Hugging Face's logo

SimpleTuner
/
cosmos3-component-generation-layers-bf16-super

Diffusers
Safetensors
Model card Files
xet
 Community
bghira commited on
Commit
4ac8699
·
verified ·
1 Parent(s): 2c453e2

Use diffusers transformer shard names

Browse files
Files changed (35) hide show
  1. model-00001-of-00033.safetensors → diffusion_pytorch_model-00001-of-00033.safetensors +0 -0
  2. model-00002-of-00033.safetensors → diffusion_pytorch_model-00002-of-00033.safetensors +0 -0
  3. model-00003-of-00033.safetensors → diffusion_pytorch_model-00003-of-00033.safetensors +0 -0
  4. model-00004-of-00033.safetensors → diffusion_pytorch_model-00004-of-00033.safetensors +0 -0
  5. model-00005-of-00033.safetensors → diffusion_pytorch_model-00005-of-00033.safetensors +0 -0
  6. model-00006-of-00033.safetensors → diffusion_pytorch_model-00006-of-00033.safetensors +0 -0
  7. model-00007-of-00033.safetensors → diffusion_pytorch_model-00007-of-00033.safetensors +0 -0
  8. model-00008-of-00033.safetensors → diffusion_pytorch_model-00008-of-00033.safetensors +0 -0
  9. model-00009-of-00033.safetensors → diffusion_pytorch_model-00009-of-00033.safetensors +0 -0
  10. model-00010-of-00033.safetensors → diffusion_pytorch_model-00010-of-00033.safetensors +0 -0
  11. model-00011-of-00033.safetensors → diffusion_pytorch_model-00011-of-00033.safetensors +0 -0
  12. model-00012-of-00033.safetensors → diffusion_pytorch_model-00012-of-00033.safetensors +0 -0
  13. model-00013-of-00033.safetensors → diffusion_pytorch_model-00013-of-00033.safetensors +0 -0
  14. model-00014-of-00033.safetensors → diffusion_pytorch_model-00014-of-00033.safetensors +0 -0
  15. model-00015-of-00033.safetensors → diffusion_pytorch_model-00015-of-00033.safetensors +0 -0
  16. model-00016-of-00033.safetensors → diffusion_pytorch_model-00016-of-00033.safetensors +0 -0
  17. model-00017-of-00033.safetensors → diffusion_pytorch_model-00017-of-00033.safetensors +0 -0
  18. model-00018-of-00033.safetensors → diffusion_pytorch_model-00018-of-00033.safetensors +0 -0
  19. model-00019-of-00033.safetensors → diffusion_pytorch_model-00019-of-00033.safetensors +0 -0
  20. model-00020-of-00033.safetensors → diffusion_pytorch_model-00020-of-00033.safetensors +0 -0
  21. model-00021-of-00033.safetensors → diffusion_pytorch_model-00021-of-00033.safetensors +0 -0
  22. model-00022-of-00033.safetensors → diffusion_pytorch_model-00022-of-00033.safetensors +0 -0
  23. model-00023-of-00033.safetensors → diffusion_pytorch_model-00023-of-00033.safetensors +0 -0
  24. model-00024-of-00033.safetensors → diffusion_pytorch_model-00024-of-00033.safetensors +0 -0
  25. model-00025-of-00033.safetensors → diffusion_pytorch_model-00025-of-00033.safetensors +0 -0
  26. model-00026-of-00033.safetensors → diffusion_pytorch_model-00026-of-00033.safetensors +0 -0
  27. model-00027-of-00033.safetensors → diffusion_pytorch_model-00027-of-00033.safetensors +0 -0
  28. model-00028-of-00033.safetensors → diffusion_pytorch_model-00028-of-00033.safetensors +0 -0
  29. model-00029-of-00033.safetensors → diffusion_pytorch_model-00029-of-00033.safetensors +0 -0
  30. model-00030-of-00033.safetensors → diffusion_pytorch_model-00030-of-00033.safetensors +0 -0
  31. model-00031-of-00033.safetensors → diffusion_pytorch_model-00031-of-00033.safetensors +0 -0
  32. model-00032-of-00033.safetensors → diffusion_pytorch_model-00032-of-00033.safetensors +0 -0
  33. model-00033-of-00033.safetensors → diffusion_pytorch_model-00033-of-00033.safetensors +0 -0
  34. diffusion_pytorch_model.safetensors.index.json +730 -0
  35. model.safetensors.index.json +0 -730
model-00001-of-00033.safetensors → diffusion_pytorch_model-00001-of-00033.safetensors RENAMED
File without changes
model-00002-of-00033.safetensors → diffusion_pytorch_model-00002-of-00033.safetensors RENAMED
File without changes
model-00003-of-00033.safetensors → diffusion_pytorch_model-00003-of-00033.safetensors RENAMED
File without changes
model-00004-of-00033.safetensors → diffusion_pytorch_model-00004-of-00033.safetensors RENAMED
File without changes
model-00005-of-00033.safetensors → diffusion_pytorch_model-00005-of-00033.safetensors RENAMED
File without changes
model-00006-of-00033.safetensors → diffusion_pytorch_model-00006-of-00033.safetensors RENAMED
File without changes
model-00007-of-00033.safetensors → diffusion_pytorch_model-00007-of-00033.safetensors RENAMED
File without changes
model-00008-of-00033.safetensors → diffusion_pytorch_model-00008-of-00033.safetensors RENAMED
File without changes
model-00009-of-00033.safetensors → diffusion_pytorch_model-00009-of-00033.safetensors RENAMED
File without changes
model-00010-of-00033.safetensors → diffusion_pytorch_model-00010-of-00033.safetensors RENAMED
File without changes
model-00011-of-00033.safetensors → diffusion_pytorch_model-00011-of-00033.safetensors RENAMED
File without changes
model-00012-of-00033.safetensors → diffusion_pytorch_model-00012-of-00033.safetensors RENAMED
File without changes
model-00013-of-00033.safetensors → diffusion_pytorch_model-00013-of-00033.safetensors RENAMED
File without changes
model-00014-of-00033.safetensors → diffusion_pytorch_model-00014-of-00033.safetensors RENAMED
File without changes
model-00015-of-00033.safetensors → diffusion_pytorch_model-00015-of-00033.safetensors RENAMED
File without changes
model-00016-of-00033.safetensors → diffusion_pytorch_model-00016-of-00033.safetensors RENAMED
File without changes
model-00017-of-00033.safetensors → diffusion_pytorch_model-00017-of-00033.safetensors RENAMED
File without changes
model-00018-of-00033.safetensors → diffusion_pytorch_model-00018-of-00033.safetensors RENAMED
File without changes
model-00019-of-00033.safetensors → diffusion_pytorch_model-00019-of-00033.safetensors RENAMED
File without changes
model-00020-of-00033.safetensors → diffusion_pytorch_model-00020-of-00033.safetensors RENAMED
File without changes
model-00021-of-00033.safetensors → diffusion_pytorch_model-00021-of-00033.safetensors RENAMED
File without changes
model-00022-of-00033.safetensors → diffusion_pytorch_model-00022-of-00033.safetensors RENAMED
File without changes
model-00023-of-00033.safetensors → diffusion_pytorch_model-00023-of-00033.safetensors RENAMED
File without changes
model-00024-of-00033.safetensors → diffusion_pytorch_model-00024-of-00033.safetensors RENAMED
File without changes
model-00025-of-00033.safetensors → diffusion_pytorch_model-00025-of-00033.safetensors RENAMED
File without changes
model-00026-of-00033.safetensors → diffusion_pytorch_model-00026-of-00033.safetensors RENAMED
File without changes
model-00027-of-00033.safetensors → diffusion_pytorch_model-00027-of-00033.safetensors RENAMED
File without changes
model-00028-of-00033.safetensors → diffusion_pytorch_model-00028-of-00033.safetensors RENAMED
File without changes
model-00029-of-00033.safetensors → diffusion_pytorch_model-00029-of-00033.safetensors RENAMED
File without changes
model-00030-of-00033.safetensors → diffusion_pytorch_model-00030-of-00033.safetensors RENAMED
File without changes
model-00031-of-00033.safetensors → diffusion_pytorch_model-00031-of-00033.safetensors RENAMED
File without changes
model-00032-of-00033.safetensors → diffusion_pytorch_model-00032-of-00033.safetensors RENAMED
File without changes
model-00033-of-00033.safetensors → diffusion_pytorch_model-00033-of-00033.safetensors RENAMED
File without changes
diffusion_pytorch_model.safetensors.index.json ADDED
@@ -0,0 +1,730 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 62515227136
4
+ },
5
+ "weight_map": {
6
+ "action_modality_embed": "diffusion_pytorch_model-00001-of-00033.safetensors",
7
+ "action_proj_in.bias.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
8
+ "action_proj_in.fc.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
9
+ "action_proj_out.bias.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
10
+ "action_proj_out.fc.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
11
+ "audio_modality_embed": "diffusion_pytorch_model-00001-of-00033.safetensors",
12
+ "audio_proj_in.bias": "diffusion_pytorch_model-00001-of-00033.safetensors",
13
+ "audio_proj_in.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
14
+ "audio_proj_out.bias": "diffusion_pytorch_model-00001-of-00033.safetensors",
15
+ "audio_proj_out.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
16
+ "layers.0.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
17
+ "layers.0.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
18
+ "layers.0.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
19
+ "layers.0.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
20
+ "layers.0.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
21
+ "layers.0.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
22
+ "layers.0.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
23
+ "layers.0.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
24
+ "layers.0.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
25
+ "layers.0.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
26
+ "layers.0.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
27
+ "layers.1.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
28
+ "layers.1.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
29
+ "layers.1.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
30
+ "layers.1.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
31
+ "layers.1.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
32
+ "layers.1.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
33
+ "layers.1.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
34
+ "layers.1.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
35
+ "layers.1.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
36
+ "layers.1.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
37
+ "layers.1.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
38
+ "layers.10.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
39
+ "layers.10.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
40
+ "layers.10.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
41
+ "layers.10.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
42
+ "layers.10.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
43
+ "layers.10.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
44
+ "layers.10.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
45
+ "layers.10.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
46
+ "layers.10.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
47
+ "layers.10.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
48
+ "layers.10.self_attn.to_add_out.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
49
+ "layers.11.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00004-of-00033.safetensors",
50
+ "layers.11.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00004-of-00033.safetensors",
51
+ "layers.11.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
52
+ "layers.11.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00004-of-00033.safetensors",
53
+ "layers.11.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00004-of-00033.safetensors",
54
+ "layers.11.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
55
+ "layers.11.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
56
+ "layers.11.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
57
+ "layers.11.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
58
+ "layers.11.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
59
+ "layers.11.self_attn.to_add_out.weight": "diffusion_pytorch_model-00004-of-00033.safetensors",
60
+ "layers.12.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00004-of-00033.safetensors",
61
+ "layers.12.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00004-of-00033.safetensors",
62
+ "layers.12.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00004-of-00033.safetensors",
63
+ "layers.12.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
64
+ "layers.12.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
65
+ "layers.12.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
66
+ "layers.12.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
67
+ "layers.12.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
68
+ "layers.12.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
69
+ "layers.12.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
70
+ "layers.12.self_attn.to_add_out.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
71
+ "layers.13.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
72
+ "layers.13.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
73
+ "layers.13.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
74
+ "layers.13.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
75
+ "layers.13.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
76
+ "layers.13.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
77
+ "layers.13.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
78
+ "layers.13.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
79
+ "layers.13.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
80
+ "layers.13.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
81
+ "layers.13.self_attn.to_add_out.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
82
+ "layers.14.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
83
+ "layers.14.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
84
+ "layers.14.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
85
+ "layers.14.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
86
+ "layers.14.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
87
+ "layers.14.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
88
+ "layers.14.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
89
+ "layers.14.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
90
+ "layers.14.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
91
+ "layers.14.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
92
+ "layers.14.self_attn.to_add_out.weight": "diffusion_pytorch_model-00005-of-00033.safetensors",
93
+ "layers.15.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
94
+ "layers.15.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
95
+ "layers.15.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
96
+ "layers.15.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
97
+ "layers.15.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
98
+ "layers.15.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
99
+ "layers.15.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
100
+ "layers.15.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
101
+ "layers.15.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
102
+ "layers.15.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
103
+ "layers.15.self_attn.to_add_out.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
104
+ "layers.16.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
105
+ "layers.16.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
106
+ "layers.16.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
107
+ "layers.16.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
108
+ "layers.16.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
109
+ "layers.16.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
