jzhoubu commited on
Commit
f50b412
1 Parent(s): 0ec64a3

Upload Retriever

Browse files
Files changed (2) hide show
  1. config.json +1 -138
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -5,157 +5,20 @@
5
  ],
6
  "device": null,
7
  "encoder_p": {
8
- "_name_or_path": "",
9
- "add_cross_attention": false,
10
- "architectures": null,
11
- "bad_words_ids": null,
12
- "begin_suppress_tokens": null,
13
- "bos_token_id": null,
14
- "chunk_size_feed_forward": 0,
15
- "cross_attention_hidden_size": null,
16
- "decoder_start_token_id": null,
17
- "diversity_penalty": 0.0,
18
- "do_sample": false,
19
- "early_stopping": false,
20
- "encoder_no_repeat_ngram_size": 0,
21
- "eos_token_id": null,
22
- "exponential_decay_length_penalty": null,
23
- "finetuning_task": null,
24
- "forced_bos_token_id": null,
25
- "forced_eos_token_id": null,
26
  "heads": 12,
27
- "id2label": {
28
- "0": "LABEL_0",
29
- "1": "LABEL_1"
30
- },
31
- "is_decoder": false,
32
- "is_encoder_decoder": false,
33
- "label2id": {
34
- "LABEL_0": 0,
35
- "LABEL_1": 1
36
- },
37
  "layers": 12,
38
- "length_penalty": 1.0,
39
- "max_length": 20,
40
- "min_length": 0,
41
- "model_type": "",
42
- "no_repeat_ngram_size": 0,
43
- "num_beam_groups": 1,
44
- "num_beams": 1,
45
- "num_return_sequences": 1,
46
- "output_attentions": false,
47
- "output_hidden_states": false,
48
- "output_scores": false,
49
- "pad_token_id": null,
50
  "patch_size": 32,
51
- "prefix": null,
52
- "problem_type": null,
53
- "pruned_heads": {},
54
- "remove_invalid_values": false,
55
- "repetition_penalty": 1.0,
56
  "resolution": 224,
57
- "return_dict": true,
58
- "return_dict_in_generate": false,
59
- "sep_token_id": null,
60
- "suppress_tokens": null,
61
- "task_specific_params": null,
62
- "temperature": 1.0,
63
- "tf_legacy_loss": false,
64
- "tie_encoder_decoder": false,
65
- "tie_word_embeddings": true,
66
- "tokenizer_class": null,
67
  "tokenizer_id": "bert-base-uncased",
68
- "top_k": 50,
69
- "top_p": 1.0,
70
  "topk": 768,
71
- "torch_dtype": null,
72
- "torchscript": false,
73
  "type": "vdr_cm_image",
74
- "typical_p": 1.0,
75
- "use_bfloat16": false,
76
  "width": 768
77
  },
78
  "encoder_q": {
79
- "_name_or_path": "",
80
- "add_cross_attention": false,
81
- "architectures": null,
82
- "attention_probs_dropout_prob": 0.1,
83
- "bad_words_ids": null,
84
- "begin_suppress_tokens": null,
85
- "bos_token_id": null,
86
- "chunk_size_feed_forward": 0,
87
- "classifier_dropout": null,
88
- "cross_attention_hidden_size": null,
89
- "decoder_start_token_id": null,
90
- "diversity_penalty": 0.0,
91
- "do_sample": false,
92
- "early_stopping": false,
93
- "encoder_no_repeat_ngram_size": 0,
94
- "eos_token_id": null,
95
- "exponential_decay_length_penalty": null,
96
- "finetuning_task": null,
97
- "forced_bos_token_id": null,
98
- "forced_eos_token_id": null,
99
- "hidden_act": "gelu",
100
- "hidden_dropout_prob": 0.1,
101
- "hidden_size": 768,
102
- "id2label": {
103
- "0": "LABEL_0",
104
- "1": "LABEL_1"
105
- },
106
- "initializer_range": 0.02,
107
- "intermediate_size": 3072,
108
- "is_decoder": false,
109
- "is_encoder_decoder": false,
110
- "label2id": {
111
- "LABEL_0": 0,
112
- "LABEL_1": 1
113
- },
114
- "layer_norm_eps": 1e-12,
115
- "length_penalty": 1.0,
116
  "max_len": 512,
117
- "max_length": 20,
118
- "max_position_embeddings": 512,
119
- "min_length": 0,
120
  "model_id": "bert-base-uncased",
121
- "model_type": "bert",
122
- "no_repeat_ngram_size": 0,
123
- "num_attention_heads": 12,
124
- "num_beam_groups": 1,
125
- "num_beams": 1,
126
- "num_hidden_layers": 12,
127
- "num_return_sequences": 1,
128
- "output_attentions": false,
129
- "output_hidden_states": false,
130
- "output_scores": false,
131
- "pad_token_id": 0,
132
- "position_embedding_type": "absolute",
133
- "prefix": null,
134
- "problem_type": null,
135
- "pruned_heads": {},
136
- "remove_invalid_values": false,
137
- "repetition_penalty": 1.0,
138
- "return_dict": true,
139
- "return_dict_in_generate": false,
140
- "sep_token_id": null,
141
- "suppress_tokens": null,
142
- "task_specific_params": null,
143
- "temperature": 1.0,
144
- "tf_legacy_loss": false,
145
- "tie_encoder_decoder": false,
146
- "tie_word_embeddings": true,
147
- "tokenizer_class": null,
148
- "top_k": 50,
149
- "top_p": 1.0,
150
  "topk": 768,
151
- "torch_dtype": null,
152
- "torchscript": false,
153
- "type": "vdr_cm_text",
154
- "type_vocab_size": 2,
155
- "typical_p": 1.0,
156
- "use_bfloat16": false,
157
- "use_cache": true,
158
- "vocab_size": 30522
159
  },
160
  "shared_encoder": false,
161
  "torch_dtype": "float32",
 
5
  ],
6
  "device": null,
7
  "encoder_p": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "heads": 12,
 
 
 
 
 
 
 
 
 
 
9
  "layers": 12,
 
 
 
 
 
 
 
 
 
 
 
 
10
  "patch_size": 32,
 
 
 
 
 
11
  "resolution": 224,
 
 
 
 
 
 
 
 
 
 
12
  "tokenizer_id": "bert-base-uncased",
 
 
13
  "topk": 768,
 
 
14
  "type": "vdr_cm_image",
 
 
15
  "width": 768
16
  },
17
  "encoder_q": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  "max_len": 512,
 
 
 
19
  "model_id": "bert-base-uncased",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
  "topk": 768,
21
+ "type": "vdr_cm_text"
 
 
 
 
 
 
 
22
  },
23
  "shared_encoder": false,
24
  "torch_dtype": "float32",
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1ae45c76c6ae4dacaeb411e300996b3106e46cbb5ef5c0bc19f42fad34dc966
3
- size 870366405
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff04580b55202e3fa292237f3375e1c16da4293be48504f8e805cacf437b8dcf
3
+ size 870371333