Hugging Face's logo

williamberman
/
muse_research_run_benchmarking_512_output

Model card Files Community
william@huggingface.co commited on
Commit
fdd7649
•
1 Parent(s): 63d791d

init

Browse files
Files changed (10) hide show
  1. text_encoder/config.json +25 -0
  2. text_encoder/merges.txt +0 -0
  3. text_encoder/pytorch_model.bin +3 -0
  4. text_encoder/special_tokens_map.json +24 -0
  5. text_encoder/tokenizer_config.json +33 -0
  6. text_encoder/vocab.json +0 -0
  7. transformer/config.json +53 -0
  8. transformer/pytorch_model.bin +3 -0
  9. vae/config.json +24 -0
  10. vae/pytorch_model.bin +3 -0
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openMUSE/clip-vit-large-patch14-text-enc",
3
+ "architectures": [
4
+ "CLIPTextModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "quick_gelu",
11
+ "hidden_size": 768,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 768,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.30.1",
24
+ "vocab_size": 49408
25
+ }
text_encoder/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec40a3f65f96219cb30a80554a39fcb365146b6aa7d0cb9621e08b010ba672d
3
+ size 494666597
text_encoder/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "!",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
text_encoder/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "do_lower_case": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 77,
23
+ "pad_token": "<|endoftext|>",
24
+ "tokenizer_class": "CLIPTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
text_encoder/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
transformer/config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "MaskGiTUViT",
3
+ "_version": "0.0.1",
4
+ "add_cond_embeds": true,
5
+ "add_cross_attention": true,
6
+ "add_micro_cond_embeds": true,
7
+ "attention_dropout": 0.0,
8
+ "block_has_attention": [
9
+ true
10
+ ],
11
+ "block_num_heads": [
12
+ 12
13
+ ],
14
+ "block_out_channels": [
15
+ 768
16
+ ],
17
+ "codebook_size": 8192,
18
+ "cond_embed_dim": 768,
19
+ "encoder_hidden_size": 768,
20
+ "ffn_type": "glu",
21
+ "hidden_dropout": 0.0,
22
+ "hidden_size": 1024,
23
+ "in_channels": 768,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 2816,
26
+ "layer_norm_before_mlm": false,
27
+ "layer_norm_embedddings": false,
28
+ "layer_norm_eps": "1e-6",
29
+ "learn_uncond_embeds": false,
30
+ "ln_elementwise_affine": true,
31
+ "mask_token_id": 8255,
32
+ "max_position_embeddings": 256,
33
+ "micro_cond_embed_dim": 1280,
34
+ "micro_cond_encode_dim": 256,
35
+ "norm_type": "rmsnorm",
36
+ "num_attention_heads": 16,
37
+ "num_classes": null,
38
+ "num_hidden_layers": 22,
39
+ "num_res_blocks": 3,
40
+ "num_vq_tokens": 256,
41
+ "patch_size": 1,
42
+ "project_encoder_hidden_states": true,
43
+ "res_ffn_factor": 4,
44
+ "use_bias": false,
45
+ "use_codebook_size_for_output": true,
46
+ "use_empty_embeds_for_uncond": true,
47
+ "use_encoder_layernorm": false,
48
+ "use_normformer": false,
49
+ "use_position_embeddings": false,
50
+ "use_vannilla_resblock": false,
51
+ "vocab_size": 8256,
52
+ "xavier_init_embed": true
53
+ }
transformer/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd8ebe8a33791dd563e66c69fad41de7869bec4426d7049a4386faa06ed2ef29
3
+ size 2414365261
vae/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "VQGANModel",
3
+ "_name_or_path": "openMUSE/vqgan-f16-8192-laion",
4
+ "_version": "0.0.1",
5
+ "attn_resolutions": [],
6
+ "channel_mult": [
7
+ 1,
8
+ 2,
9
+ 2,
10
+ 4,
11
+ 6
12
+ ],
13
+ "commitment_cost": 0.25,
14
+ "dropout": 0.0,
15
+ "hidden_channels": 128,
16
+ "no_attn_mid_block": true,
17
+ "num_channels": 3,
18
+ "num_embeddings": 8192,
19
+ "num_res_blocks": 2,
20
+ "quantized_embed_dim": 64,
21
+ "resample_with_conv": true,
22
+ "resolution": 256,
23
+ "z_channels": 64
24
+ }
vae/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:270424768555a3a34d21b961168d8de81b3e17a60a3e048cdaf84611c856b541
3
+ size 585077729