Hugging Face's logo

thuml
/
ivideogpt-oxe-256-act-free

Diffusers
Safetensors
world-model
open-x-embodiment
robotic-manipulation
video-generation
video-prediction
gpt
Model card Files Community
ivideogpt-oxe-256-act-free
File size: 936 Bytes 
9ea87ac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
 
{
  "_class_name": "CompressiveVQModel",
  "_diffusers_version": "0.27.0.dev0",
  "act_fn": "silu",
  "block_out_channels": [
    128,
    256,
    256,
    512,
    768
  ],
  "context_length": 2,
  "down_block_types": [
    "DownEncoderBlock2D",
    "DownEncoderBlock2D",
    "DownEncoderBlock2D",
    "DownEncoderBlock2D",
    "DownEncoderBlock2D"
  ],
  "force_upcast": true,
  "in_channels": 3,
  "latent_channels": 64,
  "layers_per_block": 2,
  "lookup_from_codebook": true,
  "max_att_resolution": 32,
  "mid_block_add_attention": false,
  "norm_num_groups": 32,
  "norm_type": "group",
  "num_dyn_embeddings": 8192,
  "num_vq_embeddings": 8192,
  "out_channels": 3,
  "patch_size": 4,
  "resolution": 256,
  "sample_size": 32,
  "scaling_factor": 0.18215,
  "up_block_types": [
    "UpDecoderBlock2D",
    "UpDecoderBlock2D",
    "UpDecoderBlock2D",
    "UpDecoderBlock2D",
    "UpDecoderBlock2D"
  ],
  "vq_embed_dim": null
}