.gitattributes CHANGED
@@ -32,4 +32,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip 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
- tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
32
  *.zip 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
 
config.json CHANGED
@@ -1,6 +1,5 @@
1
  {
2
- "_commit_hash": "4d06f38b304fc2a331d9f3eab77a542afafc4ffb",
3
- "_name_or_path": "BAAI/AltCLIP",
4
  "architectures": [
5
  "AltCLIPModel"
6
  ],
@@ -11,12 +10,13 @@
11
  "num_layers": 3,
12
  "projection_dim": 768,
13
  "text_config": {
14
- "_name_or_path": "",
15
  "add_cross_attention": false,
16
- "architectures": null,
17
- "attention_probs_dropout_prob": 0.1,
 
 
18
  "bad_words_ids": null,
19
- "begin_suppress_tokens": null,
20
  "bos_token_id": 0,
21
  "chunk_size_feed_forward": 0,
22
  "classifier_dropout": null,
@@ -32,13 +32,12 @@
32
  "forced_bos_token_id": null,
33
  "forced_eos_token_id": null,
34
  "hidden_act": "gelu",
35
- "hidden_dropout_prob": 0.1,
36
  "hidden_size": 1024,
37
  "id2label": {
38
  "0": "LABEL_0",
39
  "1": "LABEL_1"
40
  },
41
- "initializer_factor": 0.02,
42
  "initializer_range": 0.02,
43
  "intermediate_size": 4096,
44
  "is_decoder": false,
@@ -48,6 +47,7 @@
48
  "LABEL_1": 1
49
  },
50
  "layer_norm_eps": 1e-05,
 
51
  "length_penalty": 1.0,
52
  "max_length": 20,
53
  "max_position_embeddings": 514,
@@ -61,6 +61,7 @@
61
  "num_return_sequences": 1,
62
  "output_attentions": false,
63
  "output_hidden_states": false,
 
64
  "output_scores": false,
65
  "pad_token_id": 1,
66
  "pooler_fn": "cls",
@@ -74,7 +75,6 @@
74
  "return_dict": true,
75
  "return_dict_in_generate": false,
76
  "sep_token_id": null,
77
- "suppress_tokens": null,
78
  "task_specific_params": null,
79
  "temperature": 1.0,
80
  "tf_legacy_loss": false,
@@ -85,7 +85,7 @@
85
  "top_p": 1.0,
86
  "torch_dtype": null,
87
  "torchscript": false,
88
- "transformers_version": "4.26.0.dev0",
89
  "type_vocab_size": 1,
90
  "typical_p": 1.0,
91
  "use_bfloat16": false,
@@ -107,7 +107,6 @@
107
  "architectures": null,
108
  "attention_dropout": 0.0,
109
  "bad_words_ids": null,
110
- "begin_suppress_tokens": null,
111
  "bos_token_id": null,
112
  "chunk_size_feed_forward": 0,
113
  "cross_attention_hidden_size": null,
@@ -157,14 +156,12 @@
157
  "patch_size": 14,
158
  "prefix": null,
159
  "problem_type": null,
160
- "projection_dim": 512,
161
  "pruned_heads": {},
162
  "remove_invalid_values": false,
163
  "repetition_penalty": 1.0,
164
  "return_dict": true,
165
  "return_dict_in_generate": false,
166
  "sep_token_id": null,
167
- "suppress_tokens": null,
168
  "task_specific_params": null,
169
  "temperature": 1.0,
170
  "tf_legacy_loss": false,
@@ -175,7 +172,7 @@
175
  "top_p": 1.0,
176
  "torch_dtype": null,
177
  "torchscript": false,
178
- "transformers_version": "4.26.0.dev0",
179
  "typical_p": 1.0,
180
  "use_bfloat16": false
181
  },
 
1
  {
2
+ "_name_or_path": "",
 
3
  "architectures": [
4
  "AltCLIPModel"
5
  ],
 
10
  "num_layers": 3,
11
  "projection_dim": 768,
12
  "text_config": {
13
+ "_name_or_path": "xlm-roberta-large",
14
  "add_cross_attention": false,
15
+ "architectures": [
16
+ "XLMRobertaForMaskedLM"
17
+ ],
18
+ "attention_probs_dropout_prob": 0.0,
19
  "bad_words_ids": null,
 
20
  "bos_token_id": 0,
21
  "chunk_size_feed_forward": 0,
22
  "classifier_dropout": null,
 
32
  "forced_bos_token_id": null,
33
  "forced_eos_token_id": null,
34
  "hidden_act": "gelu",
35
+ "hidden_dropout_prob": 0.0,
36
  "hidden_size": 1024,
37
  "id2label": {
38
  "0": "LABEL_0",
39
  "1": "LABEL_1"
40
  },
 
41
  "initializer_range": 0.02,
42
  "intermediate_size": 4096,
43
  "is_decoder": false,
 
