Upload folder using huggingface_hub
Browse files- text_encoder/.ipynb_checkpoints/config-checkpoint.json +25 -0
- 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.json +0 -0
- text_encoder/tokenizer_config.json +33 -0
- text_encoder/vocab.json +0 -0
- transformer/config.json +33 -0
- transformer/pytorch_model.bin +3 -0
- vae/config.json +24 -0
- vae/pytorch_model.bin +3 -0
text_encoder/.ipynb_checkpoints/config-checkpoint.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": "float16",
|
23 |
+
"transformers_version": "4.33.0",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
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": "float16",
|
23 |
+
"transformers_version": "4.33.0",
|
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 sha256:309668b5c2804fb35dfde7d1d4eb00aedb4ba723db1c4fe2db4bf24dad824adf
|
3 |
+
size 247367841
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "MaskGiTUViT_v2",
|
3 |
+
"_name_or_path": "valhalla/research-run-finetuned-journeydb",
|
4 |
+
"_version": "0.0.1",
|
5 |
+
"add_cond_embeds": true,
|
6 |
+
"add_micro_cond_embeds": true,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"block_num_heads": 12,
|
9 |
+
"block_out_channels": [
|
10 |
+
768
|
11 |
+
],
|
12 |
+
"codebook_size": 8192,
|
13 |
+
"cond_embed_dim": 768,
|
14 |
+
"encoder_hidden_size": 768,
|
15 |
+
"force_down_up_sample": true,
|
16 |
+
"hidden_dropout": 0.0,
|
17 |
+
"hidden_size": 1024,
|
18 |
+
"in_channels": 768,
|
19 |
+
"intermediate_size": 2816,
|
20 |
+
"layer_norm_eps": 1e-06,
|
21 |
+
"ln_elementwise_affine": true,
|
22 |
+
"mask_token_id": 8255,
|
23 |
+
"micro_cond_embed_dim": 1280,
|
24 |
+
"micro_cond_encode_dim": 256,
|
25 |
+
"norm_type": "rmsnorm",
|
26 |
+
"num_attention_heads": 16,
|
27 |
+
"num_hidden_layers": 22,
|
28 |
+
"num_res_blocks": 3,
|
29 |
+
"use_bias": false,
|
30 |
+
"use_fused_mlp": false,
|
31 |
+
"use_fused_residual_norm": false,
|
32 |
+
"vocab_size": 8256
|
33 |
+
}
|
transformer/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:216e82c7f125229777f49368f64ed46eae48693f54dee8ddebcf465875fa1375
|
3 |
+
size 1216738845
|
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 sha256:66cec148c289cbf55e39e490bed921ec746d7442357dd00a2edce039ed2c3379
|
3 |
+
size 585081633
|