Hugging Face's logo

jburtoft
/
TDXL

Model card Files Community
2
jburtoft commited on
Commit
77b4a20
•
1 Parent(s): b98989b

799c1441f85edf37c5ba89faa5c4b7d35ccb03c56c0f69e2daad7747f159be38

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. text_encoder_2/model.neuron +3 -0
  3. tokenizer/merges.txt +0 -0
  4. tokenizer/special_tokens_map.json +30 -0
  5. tokenizer/tokenizer_config.json +31 -0
  6. tokenizer/vocab.json +0 -0
  7. tokenizer_2/merges.txt +0 -0
  8. tokenizer_2/special_tokens_map.json +30 -0
  9. tokenizer_2/tokenizer_config.json +39 -0
  10. tokenizer_2/vocab.json +0 -0
  11. unet/config.json +108 -0
  12. vae_decoder/config.json +59 -0
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
37
  unet/model.neuron filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
37
  unet/model.neuron filter=lfs diff=lfs merge=lfs -text
38
+ text_encoder_2/model.neuron filter=lfs diff=lfs merge=lfs -text
text_encoder_2/model.neuron ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6b763f3c12472a8e42d1c84b75826c8cea51d69e785ea4710e490f86c42d100
3
+ size 1788954872
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "additional_special_tokens": [],
22
+ "bos_token": "<|startoftext|>",
23
+ "clean_up_tokenization_spaces": true,
24
+ "do_lower_case": true,
25
+ "eos_token": "<|endoftext|>",
26
+ "errors": "replace",
27
+ "model_max_length": 77,
28
+ "pad_token": "<|endoftext|>",
29
+ "tokenizer_class": "CLIPTokenizer",
30
+ "unk_token": "<|endoftext|>"
31
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_2/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_2/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "!",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_2/tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "!",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49406": {
13
+ "content": "<|startoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "49407": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [],
30
+ "bos_token": "<|startoftext|>",
31
+ "clean_up_tokenization_spaces": true,
32
+ "do_lower_case": true,
33
+ "eos_token": "<|endoftext|>",
34
+ "errors": "replace",
35
+ "model_max_length": 77,
36
+ "pad_token": "!",
37
+ "tokenizer_class": "CLIPTokenizer",
38
+ "unk_token": "<|endoftext|>"
39
+ }
tokenizer_2/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_commit_hash": null,
4
+ "_diffusers_version": "0.23.0",
5
+ "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--ThinkDiffusion--ThinkDiffusionXL/snapshots/e31c4693b7f87128fee02fa6b16c4dc2ada13721/unet",
6
+ "_use_default_values": [
7
+ "reverse_transformer_layers_per_block"
8
+ ],
9
+ "act_fn": "silu",
10
+ "addition_embed_type": "text_time",
11
+ "addition_embed_type_num_heads": 64,
12
+ "addition_time_embed_dim": 256,
13
+ "attention_head_dim": [
14
+ 5,
15
+ 10,
16
+ 20
17
+ ],
18
+ "attention_type": "default",
19
+ "block_out_channels": [
20
+ 320,
21
+ 640,
22
+ 1280
23
+ ],
24
+ "center_input_sample": false,
25
+ "class_embed_type": null,
26
+ "class_embeddings_concat": false,
27
+ "conv_in_kernel": 3,
28
+ "conv_out_kernel": 3,
29
+ "cross_attention_dim": 2048,
30
+ "cross_attention_norm": null,
31
+ "down_block_types": [
32
+ "DownBlock2D",
33
+ "CrossAttnDownBlock2D",
34
+ "CrossAttnDownBlock2D"
35
+ ],
36
+ "downsample_padding": 1,
37
+ "dropout": 0.0,
38
+ "dual_cross_attention": false,
39
+ "encoder_hid_dim": null,
40