110
+ "layers.16.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
111
+ "layers.16.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
112
+ "layers.16.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
113
+ "layers.16.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
114
+ "layers.16.self_attn.to_add_out.weight": "diffusion_pytorch_model-00006-of-00033.safetensors",
115
+ "layers.17.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
116
+ "layers.17.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
117
+ "layers.17.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
118
+ "layers.17.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
119
+ "layers.17.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
120
+ "layers.17.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
121
+ "layers.17.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
122
+ "layers.17.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
123
+ "layers.17.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
124
+ "layers.17.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
125
+ "layers.17.self_attn.to_add_out.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
126
+ "layers.18.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
127
+ "layers.18.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00007-of-00033.safetensors",
128
+ "layers.18.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
129
+ "layers.18.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
130
+ "layers.18.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
131
+ "layers.18.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
132
+ "layers.18.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
133
+ "layers.18.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
134
+ "layers.18.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
135
+ "layers.18.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
136
+ "layers.18.self_attn.to_add_out.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
137
+ "layers.19.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
138
+ "layers.19.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
139
+ "layers.19.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
140
+ "layers.19.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
141
+ "layers.19.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
142
+ "layers.19.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
143
+ "layers.19.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
144
+ "layers.19.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
145
+ "layers.19.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
146
+ "layers.19.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
147
+ "layers.19.self_attn.to_add_out.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
148
+ "layers.2.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
149
+ "layers.2.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
150
+ "layers.2.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
151
+ "layers.2.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
152
+ "layers.2.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
153
+ "layers.2.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
154
+ "layers.2.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
155
+ "layers.2.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
156
+ "layers.2.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
157
+ "layers.2.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
158
+ "layers.2.self_attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
159
+ "layers.20.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
160
+ "layers.20.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00008-of-00033.safetensors",
161
+ "layers.20.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
162
+ "layers.20.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
163
+ "layers.20.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
164
+ "layers.20.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
165
+ "layers.20.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
166
+ "layers.20.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
167
+ "layers.20.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
168
+ "layers.20.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
169
+ "layers.20.self_attn.to_add_out.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
170
+ "layers.21.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
171
+ "layers.21.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
172
+ "layers.21.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
173
+ "layers.21.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
174
+ "layers.21.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
175
+ "layers.21.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
176
+ "layers.21.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
177
+ "layers.21.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
178
+ "layers.21.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
179
+ "layers.21.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
180
+ "layers.21.self_attn.to_add_out.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
181
+ "layers.22.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
182
+ "layers.22.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00009-of-00033.safetensors",
183
+ "layers.22.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
184
+ "layers.22.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
185
+ "layers.22.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
186
+ "layers.22.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
187
+ "layers.22.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
188
+ "layers.22.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
189
+ "layers.22.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
190
+ "layers.22.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
191
+ "layers.22.self_attn.to_add_out.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
192
+ "layers.23.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
193
+ "layers.23.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
194
+ "layers.23.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
195
+ "layers.23.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
196
+ "layers.23.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
197
+ "layers.23.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
198
+ "layers.23.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
199
+ "layers.23.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
200
+ "layers.23.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
201
+ "layers.23.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
202
+ "layers.23.self_attn.to_add_out.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
203
+ "layers.24.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
204
+ "layers.24.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
205
+ "layers.24.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
206
+ "layers.24.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
207
+ "layers.24.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
208
+ "layers.24.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
209
+ "layers.24.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
210
+ "layers.24.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
211
+ "layers.24.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
212
+ "layers.24.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
213
+ "layers.24.self_attn.to_add_out.weight": "diffusion_pytorch_model-00010-of-00033.safetensors",
214
+ "layers.25.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
215
+ "layers.25.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
216
+ "layers.25.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
217
+ "layers.25.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
218
+ "layers.25.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
219
+ "layers.25.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
220
+ "layers.25.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
221
+ "layers.25.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
222
+ "layers.25.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
223
+ "layers.25.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
224
+ "layers.25.self_attn.to_add_out.weight": "diffusion_pytorch_model-00011-of-00033.safetensors",
225
+ "layers.26.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
226
+ "layers.26.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
227
+ "layers.26.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
228
+ "layers.26.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
229
+ "layers.26.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
230
+ "layers.26.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
231
+ "layers.26.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
232
+ "layers.26.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
233
+ "layers.26.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
234
+ "layers.26.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
235
+ "layers.26.self_attn.to_add_out.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
236
+ "layers.27.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
237
+ "layers.27.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
238
+ "layers.27.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
239
+ "layers.27.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
240
+ "layers.27.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
241
+ "layers.27.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
242
+ "layers.27.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
243
+ "layers.27.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
244
+ "layers.27.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
245
+ "layers.27.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
246
+ "layers.27.self_attn.to_add_out.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
247
+ "layers.28.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00012-of-00033.safetensors",
248
+ "layers.28.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
249
+ "layers.28.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
250
+ "layers.28.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
251
+ "layers.28.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
252
+ "layers.28.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
253
+ "layers.28.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
254
+ "layers.28.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
255
+ "layers.28.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
256
+ "layers.28.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
257
+ "layers.28.self_attn.to_add_out.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
258
+ "layers.29.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
259
+ "layers.29.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
260
+ "layers.29.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
261
+ "layers.29.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
262
+ "layers.29.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
263
+ "layers.29.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
264
+ "layers.29.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
265
+ "layers.29.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
266
+ "layers.29.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
267
+ "layers.29.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
268
+ "layers.29.self_attn.to_add_out.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
269
+ "layers.3.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
270
+ "layers.3.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
271
+ "layers.3.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00002-of-00033.safetensors",
272
+ "layers.3.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
273
+ "layers.3.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
274
+ "layers.3.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
275
+ "layers.3.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
276
+ "layers.3.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
277
+ "layers.3.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
278
+ "layers.3.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
279
+ "layers.3.self_attn.to_add_out.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
280
+ "layers.30.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00013-of-00033.safetensors",
281
+ "layers.30.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
282
+ "layers.30.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
283
+ "layers.30.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
284
+ "layers.30.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
285
+ "layers.30.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
286
+ "layers.30.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
287
+ "layers.30.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
288
+ "layers.30.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
289
+ "layers.30.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
290
+ "layers.30.self_attn.to_add_out.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
291
+ "layers.31.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
292
+ "layers.31.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
293
+ "layers.31.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
294
+ "layers.31.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
295
+ "layers.31.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
296
+ "layers.31.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
297
+ "layers.31.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
298
+ "layers.31.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
299
+ "layers.31.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
300
+ "layers.31.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
301
+ "layers.31.self_attn.to_add_out.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
302
+ "layers.32.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00014-of-00033.safetensors",
303
+ "layers.32.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
304
+ "layers.32.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
305
+ "layers.32.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
306
+ "layers.32.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
307
+ "layers.32.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
308
+ "layers.32.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
309
+ "layers.32.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
310
+ "layers.32.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
311
+ "layers.32.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
312
+ "layers.32.self_attn.to_add_out.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
313
+ "layers.33.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
314
+ "layers.33.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
315
+ "layers.33.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
316
