File size: 2,806 Bytes
58872e7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
{
  "_class_name": "UNet2DConditionModel",
  "_commit_hash": null,
  "_diffusers_version": "0.23.0",
  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--ThinkDiffusion--ThinkDiffusionXL/snapshots/e31c4693b7f87128fee02fa6b16c4dc2ada13721/unet",
  "_use_default_values": [
    "reverse_transformer_layers_per_block"
  ],
  "act_fn": "silu",
  "addition_embed_type": "text_time",
  "addition_embed_type_num_heads": 64,
  "addition_time_embed_dim": 256,
  "attention_head_dim": [
    5,
    10,
    20
  ],
  "attention_type": "default",
  "block_out_channels": [
    320,
    640,
    1280
  ],
  "center_input_sample": false,
  "class_embed_type": null,
  "class_embeddings_concat": false,
  "conv_in_kernel": 3,
  "conv_out_kernel": 3,
  "cross_attention_dim": 2048,
  "cross_attention_norm": null,
  "down_block_types": [
    "DownBlock2D",
    "CrossAttnDownBlock2D",
    "CrossAttnDownBlock2D"
  ],
  "downsample_padding": 1,
  "dropout": 0.0,
  "dual_cross_attention": false,
  "encoder_hid_dim": null,
  "encoder_hid_dim_type": null,
  "flip_sin_to_cos": true,
  "freq_shift": 0,
  "in_channels": 4,
  "layers_per_block": 2,
  "mid_block_only_cross_attention": null,
  "mid_block_scale_factor": 1,
  "mid_block_type": "UNetMidBlock2DCrossAttn",
  "neuron": {
    "auto_cast": "all",
    "auto_cast_type": "bf16",
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.12.54.0+f631c2365",
    "disable_fallback": false,
    "disable_fast_relayout": false,
    "dynamic_batch_size": false,
    "input_names": [
      "sample",
      "timestep",
      "encoder_hidden_states",
      "text_embeds",
      "time_ids"
    ],
    "model_type": "unet",
    "optlevel": "2",
    "output_attentions": false,
    "output_hidden_states": false,
    "output_names": [
      "sample"
    ],
    "static_batch_size": 1,
    "static_height": 128,
    "static_num_beams": 1,
    "static_num_channels": 4,
    "static_sequence_length": 77,
    "static_width": 128
  },
  "norm_eps": 1e-05,
  "norm_num_groups": 32,
  "num_attention_heads": null,
  "num_class_embeds": null,
  "only_cross_attention": false,
  "out_channels": 4,
  "projection_class_embeddings_input_dim": 2816,
  "resnet_out_scale_factor": 1.0,
  "resnet_skip_time_act": false,
  "resnet_time_scale_shift": "default",
  "reverse_transformer_layers_per_block": null,
  "sample_size": 128,
  "task": "semantic-segmentation",
  "time_cond_proj_dim": null,
  "time_embedding_act_fn": null,
  "time_embedding_dim": null,
  "time_embedding_type": "positional",
  "timestep_post_act": null,
  "transformer_layers_per_block": [
    1,
    2,
    10
  ],
  "transformers_version": null,
  "up_block_types": [
    "CrossAttnUpBlock2D",
    "CrossAttnUpBlock2D",
    "UpBlock2D"
  ],
  "upcast_attention": null,
  "use_linear_projection": true
}