williamberman
commited on
Commit
•
9d5d357
1
Parent(s):
d1202bc
init
Browse files- text_encoder/config.json +25 -0
- text_encoder/merges.txt +0 -0
- text_encoder/pytorch_model.bin +3 -0
- text_encoder/special_tokens_map.json +24 -0
- text_encoder/tokenizer_config.json +35 -0
- text_encoder/vocab.json +0 -0
- transformer/config.json +34 -0
- transformer/pytorch_model.bin +3 -0
- vae/config.json +11 -0
- vae/pytorch_model.bin +3 -0
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openMUSE/CLIP-ViT-L-14-DataComp.XL-s13B-b90K-penultimate",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPTextModel"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"dropout": 0.0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "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": 11,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.26.1",
|
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 sha256:86e45abcf09c3a1eb2f9576010223cfaa9420a25d7a6de95f19187282718274c
|
3 |
+
size 463950241
|
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": "<|endoftext|>",
|
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 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"name_or_path": "openMUSE/CLIP-ViT-L-14-DataComp.XL-s13B-b90K-penultimate",
|
24 |
+
"pad_token": "<|endoftext|>",
|
25 |
+
"special_tokens_map_file": "/home/william_huggingface_co/.cache/huggingface/hub/models--openMUSE--CLIP-ViT-L-14-DataComp.XL-s13B-b90K-penultimate/snapshots/9623448d1c3d9ce39bd28d5393c29cc08f85ba97/special_tokens_map.json",
|
26 |
+
"tokenizer_class": "CLIPTokenizer",
|
27 |
+
"unk_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "<|endoftext|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
text_encoder/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
transformer/config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "MaskGiTUViT",
|
3 |
+
"_version": "0.0.1",
|
4 |
+
"add_cross_attention": true,
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"block_out_channels": [
|
7 |
+
512,
|
8 |
+
1024
|
9 |
+
],
|
10 |
+
"codebook_size": 8192,
|
11 |
+
"encoder_hidden_size": 768,
|
12 |
+
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"in_channels": 384,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 4096,
|
17 |
+
"layer_norm_eps": "1e-6",
|
18 |
+
"mask_token_id": 8255,
|
19 |
+
"max_position_embeddings": 256,
|
20 |
+
"norm_type": "rmsnorm",
|
21 |
+
"num_attention_heads": 16,
|
22 |
+
"num_classes": null,
|
23 |
+
"num_hidden_layers": 22,
|
24 |
+
"num_res_blocks": 3,
|
25 |
+
"num_vq_tokens": 1024,
|
26 |
+
"patch_size": 1,
|
27 |
+
"project_encoder_hidden_states": false,
|
28 |
+
"use_bias": false,
|
29 |
+
"use_codebook_size_for_output": true,
|
30 |
+
"use_encoder_layernorm": true,
|
31 |
+
"use_normformer": false,
|
32 |
+
"use_position_embeddings": false,
|
33 |
+
"vocab_size": 8256
|
34 |
+
}
|
transformer/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76e428a8cfe18ae9f1a94b59684134406fa61b5745a5a727e8604bd26b1bf2fe
|
3 |
+
size 2095759017
|
vae/config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "PaellaVQModel",
|
3 |
+
"_name_or_path": "openMUSE/paellavq-f8-8192-laion",
|
4 |
+
"_version": "0.0.1",
|
5 |
+
"bottleneck_blocks": 12,
|
6 |
+
"c_hidden": 512,
|
7 |
+
"c_latent": 4,
|
8 |
+
"codebook_size": 8192,
|
9 |
+
"levels": 3,
|
10 |
+
"scale_factor": 0.3764
|
11 |
+
}
|
vae/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:770c5640e1e70848e45f59dc0219ee01c562f864ad94bee15e4bf0aa25be7e78
|
3 |
+
size 135930429
|