+ "layers.33.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
317
+ "layers.33.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
318
+ "layers.33.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
319
+ "layers.33.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
320
+ "layers.33.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
321
+ "layers.33.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
322
+ "layers.33.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
323
+ "layers.33.self_attn.to_add_out.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
324
+ "layers.34.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
325
+ "layers.34.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
326
+ "layers.34.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
327
+ "layers.34.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
328
+ "layers.34.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
329
+ "layers.34.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00015-of-00033.safetensors",
330
+ "layers.34.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
331
+ "layers.34.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
332
+ "layers.34.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
333
+ "layers.34.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
334
+ "layers.34.self_attn.to_add_out.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
335
+ "layers.35.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
336
+ "layers.35.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
337
+ "layers.35.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
338
+ "layers.35.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
339
+ "layers.35.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
340
+ "layers.35.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
341
+ "layers.35.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
342
+ "layers.35.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
343
+ "layers.35.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
344
+ "layers.35.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
345
+ "layers.35.self_attn.to_add_out.weight": "diffusion_pytorch_model-00016-of-00033.safetensors",
346
+ "layers.36.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
347
+ "layers.36.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
348
+ "layers.36.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
349
+ "layers.36.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
350
+ "layers.36.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
351
+ "layers.36.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
352
+ "layers.36.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
353
+ "layers.36.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
354
+ "layers.36.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
355
+ "layers.36.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
356
+ "layers.36.self_attn.to_add_out.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
357
+ "layers.37.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
358
+ "layers.37.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
359
+ "layers.37.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
360
+ "layers.37.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
361
+ "layers.37.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
362
+ "layers.37.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
363
+ "layers.37.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
364
+ "layers.37.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
365
+ "layers.37.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
366
+ "layers.37.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
367
+ "layers.37.self_attn.to_add_out.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
368
+ "layers.38.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00017-of-00033.safetensors",
369
+ "layers.38.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
370
+ "layers.38.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
371
+ "layers.38.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
372
+ "layers.38.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
373
+ "layers.38.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
374
+ "layers.38.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
375
+ "layers.38.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
376
+ "layers.38.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
377
+ "layers.38.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
378
+ "layers.38.self_attn.to_add_out.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
379
+ "layers.39.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
380
+ "layers.39.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
381
+ "layers.39.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
382
+ "layers.39.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
383
+ "layers.39.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
384
+ "layers.39.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
385
+ "layers.39.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
386
+ "layers.39.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
387
+ "layers.39.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
388
+ "layers.39.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
389
+ "layers.39.self_attn.to_add_out.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
390
+ "layers.4.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
391
+ "layers.4.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
392
+ "layers.4.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
393
+ "layers.4.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
394
+ "layers.4.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
395
+ "layers.4.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
396
+ "layers.4.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
397
+ "layers.4.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
398
+ "layers.4.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
399
+ "layers.4.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
400
+ "layers.4.self_attn.to_add_out.weight": "diffusion_pytorch_model-00003-of-00033.safetensors",
401
+ "layers.40.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00018-of-00033.safetensors",
402
+ "layers.40.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
403
+ "layers.40.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
404
+ "layers.40.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
405
+ "layers.40.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
406
+ "layers.40.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
407
+ "layers.40.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
408
+ "layers.40.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
409
+ "layers.40.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
410
+ "layers.40.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
411
+ "layers.40.self_attn.to_add_out.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
412
+ "layers.41.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
413
+ "layers.41.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
414
+ "layers.41.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
415
+ "layers.41.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
416
+ "layers.41.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
417
+ "layers.41.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
418
+ "layers.41.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
419
+ "layers.41.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
420
+ "layers.41.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
421
+ "layers.41.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
422
+ "layers.41.self_attn.to_add_out.weight": "diffusion_pytorch_model-00019-of-00033.safetensors",
423
+ "layers.42.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
424
+ "layers.42.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
425
+ "layers.42.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
426
+ "layers.42.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
427
+ "layers.42.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
428
+ "layers.42.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
429
+ "layers.42.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
430
+ "layers.42.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
431
+ "layers.42.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
432
+ "layers.42.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
433
+ "layers.42.self_attn.to_add_out.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
434
+ "layers.43.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
435
+ "layers.43.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
436
+ "layers.43.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00021-of-00033.safetensors",
437
+ "layers.43.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
438
+ "layers.43.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
439
+ "layers.43.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
440
+ "layers.43.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
441
+ "layers.43.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
442
+ "layers.43.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
443
+ "layers.43.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
444
+ "layers.43.self_attn.to_add_out.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
445
+ "layers.44.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
446
+ "layers.44.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
447
+ "layers.44.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
448
+ "layers.44.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
449
+ "layers.44.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
450
+ "layers.44.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
451
+ "layers.44.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
452
+ "layers.44.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
453
+ "layers.44.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
454
+ "layers.44.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
455
+ "layers.44.self_attn.to_add_out.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
456
+ "layers.45.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
457
+ "layers.45.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
458
+ "layers.45.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00022-of-00033.safetensors",
459
+ "layers.45.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
460
+ "layers.45.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
461
+ "layers.45.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
462
+ "layers.45.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
463
+ "layers.45.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
464
+ "layers.45.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
465
+ "layers.45.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
466
+ "layers.45.self_attn.to_add_out.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
467
+ "layers.46.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
468
+ "layers.46.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
469
+ "layers.46.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
470
+ "layers.46.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
471
+ "layers.46.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
472
+ "layers.46.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
473
+ "layers.46.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
474
+ "layers.46.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
475
+ "layers.46.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
476
+ "layers.46.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
477
+ "layers.46.self_attn.to_add_out.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
478
+ "layers.47.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
479
+ "layers.47.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
480
+ "layers.47.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00023-of-00033.safetensors",
481
+ "layers.47.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
482
+ "layers.47.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
483
+ "layers.47.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
484
+ "layers.47.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
485
+ "layers.47.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
486
+ "layers.47.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
487
+ "layers.47.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
488
+ "layers.47.self_attn.to_add_out.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
489
+ "layers.48.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
490
+ "layers.48.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
491
+ "layers.48.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
492
+ "layers.48.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
493
+ "layers.48.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
494
+ "layers.48.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
495
+ "layers.48.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
496
+ "layers.48.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
497
+ "layers.48.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
498
+ "layers.48.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
499
+ "layers.48.self_attn.to_add_out.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
500
+ "layers.49.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
501
+ "layers.49.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
502
+ "layers.49.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
503
+ "layers.49.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
504
+ "layers.49.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
505
+ "layers.49.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
506
+ "layers.49.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
507
+ "layers.49.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
508
+ "layers.49.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
509
+ "layers.49.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
510
+ "layers.49.self_attn.to_add_out.weight": "diffusion_pytorch_model-00024-of-00033.safetensors",
511
+ "layers.5.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
512
+ "layers.5.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
513
+ "layers.5.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
514
+ "layers.5.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
515
+ "layers.5.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
516
+ "layers.5.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
517
+ "layers.5.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
518
+ "layers.5.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
519
+ "layers.5.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
520
+ "layers.5.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
521
+ "layers.5.self_attn.to_add_out.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
522
+ "layers.50.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
523
+ "layers.50.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
524
+ "layers.50.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
525
+ "layers.50.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
526
+ "layers.50.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
527
+ "layers.50.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
528
+ "layers.50.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
529
+ "layers.50.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
530
+ "layers.50.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
531
+ "layers.50.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
532
+ "layers.50.self_attn.to_add_out.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
533
+ "layers.51.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
534
+ "layers.51.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
535
+ "layers.51.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
536
+ "layers.51.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
537
+ "layers.51.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
538
+ "layers.51.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
539
+ "layers.51.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
540
+ "layers.51.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
541
+ "layers.51.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
542
+ "layers.51.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
543
+ "layers.51.self_attn.to_add_out.weight": "diffusion_pytorch_model-00025-of-00033.safetensors",
544
+ "layers.52.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
545
+ "layers.52.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
546
+ "layers.52.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
547
+ "layers.52.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
548
+ "layers.52.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
549
+ "layers.52.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
550
+ "layers.52.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
551
+ "layers.52.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
552
+ "layers.52.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
553
+ "layers.52.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
554
+ "layers.52.self_attn.to_add_out.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
555
+ "layers.53.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
556
+ "layers.53.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00026-of-00033.safetensors",
557
+ "layers.53.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
558
+ "layers.53.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
559
+ "layers.53.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
560
+ "layers.53.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
561
+ "layers.53.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
562
+ "layers.53.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
563
+ "layers.53.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
564
+ "layers.53.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
565
+ "layers.53.self_attn.to_add_out.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
566
+ "layers.54.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
567
+ "layers.54.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
568
+ "layers.54.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
569
+ "layers.54.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
570
+ "layers.54.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
571
+ "layers.54.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
572
+ "layers.54.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
573
+ "layers.54.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
574
+ "layers.54.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
575
+ "layers.54.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
576
+ "layers.54.self_attn.to_add_out.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
577
+ "layers.55.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
578
+ "layers.55.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00027-of-00033.safetensors",
579
+ "layers.55.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
580
+ "layers.55.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
581
+ "layers.55.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
582
+ "layers.55.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
583
+ "layers.55.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
584
+ "layers.55.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
585
+ "layers.55.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
586
+ "layers.55.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
587
+ "layers.55.self_attn.to_add_out.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
588
+ "layers.56.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
589
+ "layers.56.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
590
+ "layers.56.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
591
+ "layers.56.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
592
+ "layers.56.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
593
+ "layers.56.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
594
+ "layers.56.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
595
+ "layers.56.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
596
+ "layers.56.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
597
+ "layers.56.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
598
+ "layers.56.self_attn.to_add_out.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
599
+ "layers.57.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
600
+ "layers.57.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00028-of-00033.safetensors",
601
+ "layers.57.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
602
+ "layers.57.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
603
+ "layers.57.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
604
+ "layers.57.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
605
+ "layers.57.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
606
+ "layers.57.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
607
+ "layers.57.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
608
+ "layers.57.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
609
+ "layers.57.self_attn.to_add_out.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
610
+ "layers.58.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
611
+ "layers.58.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
612
+ "layers.58.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
613
+ "layers.58.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
614
+ "layers.58.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
615
+ "layers.58.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
616
+ "layers.58.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
617
+ "layers.58.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
618
+ "layers.58.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
619
+ "layers.58.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
620
+ "layers.58.self_attn.to_add_out.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
621
+ "layers.59.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
622
+ "layers.59.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
623
+ "layers.59.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
624
+ "layers.59.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
625
+ "layers.59.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
626
+ "layers.59.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
627
+ "layers.59.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
628
+ "layers.59.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
629
+ "layers.59.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
630
+ "layers.59.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
631
+ "layers.59.self_attn.to_add_out.weight": "diffusion_pytorch_model-00029-of-00033.safetensors",
632
+ "layers.6.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
633
+ "layers.6.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
634
+ "layers.6.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
635
+ "layers.6.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
636
+ "layers.6.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
637
+ "layers.6.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
638
+ "layers.6.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
639
+ "layers.6.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
640
+ "layers.6.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
641
+ "layers.6.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
642
+ "layers.6.self_attn.to_add_out.weight": "diffusion_pytorch_model-00020-of-00033.safetensors",
643
+ "layers.60.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
644
+ "layers.60.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
645
+ "layers.60.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
646
+ "layers.60.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
647
+ "layers.60.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
648
+ "layers.60.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
649
+ "layers.60.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
650
+ "layers.60.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
651
+ "layers.60.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
652
+ "layers.60.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
653
+ "layers.60.self_attn.to_add_out.weight": "diffusion_pytorch_model-00030-of-00033.safetensors",
654
+ "layers.61.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
655
+ "layers.61.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
656
+ "layers.61.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
657
+ "layers.61.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
658
+ "layers.61.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
659
+ "layers.61.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
660
+ "layers.61.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
661
+ "layers.61.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
662
+ "layers.61.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
663
+ "layers.61.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
664
+ "layers.61.self_attn.to_add_out.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
665
+ "layers.62.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
666
+ "layers.62.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
667
+ "layers.62.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
668
+ "layers.62.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
669
+ "layers.62.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
670
+ "layers.62.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
671
+ "layers.62.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
672
+ "layers.62.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
673
+ "layers.62.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
674
+ "layers.62.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
675
+ "layers.62.self_attn.to_add_out.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
676
+ "layers.63.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
677
+ "layers.63.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
678
+ "layers.63.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
679
+ "layers.63.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
680
+ "layers.63.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
681
+ "layers.63.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
682
+ "layers.63.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
683
+ "layers.63.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
684
+ "layers.63.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
685
+ "layers.63.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
686
+ "layers.63.self_attn.to_add_out.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
687
+ "layers.7.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
688
+ "layers.7.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
689
+ "layers.7.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
690
+ "layers.7.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
691
+ "layers.7.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
692
+ "layers.7.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
693
+ "layers.7.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
694
+ "layers.7.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
695
+ "layers.7.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
696
+ "layers.7.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
697
+ "layers.7.self_attn.to_add_out.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
698
+ "layers.8.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00031-of-00033.safetensors",
699
+ "layers.8.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
700
+ "layers.8.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
701
+ "layers.8.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
702
+ "layers.8.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
703
+ "layers.8.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
704
+ "layers.8.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
705
+ "layers.8.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
706
+ "layers.8.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
707
+ "layers.8.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
708
+ "layers.8.self_attn.to_add_out.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
709
+ "layers.9.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00004-of-00033.safetensors",
710
+ "layers.9.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00004-of-00033.safetensors",
711
+ "layers.9.mlp_moe_gen.gate_proj.weight": "diffusion_pytorch_model-00004-of-00033.safetensors",
712
+ "layers.9.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00004-of-00033.safetensors",
713
+ "layers.9.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00004-of-00033.safetensors",
714
+ "layers.9.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
715
+ "layers.9.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
716
+ "layers.9.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
717
+ "layers.9.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
718
+ "layers.9.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
719
+ "layers.9.self_attn.to_add_out.weight": "diffusion_pytorch_model-00032-of-00033.safetensors",
720
+ "norm_moe_gen.weight": "diffusion_pytorch_model-00033-of-00033.safetensors",
721
+ "proj_in.bias": "diffusion_pytorch_model-00001-of-00033.safetensors",
722
+ "proj_in.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
723
+ "proj_out.bias": "diffusion_pytorch_model-00001-of-00033.safetensors",
724
+ "proj_out.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
725
+ "time_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00033.safetensors",
726
+ "time_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00033.safetensors",
727
+ "time_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00033.safetensors",
728
+ "time_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00033.safetensors"
729
+ }
730
+ }
model.safetensors.index.json DELETED
@@ -1,730 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 62515227136
4
- },
5
- "weight_map": {
6
- "action_modality_embed": "model-00001-of-00033.safetensors",
7
- "action_proj_in.bias.weight": "model-00001-of-00033.safetensors",
8
- "action_proj_in.fc.weight": "model-00001-of-00033.safetensors",
9
- "action_proj_out.bias.weight": "model-00001-of-00033.safetensors",
10
- "action_proj_out.fc.weight": "model-00001-of-00033.safetensors",
11
- "audio_modality_embed": "model-00001-of-00033.safetensors",
12
- "audio_proj_in.bias": "model-00001-of-00033.safetensors",
13
- "audio_proj_in.weight": "model-00001-of-00033.safetensors",
14
- "audio_proj_out.bias": "model-00001-of-00033.safetensors",
15
- "audio_proj_out.weight": "model-00001-of-00033.safetensors",
16
- "layers.0.input_layernorm_moe_gen.weight": "model-00001-of-00033.safetensors",
17
- "layers.0.mlp_moe_gen.down_proj.weight": "model-00001-of-00033.safetensors",
18
- "layers.0.mlp_moe_gen.gate_proj.weight": "model-00001-of-00033.safetensors",
19
- "layers.0.mlp_moe_gen.up_proj.weight": "model-00001-of-00033.safetensors",
20
- "layers.0.post_attention_layernorm_moe_gen.weight": "model-00001-of-00033.safetensors",
21
- "layers.0.self_attn.add_k_proj.weight": "model-00001-of-00033.safetensors",
22
- "layers.0.self_attn.add_q_proj.weight": "model-00001-of-00033.safetensors",
23
- "layers.0.self_attn.add_v_proj.weight": "model-00001-of-00033.safetensors",
24
- "layers.0.self_attn.norm_added_k.weight": "model-00001-of-00033.safetensors",
25
- "layers.0.self_attn.norm_added_q.weight": "model-00001-of-00033.safetensors",
26
- "layers.0.self_attn.to_add_out.weight": "model-00001-of-00033.safetensors",
27
- "layers.1.input_layernorm_moe_gen.weight": "model-00001-of-00033.safetensors",
28
- "layers.1.mlp_moe_gen.down_proj.weight": "model-00001-of-00033.safetensors",
29
- "layers.1.mlp_moe_gen.gate_proj.weight": "model-00001-of-00033.safetensors",
30
- "layers.1.mlp_moe_gen.up_proj.weight": "model-00002-of-00033.safetensors",
31
- "layers.1.post_attention_layernorm_moe_gen.weight": "model-00002-of-00033.safetensors",
32
- "layers.1.self_attn.add_k_proj.weight": "model-00001-of-00033.safetensors",
33
- "layers.1.self_attn.add_q_proj.weight": "model-00001-of-00033.safetensors",
34
- "layers.1.self_attn.add_v_proj.weight": "model-00001-of-00033.safetensors",
35
- "layers.1.self_attn.norm_added_k.weight": "model-00001-of-00033.safetensors",
36
- "layers.1.self_attn.norm_added_q.weight": "model-00001-of-00033.safetensors",
37
- "layers.1.self_attn.to_add_out.weight": "model-00001-of-00033.safetensors",
38
- "layers.10.input_layernorm_moe_gen.weight": "model-00003-of-00033.safetensors",
39
- "layers.10.mlp_moe_gen.down_proj.weight": "model-00003-of-00033.safetensors",
40
- "layers.10.mlp_moe_gen.gate_proj.weight": "model-00003-of-00033.safetensors",
41
- "layers.10.mlp_moe_gen.up_proj.weight": "model-00003-of-00033.safetensors",
42
- "layers.10.post_attention_layernorm_moe_gen.weight": "model-00003-of-00033.safetensors",
43
- "layers.10.self_attn.add_k_proj.weight": "model-00003-of-00033.safetensors",
44
- "layers.10.self_attn.add_q_proj.weight": "model-00003-of-00033.safetensors",
45
- "layers.10.self_attn.add_v_proj.weight": "model-00003-of-00033.safetensors",
46
- "layers.10.self_attn.norm_added_k.weight": "model-00003-of-00033.safetensors",
47
- "layers.10.self_attn.norm_added_q.weight": "model-00003-of-00033.safetensors",
48
- "layers.10.self_attn.to_add_out.weight": "model-00003-of-00033.safetensors",
49
- "layers.11.input_layernorm_moe_gen.weight": "model-00004-of-00033.safetensors",
50
- "layers.11.mlp_moe_gen.down_proj.weight": "model-00004-of-00033.safetensors",
51
- "layers.11.mlp_moe_gen.gate_proj.weight": "model-00003-of-00033.safetensors",
52
- "layers.11.mlp_moe_gen.up_proj.weight": "model-00004-of-00033.safetensors",
53
- "layers.11.post_attention_layernorm_moe_gen.weight": "model-00004-of-00033.safetensors",
54
- "layers.11.self_attn.add_k_proj.weight": "model-00003-of-00033.safetensors",
55
- "layers.11.self_attn.add_q_proj.weight": "model-00003-of-00033.safetensors",
56
- "layers.11.self_attn.add_v_proj.weight": "model-00003-of-00033.safetensors",
57
- "layers.11.self_attn.norm_added_k.weight": "model-00003-of-00033.safetensors",
58
- "layers.11.self_attn.norm_added_q.weight": "model-00003-of-00033.safetensors",
59
- "layers.11.self_attn.to_add_out.weight": "model-00004-of-00033.safetensors",
60
- "layers.12.input_layernorm_moe_gen.weight": "model-00004-of-00033.safetensors",
61
- "layers.12.mlp_moe_gen.down_proj.weight": "model-00004-of-00033.safetensors",
62
- "layers.12.mlp_moe_gen.gate_proj.weight": "model-00004-of-00033.safetensors",
63
- "layers.12.mlp_moe_gen.up_proj.weight": "model-00005-of-00033.safetensors",
64
- "layers.12.post_attention_layernorm_moe_gen.weight": "model-00005-of-00033.safetensors",
65
- "layers.12.self_attn.add_k_proj.weight": "model-00005-of-00033.safetensors",
66
- "layers.12.self_attn.add_q_proj.weight": "model-00005-of-00033.safetensors",
67
- "layers.12.self_attn.add_v_proj.weight": "model-00005-of-00033.safetensors",
68
- "layers.12.self_attn.norm_added_k.weight": "model-00005-of-00033.safetensors",
69
- "layers.12.self_attn.norm_added_q.weight": "model-00005-of-00033.safetensors",
70
- "layers.12.self_attn.to_add_out.weight": "model-00005-of-00033.safetensors",
71
- "layers.13.input_layernorm_moe_gen.weight": "model-00005-of-00033.safetensors",
72
- "layers.13.mlp_moe_gen.down_proj.weight": "model-00005-of-00033.safetensors",
73
- "layers.13.mlp_moe_gen.gate_proj.weight": "model-00005-of-00033.safetensors",
74
- "layers.13.mlp_moe_gen.up_proj.weight": "model-00005-of-00033.safetensors",
75
- "layers.13.post_attention_layernorm_moe_gen.weight": "model-00005-of-00033.safetensors",
76
- "layers.13.self_attn.add_k_proj.weight": "model-00005-of-00033.safetensors",
77
- "layers.13.self_attn.add_q_proj.weight": "model-00005-of-00033.safetensors",
78
- "layers.13.self_attn.add_v_proj.weight": "model-00005-of-00033.safetensors",
79
- "layers.13.self_attn.norm_added_k.weight": "model-00005-of-00033.safetensors",
80
- "layers.13.self_attn.norm_added_q.weight": "model-00005-of-00033.safetensors",
81
- "layers.13.self_attn.to_add_out.weight": "model-00005-of-00033.safetensors",
82
- "layers.14.input_layernorm_moe_gen.weight": "model-00005-of-00033.safetensors",
83
- "layers.14.mlp_moe_gen.down_proj.weight": "model-00005-of-00033.safetensors",
84
- "layers.14.mlp_moe_gen.gate_proj.weight": "model-00006-of-00033.safetensors",
85
- "layers.14.mlp_moe_gen.up_proj.weight": "model-00006-of-00033.safetensors",
86
- "layers.14.post_attention_layernorm_moe_gen.weight": "model-00006-of-00033.safetensors",
87
- "layers.14.self_attn.add_k_proj.weight": "model-00005-of-00033.safetensors",
88
- "layers.14.self_attn.add_q_proj.weight": "model-00005-of-00033.safetensors",
89
- "layers.14.self_attn.add_v_proj.weight": "model-00005-of-00033.safetensors",
90
- "layers.14.self_attn.norm_added_k.weight": "model-00005-of-00033.safetensors",
91
- "layers.14.self_attn.norm_added_q.weight": "model-00005-of-00033.safetensors",
92
- "layers.14.self_attn.to_add_out.weight": "model-00005-of-00033.safetensors",
93
- "layers.15.input_layernorm_moe_gen.weight": "model-00006-of-00033.safetensors",
94
- "layers.15.mlp_moe_gen.down_proj.weight": "model-00006-of-00033.safetensors",
95
- "layers.15.mlp_moe_gen.gate_proj.weight": "model-00006-of-00033.safetensors",
96
- "layers.15.mlp_moe_gen.up_proj.weight": "model-00006-of-00033.safetensors",
97
- "layers.15.post_attention_layernorm_moe_gen.weight": "model-00006-of-00033.safetensors",
98
- "layers.15.self_attn.add_k_proj.weight": "model-00006-of-00033.safetensors",
99
- "layers.15.self_attn.add_q_proj.weight": "model-00006-of-00033.safetensors",
100
- "layers.15.self_attn.add_v_proj.weight": "model-00006-of-00033.safetensors",
101
- "layers.15.self_attn.norm_added_k.weight": "model-00006-of-00033.safetensors",
102
- "layers.15.self_attn.norm_added_q.weight": "model-00006-of-00033.safetensors",
103
- "layers.15.self_attn.to_add_out.weight": "model-00006-of-00033.safetensors",
104
- "layers.16.input_layernorm_moe_gen.weight": "model-00006-of-00033.safetensors",
105
- "layers.16.mlp_moe_gen.down_proj.weight": "model-00007-of-00033.safetensors",
106
- "layers.16.mlp_moe_gen.gate_proj.weight": "model-00006-of-00033.safetensors",
107
- "layers.16.mlp_moe_gen.up_proj.weight": "model-00007-of-00033.safetensors",
108
- "layers.16.post_attention_layernorm_moe_gen.weight": "model-00007-of-00033.safetensors",
109
- "layers.16.self_attn.add_k_proj.weight": "model-00006-of-00033.safetensors",
110
- "layers.16.self_attn.add_q_proj.weight": "model-00006-of-00033.safetensors",
111
- "layers.16.self_attn.add_v_proj.weight": "model-00006-of-00033.safetensors",
112
- "layers.16.self_attn.norm_added_k.weight": "model-00006-of-00033.safetensors",
113
- "layers.16.self_attn.norm_added_q.weight": "model-00006-of-00033.safetensors",
114
- "layers.16.self_attn.to_add_out.weight": "model-00006-of-00033.safetensors",
115
- "layers.17.input_layernorm_moe_gen.weight": "model-00007-of-00033.safetensors",
116
- "layers.17.mlp_moe_gen.down_proj.weight": "model-00007-of-00033.safetensors",
117
- "layers.17.mlp_moe_gen.gate_proj.weight": "model-00007-of-00033.safetensors",
118
- "layers.17.mlp_moe_gen.up_proj.weight": "model-00007-of-00033.safetensors",
119
- "layers.17.post_attention_layernorm_moe_gen.weight": "model-00007-of-00033.safetensors",
120
- "layers.17.self_attn.add_k_proj.weight": "model-00007-of-00033.safetensors",
121
- "layers.17.self_attn.add_q_proj.weight": "model-00007-of-00033.safetensors",
122
- "layers.17.self_attn.add_v_proj.weight": "model-00007-of-00033.safetensors",
123
- "layers.17.self_attn.norm_added_k.weight": "model-00007-of-00033.safetensors",
124
- "layers.17.self_attn.norm_added_q.weight": "model-00007-of-00033.safetensors",
125
- "layers.17.self_attn.to_add_out.weight": "model-00007-of-00033.safetensors",
126
- "layers.18.input_layernorm_moe_gen.weight": "model-00007-of-00033.safetensors",
127
- "layers.18.mlp_moe_gen.down_proj.weight": "model-00007-of-00033.safetensors",
128
- "layers.18.mlp_moe_gen.gate_proj.weight": "model-00008-of-00033.safetensors",
129
- "layers.18.mlp_moe_gen.up_proj.weight": "model-00008-of-00033.safetensors",
130
- "layers.18.post_attention_layernorm_moe_gen.weight": "model-00008-of-00033.safetensors",
131
- "layers.18.self_attn.add_k_proj.weight": "model-00008-of-00033.safetensors",
132
- "layers.18.self_attn.add_q_proj.weight": "model-00008-of-00033.safetensors",
133
- "layers.18.self_attn.add_v_proj.weight": "model-00008-of-00033.safetensors",
134
- "layers.18.self_attn.norm_added_k.weight": "model-00008-of-00033.safetensors",
135
- "layers.18.self_attn.norm_added_q.weight": "model-00008-of-00033.safetensors",
136
- "layers.18.self_attn.to_add_out.weight": "model-00008-of-00033.safetensors",
137
- "layers.19.input_layernorm_moe_gen.weight": "model-00008-of-00033.safetensors",
138
- "layers.19.mlp_moe_gen.down_proj.weight": "model-00008-of-00033.safetensors",
139
- "layers.19.mlp_moe_gen.gate_proj.weight": "model-00008-of-00033.safetensors",
140
- "layers.19.mlp_moe_gen.up_proj.weight": "model-00008-of-00033.safetensors",
141
- "layers.19.post_attention_layernorm_moe_gen.weight": "model-00008-of-00033.safetensors",
142
- "layers.19.self_attn.add_k_proj.weight": "model-00008-of-00033.safetensors",
143
- "layers.19.self_attn.add_q_proj.weight": "model-00008-of-00033.safetensors",
144
- "layers.19.self_attn.add_v_proj.weight": "model-00008-of-00033.safetensors",
145
- "layers.19.self_attn.norm_added_k.weight": "model-00008-of-00033.safetensors",
146
- "layers.19.self_attn.norm_added_q.weight": "model-00008-of-00033.safetensors",
147
- "layers.19.self_attn.to_add_out.weight": "model-00008-of-00033.safetensors",
148
- "layers.2.input_layernorm_moe_gen.weight": "model-00002-of-00033.safetensors",
149
- "layers.2.mlp_moe_gen.down_proj.weight": "model-00002-of-00033.safetensors",
150
- "layers.2.mlp_moe_gen.gate_proj.weight": "model-00002-of-00033.safetensors",
151
- "layers.2.mlp_moe_gen.up_proj.weight": "model-00002-of-00033.safetensors",
152
- "layers.2.post_attention_layernorm_moe_gen.weight": "model-00002-of-00033.safetensors",
153
- "layers.2.self_attn.add_k_proj.weight": "model-00002-of-00033.safetensors",
154
- "layers.2.self_attn.add_q_proj.weight": "model-00002-of-00033.safetensors",
155
- "layers.2.self_attn.add_v_proj.weight": "model-00002-of-00033.safetensors",
156
- "layers.2.self_attn.norm_added_k.weight": "model-00002-of-00033.safetensors",
157
- "layers.2.self_attn.norm_added_q.weight": "model-00002-of-00033.safetensors",
158
- "layers.2.self_attn.to_add_out.weight": "model-00002-of-00033.safetensors",
159
- "layers.20.input_layernorm_moe_gen.weight": "model-00008-of-00033.safetensors",
160
- "layers.20.mlp_moe_gen.down_proj.weight": "model-00008-of-00033.safetensors",
161
- "layers.20.mlp_moe_gen.gate_proj.weight": "model-00009-of-00033.safetensors",
162
- "layers.20.mlp_moe_gen.up_proj.weight": "model-00009-of-00033.safetensors",
163
- "layers.20.post_attention_layernorm_moe_gen.weight": "model-00009-of-00033.safetensors",
164
- "layers.20.self_attn.add_k_proj.weight": "model-00009-of-00033.safetensors",
165
- "layers.20.self_attn.add_q_proj.weight": "model-00009-of-00033.safetensors",
166
- "layers.20.self_attn.add_v_proj.weight": "model-00009-of-00033.safetensors",
167
- "layers.20.self_attn.norm_added_k.weight": "model-00009-of-00033.safetensors",
168
- "layers.20.self_attn.norm_added_q.weight": "model-00009-of-00033.safetensors",
169
- "layers.20.self_attn.to_add_out.weight": "model-00009-of-00033.safetensors",
170
- "layers.21.input_layernorm_moe_gen.weight": "model-00009-of-00033.safetensors",
171
- "layers.21.mlp_moe_gen.down_proj.weight": "model-00009-of-00033.safetensors",
172
- "layers.21.mlp_moe_gen.gate_proj.weight": "model-00009-of-00033.safetensors",
173
- "layers.21.mlp_moe_gen.up_proj.weight": "model-00009-of-00033.safetensors",
174
- "layers.21.post_attention_layernorm_moe_gen.weight": "model-00009-of-00033.safetensors",
175
- "layers.21.self_attn.add_k_proj.weight": "model-00009-of-00033.safetensors",
176
- "layers.21.self_attn.add_q_proj.weight": "model-00009-of-00033.safetensors",
177
- "layers.21.self_attn.add_v_proj.weight": "model-00009-of-00033.safetensors",
178
- "layers.21.self_attn.norm_added_k.weight": "model-00009-of-00033.safetensors",
179
- "layers.21.self_attn.norm_added_q.weight": "model-00009-of-00033.safetensors",
180
- "layers.21.self_attn.to_add_out.weight": "model-00009-of-00033.safetensors",
181
- "layers.22.input_layernorm_moe_gen.weight": "model-00009-of-00033.safetensors",
182
- "layers.22.mlp_moe_gen.down_proj.weight": "model-00009-of-00033.safetensors",
183
- "layers.22.mlp_moe_gen.gate_proj.weight": "model-00010-of-00033.safetensors",
184
- "layers.22.mlp_moe_gen.up_proj.weight": "model-00010-of-00033.safetensors",
185
- "layers.22.post_attention_layernorm_moe_gen.weight": "model-00010-of-00033.safetensors",
186
- "layers.22.self_attn.add_k_proj.weight": "model-00010-of-00033.safetensors",
187
- "layers.22.self_attn.add_q_proj.weight": "model-00010-of-00033.safetensors",
188
- "layers.22.self_attn.add_v_proj.weight": "model-00010-of-00033.safetensors",
189
- "layers.22.self_attn.norm_added_k.weight": "model-00010-of-00033.safetensors",
190
- "layers.22.self_attn.norm_added_q.weight": "model-00010-of-00033.safetensors",
191
- "layers.22.self_attn.to_add_out.weight": "model-00010-of-00033.safetensors",
192
- "layers.23.input_layernorm_moe_gen.weight": "model-00010-of-00033.safetensors",
193
- "layers.23.mlp_moe_gen.down_proj.weight": "model-00010-of-00033.safetensors",
194
- "layers.23.mlp_moe_gen.gate_proj.weight": "model-00010-of-00033.safetensors",
195
- "layers.23.mlp_moe_gen.up_proj.weight": "model-00010-of-00033.safetensors",
196
- "layers.23.post_attention_layernorm_moe_gen.weight": "model-00010-of-00033.safetensors",
197
- "layers.23.self_attn.add_k_proj.weight": "model-00010-of-00033.safetensors",
198
- "layers.23.self_attn.add_q_proj.weight": "model-00010-of-00033.safetensors",
199
- "layers.23.self_attn.add_v_proj.weight": "model-00010-of-00033.safetensors",
200
- "layers.23.self_attn.norm_added_k.weight": "model-00010-of-00033.safetensors",
201
- "layers.23.self_attn.norm_added_q.weight": "model-00010-of-00033.safetensors",
202
- "layers.23.self_attn.to_add_out.weight": "model-00010-of-00033.safetensors",
203
- "layers.24.input_layernorm_moe_gen.weight": "model-00010-of-00033.safetensors",
204
- "layers.24.mlp_moe_gen.down_proj.weight": "model-00011-of-00033.safetensors",
205
- "layers.24.mlp_moe_gen.gate_proj.weight": "model-00011-of-00033.safetensors",
206
- "layers.24.mlp_moe_gen.up_proj.weight": "model-00011-of-00033.safetensors",
207
- "layers.24.post_attention_layernorm_moe_gen.weight": "model-00011-of-00033.safetensors",
208
- "layers.24.self_attn.add_k_proj.weight": "model-00010-of-00033.safetensors",
209
- "layers.24.self_attn.add_q_proj.weight": "model-00010-of-00033.safetensors",
210
- "layers.24.self_attn.add_v_proj.weight": "model-00010-of-00033.safetensors",
211
- "layers.24.self_attn.norm_added_k.weight": "model-00010-of-00033.safetensors",
212
- "layers.24.self_attn.norm_added_q.weight": "model-00010-of-00033.safetensors",
213
- "layers.24.self_attn.to_add_out.weight": "model-00010-of-00033.safetensors",
214
- "layers.25.input_layernorm_moe_gen.weight": "model-00011-of-00033.safetensors",
215
- "layers.25.mlp_moe_gen.down_proj.weight": "model-00011-of-00033.safetensors",
216
- "layers.25.mlp_moe_gen.gate_proj.weight": "model-00011-of-00033.safetensors",
217
- "layers.25.mlp_moe_gen.up_proj.weight": "model-00011-of-00033.safetensors",
218
- "layers.25.post_attention_layernorm_moe_gen.weight": "model-00011-of-00033.safetensors",
219
- "layers.25.self_attn.add_k_proj.weight": "model-00011-of-00033.safetensors",
220
- "layers.25.self_attn.add_q_proj.weight": "model-00011-of-00033.safetensors",
221
- "layers.25.self_attn.add_v_proj.weight": "model-00011-of-00033.safetensors",
222
- "layers.25.self_attn.norm_added_k.weight": "model-00011-of-00033.safetensors",
223
- "layers.25.self_attn.norm_added_q.weight": "model-00011-of-00033.safetensors",
224
- "layers.25.self_attn.to_add_out.weight": "model-00011-of-00033.safetensors",
225
- "layers.26.input_layernorm_moe_gen.weight": "model-00012-of-00033.safetensors",
226
- "layers.26.mlp_moe_gen.down_proj.weight": "model-00012-of-00033.safetensors",
227
- "layers.26.mlp_moe_gen.gate_proj.weight": "model-00012-of-00033.safetensors",
228
- "layers.26.mlp_moe_gen.up_proj.weight": "model-00012-of-00033.safetensors",
229
- "layers.26.post_attention_layernorm_moe_gen.weight": "model-00012-of-00033.safetensors",
230
- "layers.26.self_attn.add_k_proj.weight": "model-00012-of-00033.safetensors",
231
- "layers.26.self_attn.add_q_proj.weight": "model-00012-of-00033.safetensors",
232
- "layers.26.self_attn.add_v_proj.weight": "model-00012-of-00033.safetensors",
233
- "layers.26.self_attn.norm_added_k.weight": "model-00012-of-00033.safetensors",
234
- "layers.26.self_attn.norm_added_q.weight": "model-00012-of-00033.safetensors",
235
- "layers.26.self_attn.to_add_out.weight": "model-00012-of-00033.safetensors",
236
- "layers.27.input_layernorm_moe_gen.weight": "model-00012-of-00033.safetensors",
237
- "layers.27.mlp_moe_gen.down_proj.weight": "model-00012-of-00033.safetensors",
238
- "layers.27.mlp_moe_gen.gate_proj.weight": "model-00012-of-00033.safetensors",
239
- "layers.27.mlp_moe_gen.up_proj.weight": "model-00012-of-00033.safetensors",
240
- "layers.27.post_attention_layernorm_moe_gen.weight": "model-00012-of-00033.safetensors",
241
- "layers.27.self_attn.add_k_proj.weight": "model-00012-of-00033.safetensors",
242
- "layers.27.self_attn.add_q_proj.weight": "model-00012-of-00033.safetensors",
243
- "layers.27.self_attn.add_v_proj.weight": "model-00012-of-00033.safetensors",
244
- "layers.27.self_attn.norm_added_k.weight": "model-00012-of-00033.safetensors",
245
- "layers.27.self_attn.norm_added_q.weight": "model-00012-of-00033.safetensors",
246
- "layers.27.self_attn.to_add_out.weight": "model-00012-of-00033.safetensors",
247
- "layers.28.input_layernorm_moe_gen.weight": "model-00012-of-00033.safetensors",
248
- "layers.28.mlp_moe_gen.down_proj.weight": "model-00013-of-00033.safetensors",
249
- "layers.28.mlp_moe_gen.gate_proj.weight": "model-00013-of-00033.safetensors",
250
- "layers.28.mlp_moe_gen.up_proj.weight": "model-00013-of-00033.safetensors",
251
- "layers.28.post_attention_layernorm_moe_gen.weight": "model-00013-of-00033.safetensors",
252
- "layers.28.self_attn.add_k_proj.weight": "model-00013-of-00033.safetensors",
253
- "layers.28.self_attn.add_q_proj.weight": "model-00013-of-00033.safetensors",
254
- "layers.28.self_attn.add_v_proj.weight": "model-00013-of-00033.safetensors",
255
- "layers.28.self_attn.norm_added_k.weight": "model-00013-of-00033.safetensors",
256
- "layers.28.self_attn.norm_added_q.weight": "model-00013-of-00033.safetensors",
257
- "layers.28.self_attn.to_add_out.weight": "model-00013-of-00033.safetensors",
258
- "layers.29.input_layernorm_moe_gen.weight": "model-00013-of-00033.safetensors",
259
- "layers.29.mlp_moe_gen.down_proj.weight": "model-00013-of-00033.safetensors",
260
- "layers.29.mlp_moe_gen.gate_proj.weight": "model-00013-of-00033.safetensors",
261
- "layers.29.mlp_moe_gen.up_proj.weight": "model-00013-of-00033.safetensors",
262
- "layers.29.post_attention_layernorm_moe_gen.weight": "model-00013-of-00033.safetensors",
263
- "layers.29.self_attn.add_k_proj.weight": "model-00013-of-00033.safetensors",
264
- "layers.29.self_attn.add_q_proj.weight": "model-00013-of-00033.safetensors",
265
- "layers.29.self_attn.add_v_proj.weight": "model-00013-of-00033.safetensors",
266
- "layers.29.self_attn.norm_added_k.weight": "model-00013-of-00033.safetensors",
267
- "layers.29.self_attn.norm_added_q.weight": "model-00013-of-00033.safetensors",
268
- "layers.29.self_attn.to_add_out.weight": "model-00013-of-00033.safetensors",
269
- "layers.3.input_layernorm_moe_gen.weight": "model-00002-of-00033.safetensors",
270
- "layers.3.mlp_moe_gen.down_proj.weight": "model-00002-of-00033.safetensors",
271
- "layers.3.mlp_moe_gen.gate_proj.weight": "model-00002-of-00033.safetensors",
272
- "layers.3.mlp_moe_gen.up_proj.weight": "model-00003-of-00033.safetensors",
273
- "layers.3.post_attention_layernorm_moe_gen.weight": "model-00003-of-00033.safetensors",
274
- "layers.3.self_attn.add_k_proj.weight": "model-00003-of-00033.safetensors",
275
- "layers.3.self_attn.add_q_proj.weight": "model-00003-of-00033.safetensors",
276
- "layers.3.self_attn.add_v_proj.weight": "model-00003-of-00033.safetensors",
277
- "layers.3.self_attn.norm_added_k.weight": "model-00003-of-00033.safetensors",
278
- "layers.3.self_attn.norm_added_q.weight": "model-00003-of-00033.safetensors",
279
- "layers.3.self_attn.to_add_out.weight": "model-00003-of-00033.safetensors",
280
- "layers.30.input_layernorm_moe_gen.weight": "model-00013-of-00033.safetensors",
281
- "layers.30.mlp_moe_gen.down_proj.weight": "model-00014-of-00033.safetensors",
282
- "layers.30.mlp_moe_gen.gate_proj.weight": "model-00014-of-00033.safetensors",
283
- "layers.30.mlp_moe_gen.up_proj.weight": "model-00014-of-00033.safetensors",
284
- "layers.30.post_attention_layernorm_moe_gen.weight": "model-00014-of-00033.safetensors",
285
- "layers.30.self_attn.add_k_proj.weight": "model-00014-of-00033.safetensors",
286
- "layers.30.self_attn.add_q_proj.weight": "model-00014-of-00033.safetensors",
287
- "layers.30.self_attn.add_v_proj.weight": "model-00014-of-00033.safetensors",
288
- "layers.30.self_attn.norm_added_k.weight": "model-00014-of-00033.safetensors",
289
- "layers.30.self_attn.norm_added_q.weight": "model-00014-of-00033.safetensors",
290
- "layers.30.self_attn.to_add_out.weight": "model-00014-of-00033.safetensors",
291
- "layers.31.input_layernorm_moe_gen.weight": "model-00014-of-00033.safetensors",
292
- "layers.31.mlp_moe_gen.down_proj.weight": "model-00014-of-00033.safetensors",
293
- "layers.31.mlp_moe_gen.gate_proj.weight": "model-00014-of-00033.safetensors",
294
- "layers.31.mlp_moe_gen.up_proj.weight": "model-00014-of-00033.safetensors",
295
- "layers.31.post_attention_layernorm_moe_gen.weight": "model-00014-of-00033.safetensors",
296
- "layers.31.self_attn.add_k_proj.weight": "model-00014-of-00033.safetensors",
297
- "layers.31.self_attn.add_q_proj.weight": "model-00014-of-00033.safetensors",
298
- "layers.31.self_attn.add_v_proj.weight": "model-00014-of-00033.safetensors",
299
- "layers.31.self_attn.norm_added_k.weight": "model-00014-of-00033.safetensors",
300
- "layers.31.self_attn.norm_added_q.weight": "model-00014-of-00033.safetensors",
301
- "layers.31.self_attn.to_add_out.weight": "model-00014-of-00033.safetensors",
302
- "layers.32.input_layernorm_moe_gen.weight": "model-00014-of-00033.safetensors",
303
- "layers.32.mlp_moe_gen.down_proj.weight": "model-00015-of-00033.safetensors",
304
- "layers.32.mlp_moe_gen.gate_proj.weight": "model-00015-of-00033.safetensors",
305
- "layers.32.mlp_moe_gen.up_proj.weight": "model-00015-of-00033.safetensors",
306
- "layers.32.post_attention_layernorm_moe_gen.weight": "model-00015-of-00033.safetensors",
307
- "layers.32.self_attn.add_k_proj.weight": "model-00015-of-00033.safetensors",
308
- "layers.32.self_attn.add_q_proj.weight": "model-00015-of-00033.safetensors",
309
- "layers.32.self_attn.add_v_proj.weight": "model-00015-of-00033.safetensors",
310
- "layers.32.self_attn.norm_added_k.weight": "model-00015-of-00033.safetensors",
311
- "layers.32.self_attn.norm_added_q.weight": "model-00015-of-00033.safetensors",
312
- "layers.32.self_attn.to_add_out.weight": "model-00015-of-00033.safetensors",
313
- "layers.33.input_layernorm_moe_gen.weight": "model-00015-of-00033.safetensors",
314
- "layers.33.mlp_moe_gen.down_proj.weight": "model-00015-of-00033.safetensors",
315
- "layers.33.mlp_moe_gen.gate_proj.weight": "model-00015-of-00033.safetensors",
316
- "layers.33.mlp_moe_gen.up_proj.weight": "model-00015-of-00033.safetensors",
317
- "layers.33.post_attention_layernorm_moe_gen.weight": "model-00015-of-00033.safetensors",
318
- "layers.33.self_attn.add_k_proj.weight": "model-00015-of-00033.safetensors",
319
- "layers.33.self_attn.add_q_proj.weight": "model-00015-of-00033.safetensors",
320
- "layers.33.self_attn.add_v_proj.weight": "model-00015-of-00033.safetensors",
321
- "layers.33.self_attn.norm_added_k.weight": "model-00015-of-00033.safetensors",
322
- "layers.33.self_attn.norm_added_q.weight": "model-00015-of-00033.safetensors",
323
- "layers.33.self_attn.to_add_out.weight": "model-00015-of-00033.safetensors",
324
- "layers.34.input_layernorm_moe_gen.weight": "model-00016-of-00033.safetensors",
325
- "layers.34.mlp_moe_gen.down_proj.weight": "model-00016-of-00033.safetensors",
326
- "layers.34.mlp_moe_gen.gate_proj.weight": "model-00016-of-00033.safetensors",
327
- "layers.34.mlp_moe_gen.up_proj.weight": "model-00016-of-00033.safetensors",
328
- "layers.34.post_attention_layernorm_moe_gen.weight": "model-00016-of-00033.safetensors",
329
- "layers.34.self_attn.add_k_proj.weight": "model-00015-of-00033.safetensors",
330
- "layers.34.self_attn.add_q_proj.weight": "model-00016-of-00033.safetensors",
331
- "layers.34.self_attn.add_v_proj.weight": "model-00016-of-00033.safetensors",
332
- "layers.34.self_attn.norm_added_k.weight": "model-00016-of-00033.safetensors",
333
- "layers.34.self_attn.norm_added_q.weight": "model-00016-of-00033.safetensors",
334
- "layers.34.self_attn.to_add_out.weight": "model-00016-of-00033.safetensors",
335
- "layers.35.input_layernorm_moe_gen.weight": "model-00016-of-00033.safetensors",
336
- "layers.35.mlp_moe_gen.down_proj.weight": "model-00016-of-00033.safetensors",
337
- "layers.35.mlp_moe_gen.gate_proj.weight": "model-00016-of-00033.safetensors",
338
- "layers.35.mlp_moe_gen.up_proj.weight": "model-00016-of-00033.safetensors",
339
- "layers.35.post_attention_layernorm_moe_gen.weight": "model-00016-of-00033.safetensors",
340
- "layers.35.self_attn.add_k_proj.weight": "model-00016-of-00033.safetensors",
341
- "layers.35.self_attn.add_q_proj.weight": "model-00016-of-00033.safetensors",
342
- "layers.35.self_attn.add_v_proj.weight": "model-00016-of-00033.safetensors",
343
- "layers.35.self_attn.norm_added_k.weight": "model-00016-of-00033.safetensors",
344
- "layers.35.self_attn.norm_added_q.weight": "model-00016-of-00033.safetensors",
345
- "layers.35.self_attn.to_add_out.weight": "model-00016-of-00033.safetensors",
346
- "layers.36.input_layernorm_moe_gen.weight": "model-00017-of-00033.safetensors",
347
- "layers.36.mlp_moe_gen.down_proj.weight": "model-00017-of-00033.safetensors",
348
- "layers.36.mlp_moe_gen.gate_proj.weight": "model-00017-of-00033.safetensors",
349
- "layers.36.mlp_moe_gen.up_proj.weight": "model-00017-of-00033.safetensors",
350
- "layers.36.post_attention_layernorm_moe_gen.weight": "model-00017-of-00033.safetensors",
351
- "layers.36.self_attn.add_k_proj.weight": "model-00017-of-00033.safetensors",
352
- "layers.36.self_attn.add_q_proj.weight": "model-00017-of-00033.safetensors",
353
- "layers.36.self_attn.add_v_proj.weight": "model-00017-of-00033.safetensors",
354
- "layers.36.self_attn.norm_added_k.weight": "model-00017-of-00033.safetensors",
355
- "layers.36.self_attn.norm_added_q.weight": "model-00017-of-00033.safetensors",
356
- "layers.36.self_attn.to_add_out.weight": "model-00017-of-00033.safetensors",
357
- "layers.37.input_layernorm_moe_gen.weight": "model-00017-of-00033.safetensors",
358
- "layers.37.mlp_moe_gen.down_proj.weight": "model-00017-of-00033.safetensors",
359
- "layers.37.mlp_moe_gen.gate_proj.weight": "model-00017-of-00033.safetensors",
360
- "layers.37.mlp_moe_gen.up_proj.weight": "model-00017-of-00033.safetensors",
361
- "layers.37.post_attention_layernorm_moe_gen.weight": "model-00017-of-00033.safetensors",
362
- "layers.37.self_attn.add_k_proj.weight": "model-00017-of-00033.safetensors",
363
- "layers.37.self_attn.add_q_proj.weight": "model-00017-of-00033.safetensors",
364
- "layers.37.self_attn.add_v_proj.weight": "model-00017-of-00033.safetensors",
365
- "layers.37.self_attn.norm_added_k.weight": "model-00017-of-00033.safetensors",
366
- "layers.37.self_attn.norm_added_q.weight": "model-00017-of-00033.safetensors",
367
- "layers.37.self_attn.to_add_out.weight": "model-00017-of-00033.safetensors",
368
- "layers.38.input_layernorm_moe_gen.weight": "model-00017-of-00033.safetensors",
369
- "layers.38.mlp_moe_gen.down_proj.weight": "model-00018-of-00033.safetensors",
370
- "layers.38.mlp_moe_gen.gate_proj.weight": "model-00018-of-00033.safetensors",
371
- "layers.38.mlp_moe_gen.up_proj.weight": "model-00018-of-00033.safetensors",
372
- "layers.38.post_attention_layernorm_moe_gen.weight": "model-00018-of-00033.safetensors",
373
- "layers.38.self_attn.add_k_proj.weight": "model-00018-of-00033.safetensors",
374
- "layers.38.self_attn.add_q_proj.weight": "model-00018-of-00033.safetensors",
375
- "layers.38.self_attn.add_v_proj.weight": "model-00018-of-00033.safetensors",
376
- "layers.38.self_attn.norm_added_k.weight": "model-00018-of-00033.safetensors",
377
- "layers.38.self_attn.norm_added_q.weight": "model-00018-of-00033.safetensors",
378
- "layers.38.self_attn.to_add_out.weight": "model-00018-of-00033.safetensors",
379
- "layers.39.input_layernorm_moe_gen.weight": "model-00018-of-00033.safetensors",
380
- "layers.39.mlp_moe_gen.down_proj.weight": "model-00018-of-00033.safetensors",
381
- "layers.39.mlp_moe_gen.gate_proj.weight": "model-00018-of-00033.safetensors",
382
- "layers.39.mlp_moe_gen.up_proj.weight": "model-00018-of-00033.safetensors",
383
- "layers.39.post_attention_layernorm_moe_gen.weight": "model-00018-of-00033.safetensors",
384
- "layers.39.self_attn.add_k_proj.weight": "model-00018-of-00033.safetensors",
385
- "layers.39.self_attn.add_q_proj.weight": "model-00018-of-00033.safetensors",
386
- "layers.39.self_attn.add_v_proj.weight": "model-00018-of-00033.safetensors",
387
- "layers.39.self_attn.norm_added_k.weight": "model-00018-of-00033.safetensors",
388
- "layers.39.self_attn.norm_added_q.weight": "model-00018-of-00033.safetensors",
389
- "layers.39.self_attn.to_add_out.weight": "model-00018-of-00033.safetensors",
390
- "layers.4.input_layernorm_moe_gen.weight": "model-00019-of-00033.safetensors",
391
- "layers.4.mlp_moe_gen.down_proj.weight": "model-00019-of-00033.safetensors",
392
- "layers.4.mlp_moe_gen.gate_proj.weight": "model-00019-of-00033.safetensors",
393
- "layers.4.mlp_moe_gen.up_proj.weight": "model-00020-of-00033.safetensors",
394
- "layers.4.post_attention_layernorm_moe_gen.weight": "model-00020-of-00033.safetensors",
395
- "layers.4.self_attn.add_k_proj.weight": "model-00003-of-00033.safetensors",
396
- "layers.4.self_attn.add_q_proj.weight": "model-00003-of-00033.safetensors",
397
- "layers.4.self_attn.add_v_proj.weight": "model-00003-of-00033.safetensors",
398
- "layers.4.self_attn.norm_added_k.weight": "model-00003-of-00033.safetensors",
399
- "layers.4.self_attn.norm_added_q.weight": "model-00003-of-00033.safetensors",
400
- "layers.4.self_attn.to_add_out.weight": "model-00003-of-00033.safetensors",
401
- "layers.40.input_layernorm_moe_gen.weight": "model-00018-of-00033.safetensors",
402
- "layers.40.mlp_moe_gen.down_proj.weight": "model-00019-of-00033.safetensors",
403
- "layers.40.mlp_moe_gen.gate_proj.weight": "model-00019-of-00033.safetensors",
404
- "layers.40.mlp_moe_gen.up_proj.weight": "model-00019-of-00033.safetensors",
405
- "layers.40.post_attention_layernorm_moe_gen.weight": "model-00019-of-00033.safetensors",
406
- "layers.40.self_attn.add_k_proj.weight": "model-00019-of-00033.safetensors",
407
- "layers.40.self_attn.add_q_proj.weight": "model-00019-of-00033.safetensors",
408
- "layers.40.self_attn.add_v_proj.weight": "model-00019-of-00033.safetensors",
409
- "layers.40.self_attn.norm_added_k.weight": "model-00019-of-00033.safetensors",
410
- "layers.40.self_attn.norm_added_q.weight": "model-00019-of-00033.safetensors",
411
- "layers.40.self_attn.to_add_out.weight": "model-00019-of-00033.safetensors",
412
- "layers.41.input_layernorm_moe_gen.weight": "model-00020-of-00033.safetensors",
413
- "layers.41.mlp_moe_gen.down_proj.weight": "model-00020-of-00033.safetensors",
414
- "layers.41.mlp_moe_gen.gate_proj.weight": "model-00019-of-00033.safetensors",
415
- "layers.41.mlp_moe_gen.up_proj.weight": "model-00021-of-00033.safetensors",
416
- "layers.41.post_attention_layernorm_moe_gen.weight": "model-00021-of-00033.safetensors",
417
- "layers.41.self_attn.add_k_proj.weight": "model-00019-of-00033.safetensors",
418
- "layers.41.self_attn.add_q_proj.weight": "model-00019-of-00033.safetensors",
419
- "layers.41.self_attn.add_v_proj.weight": "model-00019-of-00033.safetensors",
420
- "layers.41.self_attn.norm_added_k.weight": "model-00019-of-00033.safetensors",
421
- "layers.41.self_attn.norm_added_q.weight": "model-00019-of-00033.safetensors",
422
- "layers.41.self_attn.to_add_out.weight": "model-00019-of-00033.safetensors",
423
- "layers.42.input_layernorm_moe_gen.weight": "model-00021-of-00033.safetensors",
424
- "layers.42.mlp_moe_gen.down_proj.weight": "model-00021-of-00033.safetensors",
425
- "layers.42.mlp_moe_gen.gate_proj.weight": "model-00021-of-00033.safetensors",
426
- "layers.42.mlp_moe_gen.up_proj.weight": "model-00021-of-00033.safetensors",
427
- "layers.42.post_attention_layernorm_moe_gen.weight": "model-00021-of-00033.safetensors",
428
- "layers.42.self_attn.add_k_proj.weight": "model-00021-of-00033.safetensors",
429
- "layers.42.self_attn.add_q_proj.weight": "model-00021-of-00033.safetensors",
430
- "layers.42.self_attn.add_v_proj.weight": "model-00021-of-00033.safetensors",
431
- "layers.42.self_attn.norm_added_k.weight": "model-00021-of-00033.safetensors",
432
- "layers.42.self_attn.norm_added_q.weight": "model-00021-of-00033.safetensors",
433
- "layers.42.self_attn.to_add_out.weight": "model-00021-of-00033.safetensors",
434
- "layers.43.input_layernorm_moe_gen.weight": "model-00021-of-00033.safetensors",
435
- "layers.43.mlp_moe_gen.down_proj.weight": "model-00021-of-00033.safetensors",
436
- "layers.43.mlp_moe_gen.gate_proj.weight": "model-00021-of-00033.safetensors",
437
- "layers.43.mlp_moe_gen.up_proj.weight": "model-00022-of-00033.safetensors",
438
- "layers.43.post_attention_layernorm_moe_gen.weight": "model-00022-of-00033.safetensors",
439
- "layers.43.self_attn.add_k_proj.weight": "model-00022-of-00033.safetensors",
440
- "layers.43.self_attn.add_q_proj.weight": "model-00022-of-00033.safetensors",
441
- "layers.43.self_attn.add_v_proj.weight": "model-00022-of-00033.safetensors",
442
- "layers.43.self_attn.norm_added_k.weight": "model-00022-of-00033.safetensors",
443
- "layers.43.self_attn.norm_added_q.weight": "model-00022-of-00033.safetensors",
444
- "layers.43.self_attn.to_add_out.weight": "model-00022-of-00033.safetensors",
445
- "layers.44.input_layernorm_moe_gen.weight": "model-00022-of-00033.safetensors",
446
- "layers.44.mlp_moe_gen.down_proj.weight": "model-00022-of-00033.safetensors",
447
- "layers.44.mlp_moe_gen.gate_proj.weight": "model-00022-of-00033.safetensors",
448
- "layers.44.mlp_moe_gen.up_proj.weight": "model-00022-of-00033.safetensors",
449
- "layers.44.post_attention_layernorm_moe_gen.weight": "model-00022-of-00033.safetensors",
450
- "layers.44.self_attn.add_k_proj.weight": "model-00022-of-00033.safetensors",
451
- "layers.44.self_attn.add_q_proj.weight": "model-00022-of-00033.safetensors",
452
- "layers.44.self_attn.add_v_proj.weight": "model-00022-of-00033.safetensors",
453
- "layers.44.self_attn.norm_added_k.weight": "model-00022-of-00033.safetensors",
454
- "layers.44.self_attn.norm_added_q.weight": "model-00022-of-00033.safetensors",
455
- "layers.44.self_attn.to_add_out.weight": "model-00022-of-00033.safetensors",
456
- "layers.45.input_layernorm_moe_gen.weight": "model-00022-of-00033.safetensors",
457
- "layers.45.mlp_moe_gen.down_proj.weight": "model-00022-of-00033.safetensors",
458
- "layers.45.mlp_moe_gen.gate_proj.weight": "model-00022-of-00033.safetensors",
459
- "layers.45.mlp_moe_gen.up_proj.weight": "model-00023-of-00033.safetensors",
460
- "layers.45.post_attention_layernorm_moe_gen.weight": "model-00023-of-00033.safetensors",
461
- "layers.45.self_attn.add_k_proj.weight": "model-00023-of-00033.safetensors",
462
- "layers.45.self_attn.add_q_proj.weight": "model-00023-of-00033.safetensors",
463
- "layers.45.self_attn.add_v_proj.weight": "model-00023-of-00033.safetensors",
464
- "layers.45.self_attn.norm_added_k.weight": "model-00023-of-00033.safetensors",
465
- "layers.45.self_attn.norm_added_q.weight": "model-00023-of-00033.safetensors",
466
- "layers.45.self_attn.to_add_out.weight": "model-00023-of-00033.safetensors",
467
- "layers.46.input_layernorm_moe_gen.weight": "model-00023-of-00033.safetensors",
468
- "layers.46.mlp_moe_gen.down_proj.weight": "model-00023-of-00033.safetensors",
469
- "layers.46.mlp_moe_gen.gate_proj.weight": "model-00023-of-00033.safetensors",
470
- "layers.46.mlp_moe_gen.up_proj.weight": "model-00023-of-00033.safetensors",
471
- "layers.46.post_attention_layernorm_moe_gen.weight": "model-00023-of-00033.safetensors",
472
- "layers.46.self_attn.add_k_proj.weight": "model-00023-of-00033.safetensors",
473
- "layers.46.self_attn.add_q_proj.weight": "model-00023-of-00033.safetensors",
474
- "layers.46.self_attn.add_v_proj.weight": "model-00023-of-00033.safetensors",
475
- "layers.46.self_attn.norm_added_k.weight": "model-00023-of-00033.safetensors",
476
- "layers.46.self_attn.norm_added_q.weight": "model-00023-of-00033.safetensors",
477
- "layers.46.self_attn.to_add_out.weight": "model-00023-of-00033.safetensors",
478
- "layers.47.input_layernorm_moe_gen.weight": "model-00023-of-00033.safetensors",
479
- "layers.47.mlp_moe_gen.down_proj.weight": "model-00023-of-00033.safetensors",
480
- "layers.47.mlp_moe_gen.gate_proj.weight": "model-00023-of-00033.safetensors",
481
- "layers.47.mlp_moe_gen.up_proj.weight": "model-00024-of-00033.safetensors",
482
- "layers.47.post_attention_layernorm_moe_gen.weight": "model-00024-of-00033.safetensors",
483
- "layers.47.self_attn.add_k_proj.weight": "model-00024-of-00033.safetensors",
484
- "layers.47.self_attn.add_q_proj.weight": "model-00024-of-00033.safetensors",
485
- "layers.47.self_attn.add_v_proj.weight": "model-00024-of-00033.safetensors",
486
- "layers.47.self_attn.norm_added_k.weight": "model-00024-of-00033.safetensors",
487
- "layers.47.self_attn.norm_added_q.weight": "model-00024-of-00033.safetensors",
488
- "layers.47.self_attn.to_add_out.weight": "model-00024-of-00033.safetensors",
489
- "layers.48.input_layernorm_moe_gen.weight": "model-00024-of-00033.safetensors",
490
- "layers.48.mlp_moe_gen.down_proj.weight": "model-00024-of-00033.safetensors",
491
- "layers.48.mlp_moe_gen.gate_proj.weight": "model-00024-of-00033.safetensors",
492
- "layers.48.mlp_moe_gen.up_proj.weight": "model-00024-of-00033.safetensors",
493
- "layers.48.post_attention_layernorm_moe_gen.weight": "model-00024-of-00033.safetensors",
494
- "layers.48.self_attn.add_k_proj.weight": "model-00024-of-00033.safetensors",
495
- "layers.48.self_attn.add_q_proj.weight": "model-00024-of-00033.safetensors",
496
- "layers.48.self_attn.add_v_proj.weight": "model-00024-of-00033.safetensors",
497
- "layers.48.self_attn.norm_added_k.weight": "model-00024-of-00033.safetensors",
498
- "layers.48.self_attn.norm_added_q.weight": "model-00024-of-00033.safetensors",
499
- "layers.48.self_attn.to_add_out.weight": "model-00024-of-00033.safetensors",
500
- "layers.49.input_layernorm_moe_gen.weight": "model-00024-of-00033.safetensors",
501
- "layers.49.mlp_moe_gen.down_proj.weight": "model-00024-of-00033.safetensors",
502
- "layers.49.mlp_moe_gen.gate_proj.weight": "model-00025-of-00033.safetensors",
503
- "layers.49.mlp_moe_gen.up_proj.weight": "model-00025-of-00033.safetensors",
504
- "layers.49.post_attention_layernorm_moe_gen.weight": "model-00025-of-00033.safetensors",
505
- "layers.49.self_attn.add_k_proj.weight": "model-00024-of-00033.safetensors",
506
- "layers.49.self_attn.add_q_proj.weight": "model-00024-of-00033.safetensors",
507
- "layers.49.self_attn.add_v_proj.weight": "model-00024-of-00033.safetensors",
508
- "layers.49.self_attn.norm_added_k.weight": "model-00024-of-00033.safetensors",
509
- "layers.49.self_attn.norm_added_q.weight": "model-00024-of-00033.safetensors",
510
- "layers.49.self_attn.to_add_out.weight": "model-00024-of-00033.safetensors",
511
- "layers.5.input_layernorm_moe_gen.weight": "model-00020-of-00033.safetensors",
512
- "layers.5.mlp_moe_gen.down_proj.weight": "model-00020-of-00033.safetensors",
513
- "layers.5.mlp_moe_gen.gate_proj.weight": "model-00020-of-00033.safetensors",
514
- "layers.5.mlp_moe_gen.up_proj.weight": "model-00020-of-00033.safetensors",
515
- "layers.5.post_attention_layernorm_moe_gen.weight": "model-00020-of-00033.safetensors",
516
- "layers.5.self_attn.add_k_proj.weight": "model-00020-of-00033.safetensors",
517
- "layers.5.self_attn.add_q_proj.weight": "model-00020-of-00033.safetensors",
518
- "layers.5.self_attn.add_v_proj.weight": "model-00020-of-00033.safetensors",
519
- "layers.5.self_attn.norm_added_k.weight": "model-00020-of-00033.safetensors",
520
- "layers.5.self_attn.norm_added_q.weight": "model-00020-of-00033.safetensors",
521
- "layers.5.self_attn.to_add_out.weight": "model-00020-of-00033.safetensors",
522
- "layers.50.input_layernorm_moe_gen.weight": "model-00025-of-00033.safetensors",
523
- "layers.50.mlp_moe_gen.down_proj.weight": "model-00025-of-00033.safetensors",
524
- "layers.50.mlp_moe_gen.gate_proj.weight": "model-00025-of-00033.safetensors",
525
- "layers.50.mlp_moe_gen.up_proj.weight": "model-00025-of-00033.safetensors",
526
- "layers.50.post_attention_layernorm_moe_gen.weight": "model-00025-of-00033.safetensors",
527
- "layers.50.self_attn.add_k_proj.weight": "model-00025-of-00033.safetensors",
528
- "layers.50.self_attn.add_q_proj.weight": "model-00025-of-00033.safetensors",
529
- "layers.50.self_attn.add_v_proj.weight": "model-00025-of-00033.safetensors",
530
- "layers.50.self_attn.norm_added_k.weight": "model-00025-of-00033.safetensors",
531
- "layers.50.self_attn.norm_added_q.weight": "model-00025-of-00033.safetensors",
532
- "layers.50.self_attn.to_add_out.weight": "model-00025-of-00033.safetensors",
533
- "layers.51.input_layernorm_moe_gen.weight": "model-00025-of-00033.safetensors",
534
- "layers.51.mlp_moe_gen.down_proj.weight": "model-00026-of-00033.safetensors",
535
- "layers.51.mlp_moe_gen.gate_proj.weight": "model-00025-of-00033.safetensors",
536
- "layers.51.mlp_moe_gen.up_proj.weight": "model-00026-of-00033.safetensors",
537
- "layers.51.post_attention_layernorm_moe_gen.weight": "model-00026-of-00033.safetensors",
538
- "layers.51.self_attn.add_k_proj.weight": "model-00025-of-00033.safetensors",
539
- "layers.51.self_attn.add_q_proj.weight": "model-00025-of-00033.safetensors",
540
- "layers.51.self_attn.add_v_proj.weight": "model-00025-of-00033.safetensors",
541
- "layers.51.self_attn.norm_added_k.weight": "model-00025-of-00033.safetensors",
542
- "layers.51.self_attn.norm_added_q.weight": "model-00025-of-00033.safetensors",
543
- "layers.51.self_attn.to_add_out.weight": "model-00025-of-00033.safetensors",
544
- "layers.52.input_layernorm_moe_gen.weight": "model-00026-of-00033.safetensors",
545
- "layers.52.mlp_moe_gen.down_proj.weight": "model-00026-of-00033.safetensors",
546
- "layers.52.mlp_moe_gen.gate_proj.weight": "model-00026-of-00033.safetensors",
547
- "layers.52.mlp_moe_gen.up_proj.weight": "model-00026-of-00033.safetensors",
548
- "layers.52.post_attention_layernorm_moe_gen.weight": "model-00026-of-00033.safetensors",
549
- "layers.52.self_attn.add_k_proj.weight": "model-00026-of-00033.safetensors",
550
- "layers.52.self_attn.add_q_proj.weight": "model-00026-of-00033.safetensors",
551
- "layers.52.self_attn.add_v_proj.weight": "model-00026-of-00033.safetensors",
552
- "layers.52.self_attn.norm_added_k.weight": "model-00026-of-00033.safetensors",
553
- "layers.52.self_attn.norm_added_q.weight": "model-00026-of-00033.safetensors",
554
- "layers.52.self_attn.to_add_out.weight": "model-00026-of-00033.safetensors",
555
- "layers.53.input_layernorm_moe_gen.weight": "model-00026-of-00033.safetensors",
556
- "layers.53.mlp_moe_gen.down_proj.weight": "model-00026-of-00033.safetensors",
557
- "layers.53.mlp_moe_gen.gate_proj.weight": "model-00027-of-00033.safetensors",
558
- "layers.53.mlp_moe_gen.up_proj.weight": "model-00027-of-00033.safetensors",
559
- "layers.53.post_attention_layernorm_moe_gen.weight": "model-00027-of-00033.safetensors",
560
- "layers.53.self_attn.add_k_proj.weight": "model-00027-of-00033.safetensors",
561
- "layers.53.self_attn.add_q_proj.weight": "model-00027-of-00033.safetensors",
562
- "layers.53.self_attn.add_v_proj.weight": "model-00027-of-00033.safetensors",
563
- "layers.53.self_attn.norm_added_k.weight": "model-00027-of-00033.safetensors",
564
- "layers.53.self_attn.norm_added_q.weight": "model-00027-of-00033.safetensors",
565
- "layers.53.self_attn.to_add_out.weight": "model-00027-of-00033.safetensors",
566
- "layers.54.input_layernorm_moe_gen.weight": "model-00027-of-00033.safetensors",
567
- "layers.54.mlp_moe_gen.down_proj.weight": "model-00027-of-00033.safetensors",
568
- "layers.54.mlp_moe_gen.gate_proj.weight": "model-00027-of-00033.safetensors",
569
- "layers.54.mlp_moe_gen.up_proj.weight": "model-00027-of-00033.safetensors",
570
- "layers.54.post_attention_layernorm_moe_gen.weight": "model-00027-of-00033.safetensors",
571
- "layers.54.self_attn.add_k_proj.weight": "model-00027-of-00033.safetensors",
572
- "layers.54.self_attn.add_q_proj.weight": "model-00027-of-00033.safetensors",
573
- "layers.54.self_attn.add_v_proj.weight": "model-00027-of-00033.safetensors",
574
- "layers.54.self_attn.norm_added_k.weight": "model-00027-of-00033.safetensors",
575
- "layers.54.self_attn.norm_added_q.weight": "model-00027-of-00033.safetensors",
576
- "layers.54.self_attn.to_add_out.weight": "model-00027-of-00033.safetensors",
577
- "layers.55.input_layernorm_moe_gen.weight": "model-00027-of-00033.safetensors",
578
- "layers.55.mlp_moe_gen.down_proj.weight": "model-00027-of-00033.safetensors",
579
- "layers.55.mlp_moe_gen.gate_proj.weight": "model-00028-of-00033.safetensors",
580
- "layers.55.mlp_moe_gen.up_proj.weight": "model-00028-of-00033.safetensors",
581
- "layers.55.post_attention_layernorm_moe_gen.weight": "model-00028-of-00033.safetensors",
582
- "layers.55.self_attn.add_k_proj.weight": "model-00028-of-00033.safetensors",
583
- "layers.55.self_attn.add_q_proj.weight": "model-00028-of-00033.safetensors",
584
- "layers.55.self_attn.add_v_proj.weight": "model-00028-of-00033.safetensors",
585
- "layers.55.self_attn.norm_added_k.weight": "model-00028-of-00033.safetensors",
586
- "layers.55.self_attn.norm_added_q.weight": "model-00028-of-00033.safetensors",
587
- "layers.55.self_attn.to_add_out.weight": "model-00028-of-00033.safetensors",
588
- "layers.56.input_layernorm_moe_gen.weight": "model-00028-of-00033.safetensors",
589
- "layers.56.mlp_moe_gen.down_proj.weight": "model-00028-of-00033.safetensors",
590
- "layers.56.mlp_moe_gen.gate_proj.weight": "model-00028-of-00033.safetensors",
591
- "layers.56.mlp_moe_gen.up_proj.weight": "model-00028-of-00033.safetensors",
592
- "layers.56.post_attention_layernorm_moe_gen.weight": "model-00028-of-00033.safetensors",
593
- "layers.56.self_attn.add_k_proj.weight": "model-00028-of-00033.safetensors",
594
- "layers.56.self_attn.add_q_proj.weight": "model-00028-of-00033.safetensors",
595
- "layers.56.self_attn.add_v_proj.weight": "model-00028-of-00033.safetensors",
596
- "layers.56.self_attn.norm_added_k.weight": "model-00028-of-00033.safetensors",
597
- "layers.56.self_attn.norm_added_q.weight": "model-00028-of-00033.safetensors",
598
- "layers.56.self_attn.to_add_out.weight": "model-00028-of-00033.safetensors",
599
- "layers.57.input_layernorm_moe_gen.weight": "model-00028-of-00033.safetensors",
600
- "layers.57.mlp_moe_gen.down_proj.weight": "model-00028-of-00033.safetensors",
601
- "layers.57.mlp_moe_gen.gate_proj.weight": "model-00029-of-00033.safetensors",
602
- "layers.57.mlp_moe_gen.up_proj.weight": "model-00029-of-00033.safetensors",
603
- "layers.57.post_attention_layernorm_moe_gen.weight": "model-00029-of-00033.safetensors",
604
- "layers.57.self_attn.add_k_proj.weight": "model-00029-of-00033.safetensors",
605
- "layers.57.self_attn.add_q_proj.weight": "model-00029-of-00033.safetensors",
606
- "layers.57.self_attn.add_v_proj.weight": "model-00029-of-00033.safetensors",
607
- "layers.57.self_attn.norm_added_k.weight": "model-00029-of-00033.safetensors",
608
- "layers.57.self_attn.norm_added_q.weight": "model-00029-of-00033.safetensors",
609
- "layers.57.self_attn.to_add_out.weight": "model-00029-of-00033.safetensors",
610
- "layers.58.input_layernorm_moe_gen.weight": "model-00029-of-00033.safetensors",
611
- "layers.58.mlp_moe_gen.down_proj.weight": "model-00029-of-00033.safetensors",
612
- "layers.58.mlp_moe_gen.gate_proj.weight": "model-00029-of-00033.safetensors",
613
- "layers.58.mlp_moe_gen.up_proj.weight": "model-00029-of-00033.safetensors",
614
- "layers.58.post_attention_layernorm_moe_gen.weight": "model-00029-of-00033.safetensors",
615
- "layers.58.self_attn.add_k_proj.weight": "model-00029-of-00033.safetensors",
616
- "layers.58.self_attn.add_q_proj.weight": "model-00029-of-00033.safetensors",
617
- "layers.58.self_attn.add_v_proj.weight": "model-00029-of-00033.safetensors",
618
- "layers.58.self_attn.norm_added_k.weight": "model-00029-of-00033.safetensors",
619
- "layers.58.self_attn.norm_added_q.weight": "model-00029-of-00033.safetensors",
620
- "layers.58.self_attn.to_add_out.weight": "model-00029-of-00033.safetensors",
621
- "layers.59.input_layernorm_moe_gen.weight": "model-00029-of-00033.safetensors",
622
- "layers.59.mlp_moe_gen.down_proj.weight": "model-00030-of-00033.safetensors",
623
- "layers.59.mlp_moe_gen.gate_proj.weight": "model-00030-of-00033.safetensors",
624
- "layers.59.mlp_moe_gen.up_proj.weight": "model-00030-of-00033.safetensors",
625
- "layers.59.post_attention_layernorm_moe_gen.weight": "model-00030-of-00033.safetensors",
626
- "layers.59.self_attn.add_k_proj.weight": "model-00029-of-00033.safetensors",
627
- "layers.59.self_attn.add_q_proj.weight": "model-00029-of-00033.safetensors",
628
- "layers.59.self_attn.add_v_proj.weight": "model-00029-of-00033.safetensors",
629
- "layers.59.self_attn.norm_added_k.weight": "model-00029-of-00033.safetensors",
630
- "layers.59.self_attn.norm_added_q.weight": "model-00029-of-00033.safetensors",
631
- "layers.59.self_attn.to_add_out.weight": "model-00029-of-00033.safetensors",
632
- "layers.6.input_layernorm_moe_gen.weight": "model-00031-of-00033.safetensors",
633
- "layers.6.mlp_moe_gen.down_proj.weight": "model-00031-of-00033.safetensors",
634
- "layers.6.mlp_moe_gen.gate_proj.weight": "model-00020-of-00033.safetensors",
635
- "layers.6.mlp_moe_gen.up_proj.weight": "model-00031-of-00033.safetensors",
636
- "layers.6.post_attention_layernorm_moe_gen.weight": "model-00031-of-00033.safetensors",
637
- "layers.6.self_attn.add_k_proj.weight": "model-00020-of-00033.safetensors",
638
- "layers.6.self_attn.add_q_proj.weight": "model-00020-of-00033.safetensors",
639
- "layers.6.self_attn.add_v_proj.weight": "model-00020-of-00033.safetensors",
640
- "layers.6.self_attn.norm_added_k.weight": "model-00020-of-00033.safetensors",
641
- "layers.6.self_attn.norm_added_q.weight": "model-00020-of-00033.safetensors",
642
- "layers.6.self_attn.to_add_out.weight": "model-00020-of-00033.safetensors",
643
- "layers.60.input_layernorm_moe_gen.weight": "model-00030-of-00033.safetensors",
644
- "layers.60.mlp_moe_gen.down_proj.weight": "model-00030-of-00033.safetensors",
645
- "layers.60.mlp_moe_gen.gate_proj.weight": "model-00030-of-00033.safetensors",
646
- "layers.60.mlp_moe_gen.up_proj.weight": "model-00030-of-00033.safetensors",
647
- "layers.60.post_attention_layernorm_moe_gen.weight": "model-00030-of-00033.safetensors",
648
- "layers.60.self_attn.add_k_proj.weight": "model-00030-of-00033.safetensors",
649
- "layers.60.self_attn.add_q_proj.weight": "model-00030-of-00033.safetensors",
650
- "layers.60.self_attn.add_v_proj.weight": "model-00030-of-00033.safetensors",
651
- "layers.60.self_attn.norm_added_k.weight": "model-00030-of-00033.safetensors",
652
- "layers.60.self_attn.norm_added_q.weight": "model-00030-of-00033.safetensors",
653
- "layers.60.self_attn.to_add_out.weight": "model-00030-of-00033.safetensors",
654
- "layers.61.input_layernorm_moe_gen.weight": "model-00032-of-00033.safetensors",
655
- "layers.61.mlp_moe_gen.down_proj.weight": "model-00032-of-00033.safetensors",
656
- "layers.61.mlp_moe_gen.gate_proj.weight": "model-00031-of-00033.safetensors",
657
- "layers.61.mlp_moe_gen.up_proj.weight": "model-00032-of-00033.safetensors",
658
- "layers.61.post_attention_layernorm_moe_gen.weight": "model-00032-of-00033.safetensors",
659
- "layers.61.self_attn.add_k_proj.weight": "model-00031-of-00033.safetensors",
660
- "layers.61.self_attn.add_q_proj.weight": "model-00031-of-00033.safetensors",
661
- "layers.61.self_attn.add_v_proj.weight": "model-00031-of-00033.safetensors",
662
- "layers.61.self_attn.norm_added_k.weight": "model-00031-of-00033.safetensors",
663
- "layers.61.self_attn.norm_added_q.weight": "model-00031-of-00033.safetensors",
664
- "layers.61.self_attn.to_add_out.weight": "model-00031-of-00033.safetensors",
665
- "layers.62.input_layernorm_moe_gen.weight": "model-00032-of-00033.safetensors",
666
- "layers.62.mlp_moe_gen.down_proj.weight": "model-00032-of-00033.safetensors",
667
- "layers.62.mlp_moe_gen.gate_proj.weight": "model-00033-of-00033.safetensors",
668
- "layers.62.mlp_moe_gen.up_proj.weight": "model-00033-of-00033.safetensors",
669
- "layers.62.post_attention_layernorm_moe_gen.weight": "model-00033-of-00033.safetensors",
670
- "layers.62.self_attn.add_k_proj.weight": "model-00033-of-00033.safetensors",
671
- "layers.62.self_attn.add_q_proj.weight": "model-00033-of-00033.safetensors",
672
- "layers.62.self_attn.add_v_proj.weight": "model-00033-of-00033.safetensors",
673
- "layers.62.self_attn.norm_added_k.weight": "model-00033-of-00033.safetensors",
674
- "layers.62.self_attn.norm_added_q.weight": "model-00033-of-00033.safetensors",
675
- "layers.62.self_attn.to_add_out.weight": "model-00033-of-00033.safetensors",
676
- "layers.63.input_layernorm_moe_gen.weight": "model-00033-of-00033.safetensors",
677
- "layers.63.mlp_moe_gen.down_proj.weight": "model-00033-of-00033.safetensors",
678
- "layers.63.mlp_moe_gen.gate_proj.weight": "model-00033-of-00033.safetensors",
679
- "layers.63.mlp_moe_gen.up_proj.weight": "model-00033-of-00033.safetensors",
680
- "layers.63.post_attention_layernorm_moe_gen.weight": "model-00033-of-00033.safetensors",
681
- "layers.63.self_attn.add_k_proj.weight": "model-00033-of-00033.safetensors",
682
- "layers.63.self_attn.add_q_proj.weight": "model-00033-of-00033.safetensors",
683
- "layers.63.self_attn.add_v_proj.weight": "model-00033-of-00033.safetensors",
684
- "layers.63.self_attn.norm_added_k.weight": "model-00033-of-00033.safetensors",
685
- "layers.63.self_attn.norm_added_q.weight": "model-00033-of-00033.safetensors",
686
- "layers.63.self_attn.to_add_out.weight": "model-00033-of-00033.safetensors",
687
- "layers.7.input_layernorm_moe_gen.weight": "model-00031-of-00033.safetensors",
688
- "layers.7.mlp_moe_gen.down_proj.weight": "model-00031-of-00033.safetensors",
689
- "layers.7.mlp_moe_gen.gate_proj.weight": "model-00031-of-00033.safetensors",
690
- "layers.7.mlp_moe_gen.up_proj.weight": "model-00031-of-00033.safetensors",
691
- "layers.7.post_attention_layernorm_moe_gen.weight": "model-00031-of-00033.safetensors",
692
- "layers.7.self_attn.add_k_proj.weight": "model-00031-of-00033.safetensors",
693
- "layers.7.self_attn.add_q_proj.weight": "model-00031-of-00033.safetensors",
694
- "layers.7.self_attn.add_v_proj.weight": "model-00031-of-00033.safetensors",
695
- "layers.7.self_attn.norm_added_k.weight": "model-00031-of-00033.safetensors",
696
- "layers.7.self_attn.norm_added_q.weight": "model-00031-of-00033.safetensors",
697
- "layers.7.self_attn.to_add_out.weight": "model-00031-of-00033.safetensors",
698
- "layers.8.input_layernorm_moe_gen.weight": "model-00031-of-00033.safetensors",
699
- "layers.8.mlp_moe_gen.down_proj.weight": "model-00032-of-00033.safetensors",
700
- "layers.8.mlp_moe_gen.gate_proj.weight": "model-00032-of-00033.safetensors",
701
- "layers.8.mlp_moe_gen.up_proj.weight": "model-00032-of-00033.safetensors",
702
- "layers.8.post_attention_layernorm_moe_gen.weight": "model-00032-of-00033.safetensors",
703
- "layers.8.self_attn.add_k_proj.weight": "model-00032-of-00033.safetensors",
704
- "layers.8.self_attn.add_q_proj.weight": "model-00032-of-00033.safetensors",
705
- "layers.8.self_attn.add_v_proj.weight": "model-00032-of-00033.safetensors",
706
- "layers.8.self_attn.norm_added_k.weight": "model-00032-of-00033.safetensors",
707
- "layers.8.self_attn.norm_added_q.weight": "model-00032-of-00033.safetensors",
708
- "layers.8.self_attn.to_add_out.weight": "model-00032-of-00033.safetensors",
709
- "layers.9.input_layernorm_moe_gen.weight": "model-00004-of-00033.safetensors",
710
- "layers.9.mlp_moe_gen.down_proj.weight": "model-00004-of-00033.safetensors",
711
- "layers.9.mlp_moe_gen.gate_proj.weight": "model-00004-of-00033.safetensors",
712
- "layers.9.mlp_moe_gen.up_proj.weight": "model-00004-of-00033.safetensors",
713
- "layers.9.post_attention_layernorm_moe_gen.weight": "model-00004-of-00033.safetensors",
714
- "layers.9.self_attn.add_k_proj.weight": "model-00032-of-00033.safetensors",
715
- "layers.9.self_attn.add_q_proj.weight": "model-00032-of-00033.safetensors",
716
- "layers.9.self_attn.add_v_proj.weight": "model-00032-of-00033.safetensors",
717
- "layers.9.self_attn.norm_added_k.weight": "model-00032-of-00033.safetensors",
718
- "layers.9.self_attn.norm_added_q.weight": "model-00032-of-00033.safetensors",
719
- "layers.9.self_attn.to_add_out.weight": "model-00032-of-00033.safetensors",
720
- "norm_moe_gen.weight": "model-00033-of-00033.safetensors",
721
- "proj_in.bias": "model-00001-of-00033.safetensors",
722
- "proj_in.weight": "model-00001-of-00033.safetensors",
723
- "proj_out.bias": "model-00001-of-00033.safetensors",
724
- "proj_out.weight": "model-00001-of-00033.safetensors",
725
- "time_embedder.linear_1.bias": "model-00001-of-00033.safetensors",
726
- "time_embedder.linear_1.weight": "model-00001-of-00033.safetensors",
727
- "time_embedder.linear_2.bias": "model-00001-of-00033.safetensors",
728
- "time_embedder.linear_2.weight": "model-00001-of-00033.safetensors"
729
- }
730
- }