47
  "LABEL_1": 1
48
  },
49
  "layer_norm_eps": 1e-05,
50
+ "learn_encoder": false,
51
  "length_penalty": 1.0,
52
  "max_length": 20,
53
  "max_position_embeddings": 514,
 
61
  "num_return_sequences": 1,
62
  "output_attentions": false,
63
  "output_hidden_states": false,
64
+ "output_past": true,
65
  "output_scores": false,
66
  "pad_token_id": 1,
67
  "pooler_fn": "cls",
 
75
  "return_dict": true,
76
  "return_dict_in_generate": false,
77
  "sep_token_id": null,
 
78
  "task_specific_params": null,
79
  "temperature": 1.0,
80
  "tf_legacy_loss": false,
 
85
  "top_p": 1.0,
86
  "torch_dtype": null,
87
  "torchscript": false,
88
+ "transformers_version": "4.21.1",
89
  "type_vocab_size": 1,
90
  "typical_p": 1.0,
91
  "use_bfloat16": false,
 
107
  "architectures": null,
108
  "attention_dropout": 0.0,
109
  "bad_words_ids": null,
 
110
  "bos_token_id": null,
111
  "chunk_size_feed_forward": 0,
112
  "cross_attention_hidden_size": null,
 
156
  "patch_size": 14,
157
  "prefix": null,
158
  "problem_type": null,
 
159
  "pruned_heads": {},
160
  "remove_invalid_values": false,
161
  "repetition_penalty": 1.0,
162
  "return_dict": true,
163
  "return_dict_in_generate": false,
164
  "sep_token_id": null,
 
165
  "task_specific_params": null,
166
  "temperature": 1.0,
167
  "tf_legacy_loss": false,
 
172
  "top_p": 1.0,
173
  "torch_dtype": null,
174
  "torchscript": false,
175
+ "transformers_version": "4.21.1",
176
  "typical_p": 1.0,
177
  "use_bfloat16": false
178
  },
preprocessor_config.json CHANGED
@@ -1,12 +1,8 @@
1
  {
2
- "crop_size": {
3
- "height": 224,
4
- "width": 224
5
- },
6
  "do_center_crop": true,
7
  "do_convert_rgb": true,
8
  "do_normalize": true,
9
- "do_rescale": true,
10
  "do_resize": true,
11
  "feature_extractor_type": "CLIPFeatureExtractor",
12
  "image_mean": [
@@ -14,7 +10,6 @@
14
  0.4578275,
15
  0.40821073
16
  ],
17
- "image_processor_type": "CLIPImageProcessor",
18
  "image_std": [
19
  0.26862954,
20
  0.26130258,
@@ -22,8 +17,5 @@
22
  ],
23
  "processor_class": "AltCLIPProcessor",
24
  "resample": 3,
25
- "rescale_factor": 0.00392156862745098,
26
- "size": {
27
- "shortest_edge": 224
28
- }
29
  }
 
1
  {
2
+ "crop_size": 224,
 
 
 
3
  "do_center_crop": true,
4
  "do_convert_rgb": true,
5
  "do_normalize": true,
 
6
  "do_resize": true,
7
  "feature_extractor_type": "CLIPFeatureExtractor",
8
  "image_mean": [
 
10
  0.4578275,
11
  0.40821073
12
  ],
 
13
  "image_std": [
14
  0.26862954,
15
  0.26130258,
 
17
  ],
18
  "processor_class": "AltCLIPProcessor",
19
  "resample": 3,
20
+ "size": 224
 
 
 
21
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0102cd1b26b61103dc89068d15cf02682f7bbd910e1ea99939f2bfc8c6772ebe
3
- size 3457011159
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e857ebe6ee6ea950e0ff7e616deeb698db12cbe5df0beb527b1f377850d012e8
3
+ size 3461239422
tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:de3788bb2f349135f2ad2e2b10dff3cee7f23fab906a5fbdadf20bc963b05b4c
3
- size 17098080
 
 
 
 
tokenizer_config.json CHANGED
@@ -11,9 +11,9 @@
11
  "single_word": false
12
  },
13
  "model_max_length": 512,
14
- "name_or_path": "BAAI/AltCLIP",
15
  "pad_token": "<pad>",
16
- "processor_class": "AltCLIPProcessor",
17
  "sep_token": "</s>",
18
  "sp_model_kwargs": {},
19
  "special_tokens_map_file": null,
 
11
  "single_word": false
12
  },
13
  "model_max_length": 512,
14
+ "name_or_path": "/sharefs/baai-mrnd/yzd/test/xlm-roberta-large",
15
  "pad_token": "<pad>",
16
+ "processor_class": "CHCLIPProcess",
17
  "sep_token": "</s>",
18
  "sp_model_kwargs": {},
19
  "special_tokens_map_file": null,