jianzongwu commited on
Commit
604857e
·
verified ·
1 Parent(s): 4271c2c

Update image_generator/magi_image_encoder/config.json

Browse files
image_generator/magi_image_encoder/config.json CHANGED
@@ -1,84 +1,28 @@
1
  {
2
- "_name_or_path": "checkpoints/vit-mae-base",
3
- "add_cross_attention": false,
4
  "architectures": [
5
- "ViTMAEForPreTraining"
6
  ],
7
  "attention_probs_dropout_prob": 0.0,
8
- "bad_words_ids": null,
9
- "begin_suppress_tokens": null,
10
- "bos_token_id": null,
11
- "chunk_size_feed_forward": 0,
12
- "cross_attention_hidden_size": null,
13
  "decoder_hidden_size": 512,
14
  "decoder_intermediate_size": 2048,
15
  "decoder_num_attention_heads": 16,
16
  "decoder_num_hidden_layers": 8,
17
- "decoder_start_token_id": null,
18
- "diversity_penalty": 0.0,
19
- "do_sample": false,
20
- "early_stopping": false,
21
- "encoder_no_repeat_ngram_size": 0,
22
- "eos_token_id": null,
23
- "exponential_decay_length_penalty": null,
24
- "finetuning_task": null,
25
- "forced_bos_token_id": null,
26
- "forced_eos_token_id": null,
27
  "hidden_act": "gelu",
28
  "hidden_dropout_prob": 0.0,
29
  "hidden_size": 768,
30
- "id2label": {
31
- "0": "LABEL_0",
32
- "1": "LABEL_1"
33
- },
34
  "image_size": 224,
35
  "initializer_range": 0.02,
36
  "intermediate_size": 3072,
37
- "is_decoder": false,
38
- "is_encoder_decoder": false,
39
- "label2id": {
40
- "LABEL_0": 0,
41
- "LABEL_1": 1
42
- },
43
  "layer_norm_eps": 1e-12,
44
- "length_penalty": 1.0,
45
  "mask_ratio": 0.75,
46
- "max_length": 20,
47
- "min_length": 0,
48
- "model_type": "",
49
- "no_repeat_ngram_size": 0,
50
  "norm_pix_loss": false,
51
  "num_attention_heads": 12,
52
- "num_beam_groups": 1,
53
- "num_beams": 1,
54
  "num_channels": 3,
55
  "num_hidden_layers": 12,
56
- "num_return_sequences": 1,
57
- "output_attentions": false,
58
- "output_hidden_states": false,
59
- "output_scores": false,
60
- "pad_token_id": null,
61
  "patch_size": 16,
62
- "prefix": null,
63
- "problem_type": null,
64
- "pruned_heads": {},
65
  "qkv_bias": true,
66
- "remove_invalid_values": false,
67
- "repetition_penalty": 1.0,
68
- "return_dict": true,
69
- "return_dict_in_generate": false,
70
- "sep_token_id": null,
71
- "suppress_tokens": null,
72
- "task_specific_params": null,
73
- "temperature": 1.0,
74
- "tf_legacy_loss": false,
75
- "tie_encoder_decoder": false,
76
- "tie_word_embeddings": true,
77
- "tokenizer_class": null,
78
- "top_k": 50,
79
- "top_p": 1.0,
80
  "torch_dtype": "float32",
81
- "torchscript": false,
82
- "typical_p": 1.0,
83
- "use_bfloat16": false
84
- }
 
1
  {
 
 
2
  "architectures": [
3
+ "ViTMAEForPreTraining"
4
  ],
5
  "attention_probs_dropout_prob": 0.0,
 
 
 
 
 
6
  "decoder_hidden_size": 512,
7
  "decoder_intermediate_size": 2048,
8
  "decoder_num_attention_heads": 16,
9
  "decoder_num_hidden_layers": 8,
 
 
 
 
 
 
 
 
 
 
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.0,
12
  "hidden_size": 768,
 
 
 
 
13
  "image_size": 224,
14
  "initializer_range": 0.02,
15
  "intermediate_size": 3072,
 
 
 
 
 
 
16
  "layer_norm_eps": 1e-12,
 
17
  "mask_ratio": 0.75,
18
+ "model_type": "vit_mae",
 
 
 
19
  "norm_pix_loss": false,
20
  "num_attention_heads": 12,
 
 
21
  "num_channels": 3,
22
  "num_hidden_layers": 12,
 
 
 
 
 
23
  "patch_size": 16,
 
 
 
24
  "qkv_bias": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  "torch_dtype": "float32",
26
+ "transformers_version": "4.16.0.dev0"
27
+ }
28
+