+ "encoder_hid_dim_type": null,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "in_channels": 4,
44
+ "layers_per_block": 2,
45
+ "mid_block_only_cross_attention": null,
46
+ "mid_block_scale_factor": 1,
47
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
48
+ "neuron": {
49
+ "auto_cast": "all",
50
+ "auto_cast_type": "bf16",
51
+ "compiler_type": "neuronx-cc",
52
+ "compiler_version": "2.12.54.0+f631c2365",
53
+ "disable_fallback": false,
54
+ "disable_fast_relayout": false,
55
+ "dynamic_batch_size": false,
56
+ "input_names": [
57
+ "sample",
58
+ "timestep",
59
+ "encoder_hidden_states",
60
+ "text_embeds",
61
+ "time_ids"
62
+ ],
63
+ "model_type": "unet",
64
+ "optlevel": "2",
65
+ "output_attentions": false,
66
+ "output_hidden_states": false,
67
+ "output_names": [
68
+ "sample"
69
+ ],
70
+ "static_batch_size": 1,
71
+ "static_height": 128,
72
+ "static_num_beams": 1,
73
+ "static_num_channels": 4,
74
+ "static_sequence_length": 77,
75
+ "static_width": 128
76
+ },
77
+ "norm_eps": 1e-05,
78
+ "norm_num_groups": 32,
79
+ "num_attention_heads": null,
80
+ "num_class_embeds": null,
81
+ "only_cross_attention": false,
82
+ "out_channels": 4,
83
+ "projection_class_embeddings_input_dim": 2816,
84
+ "resnet_out_scale_factor": 1.0,
85
+ "resnet_skip_time_act": false,
86
+ "resnet_time_scale_shift": "default",
87
+ "reverse_transformer_layers_per_block": null,
88
+ "sample_size": 128,
89
+ "task": "semantic-segmentation",
90
+ "time_cond_proj_dim": null,
91
+ "time_embedding_act_fn": null,
92
+ "time_embedding_dim": null,
93
+ "time_embedding_type": "positional",
94
+ "timestep_post_act": null,
95
+ "transformer_layers_per_block": [
96
+ 1,
97
+ 2,
98
+ 10
99
+ ],
100
+ "transformers_version": null,
101
+ "up_block_types": [
102
+ "CrossAttnUpBlock2D",
103
+ "CrossAttnUpBlock2D",
104
+ "UpBlock2D"
105
+ ],
106
+ "upcast_attention": null,
107
+ "use_linear_projection": true
108
+ }
vae_decoder/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_commit_hash": null,
4
+ "_diffusers_version": "0.23.0",
5
+ "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--ThinkDiffusion--ThinkDiffusionXL/snapshots/e31c4693b7f87128fee02fa6b16c4dc2ada13721/vae",
6
+ "act_fn": "silu",
7
+ "block_out_channels": [
8
+ 128,
9
+ 256,
10
+ 512,
11
+ 512
12
+ ],
13
+ "down_block_types": [
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D",
17
+ "DownEncoderBlock2D"
18
+ ],
19
+ "force_upcast": true,
20
+ "in_channels": 3,
21
+ "latent_channels": 4,
22
+ "layers_per_block": 2,
23
+ "neuron": {
24
+ "auto_cast": "all",
25
+ "auto_cast_type": "bf16",
26
+ "compiler_type": "neuronx-cc",
27
+ "compiler_version": "2.12.54.0+f631c2365",
28
+ "disable_fallback": false,
29
+ "disable_fast_relayout": false,
30
+ "dynamic_batch_size": false,
31
+ "input_names": [
32
+ "latent_sample"
33
+ ],
34
+ "model_type": "vae-decoder",
35
+ "optlevel": "2",
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "output_names": [
39
+ "sample"
40
+ ],
41
+ "static_batch_size": 1,
42
+ "static_height": 128,
43
+ "static_num_beams": 1,
44
+ "static_num_channels": 4,
45
+ "static_width": 128
46
+ },
47
+ "norm_num_groups": 32,
48
+ "out_channels": 3,
49
+ "sample_size": 1024,
50
+ "scaling_factor": 0.13025,
51
+ "task": "semantic-segmentation",
52
+ "transformers_version": null,
53
+ "up_block_types": [
54
+ "UpDecoderBlock2D",
55
+ "UpDecoderBlock2D",
56
+ "UpDecoderBlock2D",
57
+ "UpDecoderBlock2D"
58
+ ]
59
+ }