pranavajay
commited on
Commit
•
d6c9722
1
Parent(s):
cf511ec
Upload config.json with huggingface_hub
Browse files- config.json +20 -68
config.json
CHANGED
@@ -1,72 +1,24 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
"act_fn": "silu",
|
5 |
-
"addition_embed_type": "text_time",
|
6 |
-
"addition_embed_type_num_heads": 64,
|
7 |
-
"addition_time_embed_dim": 256,
|
8 |
-
"attention_head_dim": [
|
9 |
-
5,
|
10 |
-
10,
|
11 |
-
20
|
12 |
],
|
13 |
-
"
|
14 |
-
"
|
15 |
-
320,
|
16 |
-
640,
|
17 |
-
1280
|
18 |
-
],
|
19 |
-
"center_input_sample": false,
|
20 |
-
"class_embed_type": null,
|
21 |
-
"class_embeddings_concat": false,
|
22 |
-
"conv_in_kernel": 3,
|
23 |
-
"conv_out_kernel": 3,
|
24 |
-
"cross_attention_dim": 2048,
|
25 |
-
"cross_attention_norm": null,
|
26 |
-
"down_block_types": [
|
27 |
-
"DownBlock2D",
|
28 |
-
"CrossAttnDownBlock2D",
|
29 |
-
"CrossAttnDownBlock2D"
|
30 |
-
],
|
31 |
-
"downsample_padding": 1,
|
32 |
"dropout": 0.0,
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"projection_class_embeddings_input_dim": 2816,
|
50 |
-
"resnet_out_scale_factor": 1.0,
|
51 |
-
"resnet_skip_time_act": false,
|
52 |
-
"resnet_time_scale_shift": "default",
|
53 |
-
"reverse_transformer_layers_per_block": null,
|
54 |
-
"sample_size": 128,
|
55 |
-
"time_cond_proj_dim": null,
|
56 |
-
"time_embedding_act_fn": null,
|
57 |
-
"time_embedding_dim": null,
|
58 |
-
"time_embedding_type": "positional",
|
59 |
-
"timestep_post_act": null,
|
60 |
-
"transformer_layers_per_block": [
|
61 |
-
1,
|
62 |
-
2,
|
63 |
-
10
|
64 |
-
],
|
65 |
-
"up_block_types": [
|
66 |
-
"CrossAttnUpBlock2D",
|
67 |
-
"CrossAttnUpBlock2D",
|
68 |
-
"UpBlock2D"
|
69 |
-
],
|
70 |
-
"upcast_attention": null,
|
71 |
-
"use_linear_projection": true
|
72 |
}
|
|
|
1 |
{
|
2 |
+
"architectures": [
|
3 |
+
"CLIPTextModelWithProjection"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
"dropout": 0.0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_size": 1280,
|
11 |
+
"initializer_factor": 1.0,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5120,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 77,
|
16 |
+
"model_type": "clip_text_model",
|
17 |
+
"num_attention_heads": 20,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"projection_dim": 1280,
|
21 |
+
"torch_dtype": "float16",
|
22 |
+
"transformers_version": "4.42.4",
|
23 |
+
"vocab_size": 49408
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
}
|