
+ "hidden_act": "gelu",
88
+ "hidden_size": 1280,
89
+ "intermediate_size": 5120,
90
+ "num_attention_heads": 20,
91
+ "num_hidden_layers": 32
92
+ },
93
+ "torch_dtype": "float32",
94
+ "transformers_version": null,
95
+ "vision_config": {
96
+ "_name_or_path": "",
97
+ "add_cross_attention": false,
98
+ "architectures": null,
99
+ "attention_dropout": 0.0,
100
+ "bad_words_ids": null,
101
+ "begin_suppress_tokens": null,
102
+ "bos_token_id": null,
103
+ "chunk_size_feed_forward": 0,
104
+ "cross_attention_hidden_size": null,
105
+ "decoder_start_token_id": null,
106
+ "diversity_penalty": 0.0,
107
+ "do_sample": false,
108
+ "dropout": 0.0,
109
+ "early_stopping": false,
110
+ "encoder_no_repeat_ngram_size": 0,
111
+ "eos_token_id": null,
112
+ "exponential_decay_length_penalty": null,
113
+ "finetuning_task": null,
114
+ "forced_bos_token_id": null,
115
+ "forced_eos_token_id": null,
116
+ "hidden_act": "gelu",
117
+ "hidden_size": 1664,
118
+ "id2label": {
119
+ "0": "LABEL_0",
120
+ "1": "LABEL_1"
121
  },
122
+ "image_size": 224,
123
+ "initializer_factor": 1.0,
124
+ "initializer_range": 0.02,
125
+ "intermediate_size": 8192,
126
+ "is_decoder": false,
127
+ "is_encoder_decoder": false,
128
+ "label2id": {
129
+ "LABEL_0": 0,
130
+ "LABEL_1": 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
131
  },
132
+ "layer_norm_eps": 1e-05,
133
+ "length_penalty": 1.0,
134
+ "max_length": 20,
135
+ "min_length": 0,
136
+ "model_type": "clip_vision_model",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 16,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_channels": 3,
142
+ "num_hidden_layers": 48,
143
+ "num_return_sequences": 1,
144
+ "output_attentions": false,
145
+ "output_hidden_states": false,
146
+ "output_scores": false,
147
+ "pad_token_id": null,
148
+ "patch_size": 14,
149
+ "prefix": null,
150
+ "problem_type": null,
151
+ "pruned_heads": {},
152
+ "remove_invalid_values": false,
153
+ "repetition_penalty": 1.0,
154
+ "return_dict": true,
155
+ "return_dict_in_generate": false,
156
+ "sep_token_id": null,
157
+ "suppress_tokens": null,
158
+ "task_specific_params": null,
159
+ "temperature": 1.0,
160
+ "tf_legacy_loss": false,
161
+ "tie_encoder_decoder": false,
162
+ "tie_word_embeddings": true,
163
+ "tokenizer_class": null,
164
+ "top_k": 50,
165
+ "top_p": 1.0,
166
+ "torch_dtype": null,
167
+ "torchscript": false,
168
+ "transformers_version": "4.24.0",
169
+ "typical_p": 1.0,
170
+ "use_bfloat16": false
171
+ },
172
+ "vision_config_dict": {
173
+ "hidden_act": "gelu",
174
+ "hidden_size": 1664,
175
+ "intermediate_size": 8192,
176
+ "num_attention_heads": 16,
177
+ "num_hidden_layers": 48,
178
+ "patch_size": 14
179
  }
180
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79cfbc5cb39085ce8eedff70562d3c54795abdccd132d6dcb8e1462fbd71a1a0
3
+ size 9990161549
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31847ed3e29dade79ab29eafc0f8230200ec46233ce1d8f6e71b987a9fbacf47
3
+ size 168539369
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff