Hugging Face's logo

nvidia
/
Cosmos3-Nano-Transfer-Auto

Cosmos
Diffusers
Safetensors
cosmos3_omni
nvidia
cosmos3
omnimodel
Model card Files
xet
 Community
4
mbalaNV commited on
Commit
848b340
·
verified ·
1 Parent(s): ac871d0

Update config

Browse files
Files changed (5) hide show
  1. config.json +2 -0
  2. model.safetensors.index.json +382 -382
  3. model_index.json +2 -2
  4. modular_model_index.json +4 -4
  5. scheduler/scheduler_config.json +4 -4
config.json CHANGED
@@ -216,6 +216,8 @@
216
  "sensor_to_sensor_bounds": null
217
  }
218
  },
 
 
219
  "maskless_cross_view_band_keys": "other_views",
220
  "maskless_cross_view_band_radius": 0,
221
  "maskless_cross_view_include_frame_zero": false,
 
216
  "sensor_to_sensor_bounds": null
217
  }
218
  },
219
+ "maskless_cross_view_action_attends_action": false,
220
+ "maskless_cross_view_attends_action": false,
221
  "maskless_cross_view_band_keys": "other_views",
222
  "maskless_cross_view_band_radius": 0,
223
  "maskless_cross_view_include_frame_zero": false,
model.safetensors.index.json CHANGED
@@ -3,234 +3,159 @@
3
  "total_size": 30314648192
4
  },
5
  "weight_map": {
6
- "embed_tokens.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
7
- "layers.0.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
8
- "layers.0.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
9
- "layers.0.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
10
- "layers.0.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
11
- "layers.0.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
12
- "layers.0.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
13
- "layers.0.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
14
- "layers.0.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
15
- "layers.0.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
16
- "layers.0.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
17
- "layers.0.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
18
- "layers.0.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
19
- "layers.0.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
20
- "layers.0.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
21
- "layers.0.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
22
- "layers.0.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
23
- "layers.0.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
24
- "layers.0.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
25
- "layers.0.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
26
- "layers.0.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
27
- "layers.0.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
28
- "layers.0.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
29
- "layers.1.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
30
- "layers.1.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
31
- "layers.1.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
32
- "layers.1.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
33
- "layers.1.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
34
- "layers.1.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
35
- "layers.1.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
36
- "layers.1.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
37
- "layers.1.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
38
- "layers.1.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
39
- "layers.1.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
40
- "layers.1.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
41
- "layers.1.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
42
- "layers.1.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
43
- "layers.1.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
44
- "layers.1.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
45
- "layers.1.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
46
- "layers.1.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
47
- "layers.1.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
48
- "layers.1.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
49
- "layers.1.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
50
- "layers.1.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
51
- "layers.10.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
52
- "layers.10.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
53
- "layers.10.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
54
- "layers.10.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
55
- "layers.10.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
56
- "layers.10.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
57
- "layers.10.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
58
- "layers.10.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
59
- "layers.10.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
60
- "layers.10.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
61
- "layers.10.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
62
- "layers.10.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
63
- "layers.10.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
64
- "layers.10.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
65
- "layers.10.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
66
- "layers.10.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
67
- "layers.10.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
68
- "layers.10.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
69
- "layers.10.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
70
- "layers.10.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
71
- "layers.10.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
72
- "layers.10.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
73
- "layers.11.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
74
- "layers.11.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
75
- "layers.11.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
76
- "layers.11.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
77
- "layers.11.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
78
- "layers.11.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
79
- "layers.11.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
80
- "lm_head.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
81
- "layers.18.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
82
- "layers.18.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
83
- "layers.18.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
84
- "layers.18.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
85
- "layers.18.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
86
- "layers.18.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
87
- "layers.18.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
88
- "layers.18.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
89
- "layers.18.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
90
- "layers.18.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
91
- "layers.18.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
92
- "layers.18.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
93
- "layers.18.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
94
- "layers.18.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
95
- "layers.18.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
96
- "layers.18.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
97
- "layers.19.input_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
98
- "layers.19.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
99
- "layers.19.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
100
- "layers.19.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
101
- "layers.19.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
102
- "layers.19.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
103
- "layers.19.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
104
- "layers.19.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
105
- "layers.19.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
106
- "layers.19.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
107
- "layers.19.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
108
- "layers.19.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
109
- "layers.19.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
110
- "layers.19.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
111
- "layers.19.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
112
- "layers.19.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
113
- "layers.19.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
114
- "layers.19.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
115
- "layers.19.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
116
- "layers.19.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
117
- "layers.19.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
118
- "layers.19.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
119
- "layers.2.input_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
120
- "layers.2.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
121
- "layers.2.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
122
- "layers.2.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
123
- "layers.2.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
124
- "layers.2.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
125
- "layers.2.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
126
- "layers.2.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
127
- "layers.2.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
128
- "layers.2.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
129
- "layers.2.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
130
- "layers.2.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
131
- "layers.2.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
132
- "layers.2.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
133
- "layers.2.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
134
- "layers.2.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
135
- "layers.2.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
136
- "layers.2.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
137
- "layers.2.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
138
- "layers.2.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
139
- "layers.2.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
140
- "layers.2.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
141
- "layers.20.input_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
142
- "layers.20.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
143
- "layers.20.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
144
- "layers.20.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
145
- "layers.20.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
146
- "layers.20.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
147
- "layers.20.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
148
- "layers.20.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
149
- "layers.20.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
150
- "layers.20.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
151
- "layers.20.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
152
- "layers.20.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
153
- "layers.20.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
154
- "layers.20.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
155
- "layers.20.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
156
- "layers.20.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
157
- "layers.20.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
158
- "layers.20.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
159
- "layers.20.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
160
- "layers.20.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
161
- "layers.20.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
162
- "layers.20.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
163
- "layers.21.input_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
164
- "layers.21.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
165
- "layers.21.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
166
- "layers.21.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
167
- "layers.21.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
168
- "layers.21.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
169
- "layers.21.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
170
- "layers.21.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
171
- "layers.21.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
172
- "layers.21.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
173
- "layers.21.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
174
- "layers.21.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
175
- "layers.21.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
176
- "layers.21.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
177
- "layers.21.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
178
- "layers.21.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
179
- "layers.21.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
180
- "layers.21.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
181
- "layers.21.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
182
- "layers.21.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
183
- "layers.21.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
184
- "layers.21.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
185
- "layers.22.input_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
186
- "layers.22.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
187
- "layers.22.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
188
- "layers.22.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
189
- "layers.22.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
190
- "layers.22.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
191
- "layers.22.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
192
- "layers.22.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
193
- "layers.22.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
194
- "layers.22.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
195
- "layers.22.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
196
- "layers.22.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
197
- "layers.22.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
198
- "layers.22.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
199
- "layers.22.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
200
- "layers.22.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
201
- "layers.22.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
202
- "layers.22.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
203
- "layers.22.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
204
- "layers.22.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
205
- "layers.22.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
206
- "layers.22.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
207
- "layers.23.input_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
208
- "layers.23.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
209
- "layers.23.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
210
- "layers.23.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
211
- "layers.23.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
212
- "layers.23.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
213
- "layers.23.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
214
- "layers.23.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
215
- "layers.23.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
216
- "layers.23.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
217
- "layers.23.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
218
- "layers.23.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
219
- "layers.23.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
220
- "layers.23.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
221
- "layers.23.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
222
- "layers.23.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
223
- "layers.23.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
224
- "layers.23.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
225
- "layers.23.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
226
- "layers.23.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
227
- "layers.23.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
228
- "layers.23.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
229
- "layers.24.input_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
230
- "layers.24.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
231
- "layers.24.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
232
- "layers.24.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
233
- "layers.24.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
234
  "layers.30.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
235
  "layers.30.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
236
  "layers.30.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
@@ -506,6 +431,234 @@
506
  "time_embedder.linear_1.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
507
  "time_embedder.linear_2.bias": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
508
  "time_embedder.linear_2.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
509
  "layers.24.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
510
  "layers.24.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
511
  "layers.24.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
@@ -658,159 +811,6 @@
658
  "layers.30.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
659
  "layers.30.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
660
  "layers.30.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
661
- "layers.30.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
662
- "layers.11.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
663
- "layers.11.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
664
- "layers.11.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
665
- "layers.11.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
666
- "layers.11.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
667
- "layers.11.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
668
- "layers.11.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
669
- "layers.11.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
670
- "layers.11.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
671
- "layers.11.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
672
- "layers.11.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
673
- "layers.11.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
674
- "layers.11.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
675
- "layers.11.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
676
- "layers.11.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
677
- "layers.12.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
678
- "layers.12.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
679
- "layers.12.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
680
- "layers.12.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
681
- "layers.12.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
682
- "layers.12.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
683
- "layers.12.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
684
- "layers.12.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
685
- "layers.12.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
686
- "layers.12.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
687
- "layers.12.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
688
- "layers.12.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
689
- "layers.12.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
690
- "layers.12.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
691
- "layers.12.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
692
- "layers.12.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
693
- "layers.12.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
694
- "layers.12.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
695
- "layers.12.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
696
- "layers.12.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
697
- "layers.12.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
698
- "layers.12.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
699
- "layers.13.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
700
- "layers.13.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
701
- "layers.13.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
702
- "layers.13.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
703
- "layers.13.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
704
- "layers.13.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
705
- "layers.13.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
706
- "layers.13.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
707
- "layers.13.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
708
- "layers.13.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
709
- "layers.13.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
710
- "layers.13.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
711
- "layers.13.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
712
- "layers.13.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
713
- "layers.13.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
714
- "layers.13.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
715
- "layers.13.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
716
- "layers.13.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
717
- "layers.13.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
718
- "layers.13.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
719
- "layers.13.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
720
- "layers.13.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
721
- "layers.14.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
722
- "layers.14.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
723
- "layers.14.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
724
- "layers.14.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
725
- "layers.14.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
726
- "layers.14.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
727
- "layers.14.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
728
- "layers.14.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
729
- "layers.14.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
730
- "layers.14.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
731
- "layers.14.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
732
- "layers.14.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
733
- "layers.14.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
734
- "layers.14.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
735
- "layers.14.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
736
- "layers.14.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
737
- "layers.14.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
738
- "layers.14.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
739
- "layers.14.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
740
- "layers.14.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
741
- "layers.14.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
742
- "layers.14.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
743
- "layers.15.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
744
- "layers.15.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
745
- "layers.15.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
746
- "layers.15.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
747
- "layers.15.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
748
- "layers.15.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
749
- "layers.15.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
750
- "layers.15.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
751
- "layers.15.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
752
- "layers.15.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
753
- "layers.15.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
754
- "layers.15.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
755
- "layers.15.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
756
- "layers.15.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
757
- "layers.15.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
758
- "layers.15.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
759
- "layers.15.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
760
- "layers.15.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
761
- "layers.15.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
762
- "layers.15.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
763
- "layers.15.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
764
- "layers.15.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
765
- "layers.16.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
766
- "layers.16.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
767
- "layers.16.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
768
- "layers.16.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
769
- "layers.16.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
770
- "layers.16.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
771
- "layers.16.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
772
- "layers.16.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
773
- "layers.16.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
774
- "layers.16.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
775
- "layers.16.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
776
- "layers.16.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
777
- "layers.16.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
778
- "layers.16.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
779
- "layers.16.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
780
- "layers.16.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
781
- "layers.16.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
782
- "layers.16.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
783
- "layers.16.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
784
- "layers.16.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
785
- "layers.16.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
786
- "layers.16.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
787
- "layers.17.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
788
- "layers.17.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
789
- "layers.17.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
790
- "layers.17.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
791
- "layers.17.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
792
- "layers.17.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
793
- "layers.17.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
794
- "layers.17.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
795
- "layers.17.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
796
- "layers.17.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
797
- "layers.17.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
798
- "layers.17.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
799
- "layers.17.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
800
- "layers.17.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
801
- "layers.17.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
802
- "layers.17.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
803
- "layers.17.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
804
- "layers.17.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
805
- "layers.17.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
806
- "layers.17.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
807
- "layers.17.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
808
- "layers.17.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
809
- "layers.18.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
810
- "layers.18.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
811
- "layers.18.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
812
- "layers.18.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
813
- "layers.18.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
814
- "layers.18.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors"
815
  }
816
  }
 
3
  "total_size": 30314648192
4
  },
5
  "weight_map": {
6
+ "layers.11.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
7
+ "layers.11.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
8
+ "layers.11.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
9
+ "layers.11.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
10
+ "layers.11.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
11
+ "layers.11.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
12
+ "layers.11.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
13
+ "layers.11.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
14
+ "layers.11.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
15
+ "layers.11.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
16
+ "layers.11.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
17
+ "layers.11.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
18
+ "layers.11.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
19
+ "layers.11.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
20
+ "layers.11.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
21
+ "layers.12.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
22
+ "layers.12.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
23
+ "layers.12.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
24
+ "layers.12.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
25
+ "layers.12.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
26
+ "layers.12.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
27
+ "layers.12.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
28
+ "layers.12.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
29
+ "layers.12.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
30
+ "layers.12.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
31
+ "layers.12.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
32
+ "layers.12.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
33
+ "layers.12.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
34
+ "layers.12.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
35
+ "layers.12.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
36
+ "layers.12.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
37
+ "layers.12.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
38
+ "layers.12.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
39
+ "layers.12.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
40
+ "layers.12.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
41
+ "layers.12.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
42
+ "layers.12.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
43
+ "layers.13.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
44
+ "layers.13.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
45
+ "layers.13.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
46
+ "layers.13.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
47
+ "layers.13.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
48
+ "layers.13.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
49
+ "layers.13.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
50
+ "layers.13.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
51
+ "layers.13.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
52
+ "layers.13.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
53
+ "layers.13.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
54
+ "layers.13.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
55
+ "layers.13.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
56
+ "layers.13.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
57
+ "layers.13.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
58
+ "layers.13.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
59
+ "layers.13.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
60
+ "layers.13.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
61
+ "layers.13.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
62
+ "layers.13.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
63
+ "layers.13.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
64
+ "layers.13.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
65
+ "layers.14.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
66
+ "layers.14.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
67
+ "layers.14.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
68
+ "layers.14.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
69
+ "layers.14.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
70
+ "layers.14.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
71
+ "layers.14.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
72
+ "layers.14.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
73
+ "layers.14.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
74
+ "layers.14.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
75
+ "layers.14.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
76
+ "layers.14.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
77
+ "layers.14.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
78
+ "layers.14.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
79
+ "layers.14.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
80
+ "layers.14.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
81
+ "layers.14.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
82
+ "layers.14.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
83
+ "layers.14.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
84
+ "layers.14.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
85
+ "layers.14.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
86
+ "layers.14.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
87
+ "layers.15.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
88
+ "layers.15.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
89
+ "layers.15.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
90
+ "layers.15.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
91
+ "layers.15.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
92
+ "layers.15.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
93
+ "layers.15.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
94
+ "layers.15.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
95
+ "layers.15.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
96
+ "layers.15.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
97
+ "layers.15.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
98
+ "layers.15.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
99
+ "layers.15.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
100
+ "layers.15.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
101
+ "layers.15.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
102
+ "layers.15.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
103
+ "layers.15.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
104
+ "layers.15.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
105
+ "layers.15.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
106
+ "layers.15.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
107
+ "layers.15.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
108
+ "layers.15.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
109
+ "layers.16.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
110
+ "layers.16.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
111
+ "layers.16.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
112
+ "layers.16.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
113
+ "layers.16.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
114
+ "layers.16.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
115
+ "layers.16.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
116
+ "layers.16.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
117
+ "layers.16.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
118
+ "layers.16.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
119
+ "layers.16.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
120
+ "layers.16.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
121
+ "layers.16.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
122
+ "layers.16.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
123
+ "layers.16.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
124
+ "layers.16.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
125
+ "layers.16.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
126
+ "layers.16.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
127
+ "layers.16.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
128
+ "layers.16.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
129
+ "layers.16.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
130
+ "layers.16.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
131
+ "layers.17.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
132
+ "layers.17.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
133
+ "layers.17.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
134
+ "layers.17.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
135
+ "layers.17.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
136
+ "layers.17.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
137
+ "layers.17.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
138
+ "layers.17.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
139
+ "layers.17.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
140
+ "layers.17.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
141
+ "layers.17.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
142
+ "layers.17.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
143
+ "layers.17.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
144
+ "layers.17.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
145
+ "layers.17.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
146
+ "layers.17.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
147
+ "layers.17.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
148
+ "layers.17.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
149
+ "layers.17.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
150
+ "layers.17.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
151
+ "layers.17.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
152
+ "layers.17.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
153
+ "layers.18.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
154
+ "layers.18.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
155
+ "layers.18.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
156
+ "layers.18.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
157
+ "layers.18.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
158
+ "layers.18.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
159
  "layers.30.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
160
  "layers.30.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
161
  "layers.30.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
 
431
  "time_embedder.linear_1.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
432
  "time_embedder.linear_2.bias": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
433
  "time_embedder.linear_2.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
434
+ "embed_tokens.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
435
+ "layers.0.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
436
+ "layers.0.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
437
+ "layers.0.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
438
+ "layers.0.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
439
+ "layers.0.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
440
+ "layers.0.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
441
+ "layers.0.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
442
+ "layers.0.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
443
+ "layers.0.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
444
+ "layers.0.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
445
+ "layers.0.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
446
+ "layers.0.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
447
+ "layers.0.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
448
+ "layers.0.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
449
+ "layers.0.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
450
+ "layers.0.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
451
+ "layers.0.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
452
+ "layers.0.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
453
+ "layers.0.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
454
+ "layers.0.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
455
+ "layers.0.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
456
+ "layers.0.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
457
+ "layers.1.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
458
+ "layers.1.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
459
+ "layers.1.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
460
+ "layers.1.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
461
+ "layers.1.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
462
+ "layers.1.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
463
+ "layers.1.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
464
+ "layers.1.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
465
+ "layers.1.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
466
+ "layers.1.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
467
+ "layers.1.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
468
+ "layers.1.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
469
+ "layers.1.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
470
+ "layers.1.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
471
+ "layers.1.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
472
+ "layers.1.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
473
+ "layers.1.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
474
+ "layers.1.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
475
+ "layers.1.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
476
+ "layers.1.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
477
+ "layers.1.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
478
+ "layers.1.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
479
+ "layers.10.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
480
+ "layers.10.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
481
+ "layers.10.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
482
+ "layers.10.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
483
+ "layers.10.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
484
+ "layers.10.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
485
+ "layers.10.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
486
+ "layers.10.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
487
+ "layers.10.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
488
+ "layers.10.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
489
+ "layers.10.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
490
+ "layers.10.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
491
+ "layers.10.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
492
+ "layers.10.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
493
+ "layers.10.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
494
+ "layers.10.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
495
+ "layers.10.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
496
+ "layers.10.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
497
+ "layers.10.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
498
+ "layers.10.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
499
+ "layers.10.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
500
+ "layers.10.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
501
+ "layers.11.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
502
+ "layers.11.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
503
+ "layers.11.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
504
+ "layers.11.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
505
+ "layers.11.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
506
+ "layers.11.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
507
+ "layers.11.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
508
+ "lm_head.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
509
+ "layers.18.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
510
+ "layers.18.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
511
+ "layers.18.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
512
+ "layers.18.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
513
+ "layers.18.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
514
+ "layers.18.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
515
+ "layers.18.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
516
+ "layers.18.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
517
+ "layers.18.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
518
+ "layers.18.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
519
+ "layers.18.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
520
+ "layers.18.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
521
+ "layers.18.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
522
+ "layers.18.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
523
+ "layers.18.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
524
+ "layers.18.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
525
+ "layers.19.input_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
526
+ "layers.19.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
527
+ "layers.19.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
528
+ "layers.19.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
529
+ "layers.19.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
530
+ "layers.19.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
531
+ "layers.19.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
532
+ "layers.19.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
533
+ "layers.19.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
534
+ "layers.19.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
535
+ "layers.19.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
536
+ "layers.19.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
537
+ "layers.19.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
538
+ "layers.19.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
539
+ "layers.19.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
540
+ "layers.19.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
541
+ "layers.19.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
542
+ "layers.19.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
543
+ "layers.19.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
544
+ "layers.19.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
545
+ "layers.19.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
546
+ "layers.19.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
547
+ "layers.2.input_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
548
+ "layers.2.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
549
+ "layers.2.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
550
+ "layers.2.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
551
+ "layers.2.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
552
+ "layers.2.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
553
+ "layers.2.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
554
+ "layers.2.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
555
+ "layers.2.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
556
+ "layers.2.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
557
+ "layers.2.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
558
+ "layers.2.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
559
+ "layers.2.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
560
+ "layers.2.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
561
+ "layers.2.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
562
+ "layers.2.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
563
+ "layers.2.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
564
+ "layers.2.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
565
+ "layers.2.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
566
+ "layers.2.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
567
+ "layers.2.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
568
+ "layers.2.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
569
+ "layers.20.input_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
570
+ "layers.20.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
571
+ "layers.20.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
572
+ "layers.20.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
573
+ "layers.20.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
574
+ "layers.20.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
575
+ "layers.20.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
576
+ "layers.20.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
577
+ "layers.20.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
578
+ "layers.20.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
579
+ "layers.20.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
580
+ "layers.20.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
581
+ "layers.20.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
582
+ "layers.20.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
583
+ "layers.20.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
584
+ "layers.20.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
585
+ "layers.20.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
586
+ "layers.20.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
587
+ "layers.20.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
588
+ "layers.20.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
589
+ "layers.20.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
590
+ "layers.20.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
591
+ "layers.21.input_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
592
+ "layers.21.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
593
+ "layers.21.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
594
+ "layers.21.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
595
+ "layers.21.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
596
+ "layers.21.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
597
+ "layers.21.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
598
+ "layers.21.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
599
+ "layers.21.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
600
+ "layers.21.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
601
+ "layers.21.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
602
+ "layers.21.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
603
+ "layers.21.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
604
+ "layers.21.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
605
+ "layers.21.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
606
+ "layers.21.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
607
+ "layers.21.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
608
+ "layers.21.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
609
+ "layers.21.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
610
+ "layers.21.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
611
+ "layers.21.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
612
+ "layers.21.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
613
+ "layers.22.input_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
614
+ "layers.22.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
615
+ "layers.22.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
616
+ "layers.22.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
617
+ "layers.22.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
618
+ "layers.22.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
619
+ "layers.22.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
620
+ "layers.22.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
621
+ "layers.22.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
622
+ "layers.22.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
623
+ "layers.22.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
624
+ "layers.22.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
625
+ "layers.22.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
626
+ "layers.22.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
627
+ "layers.22.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
628
+ "layers.22.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
629
+ "layers.22.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
630
+ "layers.22.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
631
+ "layers.22.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
632
+ "layers.22.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
633
+ "layers.22.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
634
+ "layers.22.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
635
+ "layers.23.input_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
636
+ "layers.23.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
637
+ "layers.23.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
638
+ "layers.23.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
639
+ "layers.23.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
640
+ "layers.23.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
641
+ "layers.23.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
642
+ "layers.23.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
643
+ "layers.23.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
644
+ "layers.23.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
645
+ "layers.23.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
646
+ "layers.23.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
647
+ "layers.23.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
648
+ "layers.23.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
649
+ "layers.23.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
650
+ "layers.23.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
651
+ "layers.23.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
652
+ "layers.23.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
653
+ "layers.23.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
654
+ "layers.23.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
655
+ "layers.23.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
656
+ "layers.23.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
657
+ "layers.24.input_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
658
+ "layers.24.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
659
+ "layers.24.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
660
+ "layers.24.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
661
+ "layers.24.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
662
  "layers.24.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
663
  "layers.24.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
664
  "layers.24.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
 
811
  "layers.30.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
812
  "layers.30.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
813
  "layers.30.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
814
+ "layers.30.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
815
  }
816
  }
model_index.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "Cosmos3MultiviewPipeline",
3
  "_diffusers_version": "0.39.0",
4
- "default_use_system_prompt": true,
5
  "enable_safety_checker": false,
6
  "safety_checker": [
7
  null,
@@ -23,7 +23,7 @@
23
  "diffusers",
24
  "Cosmos3OmniTransformer"
25
  ],
26
- "use_native_flow_schedule": false,
27
  "vae": [
28
  "diffusers",
29
  "AutoencoderKLWan"
 
1
  {
2
  "_class_name": "Cosmos3MultiviewPipeline",
3
  "_diffusers_version": "0.39.0",
4
+ "default_use_system_prompt": false,
5
  "enable_safety_checker": false,
6
  "safety_checker": [
7
  null,
 
23
  "diffusers",
24
  "Cosmos3OmniTransformer"
25
  ],
26
+ "use_native_flow_schedule": true,
27
  "vae": [
28
  "diffusers",
29
  "AutoencoderKLWan"
modular_model_index.json CHANGED
@@ -7,7 +7,7 @@
7
  "diffusers",
8
  "UniPCMultistepScheduler",
9
  {
10
- "pretrained_model_name_or_path": "diffusers_format2",
11
  "subfolder": "scheduler",
12
  "type_hint": [
13
  "diffusers",
@@ -20,7 +20,7 @@
20
  "transformers",
21
  "Qwen2TokenizerFast",
22
  {
23
- "pretrained_model_name_or_path": "diffusers_format2",
24
  "subfolder": "text_tokenizer",
25
  "type_hint": [
26
  "transformers",
@@ -33,7 +33,7 @@
33
  "diffusers",
34
  "Cosmos3OmniTransformer",
35
  {
36
- "pretrained_model_name_or_path": "diffusers_format2",
37
  "subfolder": "transformer",
38
  "type_hint": [
39
  "diffusers",
@@ -46,7 +46,7 @@
46
  "diffusers",
47
  "AutoencoderKLWan",
48
  {
49
- "pretrained_model_name_or_path": "diffusers_format2",
50
  "subfolder": "vae",
51
  "type_hint": [
52
  "diffusers",
 
7
  "diffusers",
8
  "UniPCMultistepScheduler",
9
  {
10
+ "pretrained_model_name_or_path": "diffusers_format6",
11
  "subfolder": "scheduler",
12
  "type_hint": [
13
  "diffusers",
 
20
  "transformers",
21
  "Qwen2TokenizerFast",
22
  {
23
+ "pretrained_model_name_or_path": "diffusers_format6",
24
  "subfolder": "text_tokenizer",
25
  "type_hint": [
26
  "transformers",
 
33
  "diffusers",
34
  "Cosmos3OmniTransformer",
35
  {
36
+ "pretrained_model_name_or_path": "diffusers_format6",
37
  "subfolder": "transformer",
38
  "type_hint": [
39
  "diffusers",
 
46
  "diffusers",
47
  "AutoencoderKLWan",
48
  {
49
+ "pretrained_model_name_or_path": "diffusers_format6",
50
  "subfolder": "vae",
51
  "type_hint": [
52
  "diffusers",
scheduler/scheduler_config.json CHANGED
@@ -7,7 +7,7 @@
7
  "disable_corrector": [],
8
  "dynamic_thresholding_ratio": 0.995,
9
  "final_sigmas_type": "zero",
10
- "flow_shift": 1.0,
11
  "lower_order_final": true,
12
  "num_train_timesteps": 1000,
13
  "predict_x0": true,
@@ -15,8 +15,8 @@
15
  "rescale_betas_zero_snr": false,
16
  "sample_max_value": 1.0,
17
  "shift_terminal": null,
18
- "sigma_max": 200.0,
19
- "sigma_min": 0.147,
20
  "solver_order": 2,
21
  "solver_p": null,
22
  "solver_type": "bh2",
@@ -29,5 +29,5 @@
29
  "use_dynamic_shifting": false,
30
  "use_exponential_sigmas": false,
31
  "use_flow_sigmas": true,
32
- "use_karras_sigmas": true
33
  }
 
7
  "disable_corrector": [],
8
  "dynamic_thresholding_ratio": 0.995,
9
  "final_sigmas_type": "zero",
10
+ "flow_shift": 10.0,
11
  "lower_order_final": true,
12
  "num_train_timesteps": 1000,
13
  "predict_x0": true,
 
15
  "rescale_betas_zero_snr": false,
16
  "sample_max_value": 1.0,
17
  "shift_terminal": null,
18
+ "sigma_max": null,
19
+ "sigma_min": null,
20
  "solver_order": 2,
21
  "solver_p": null,
22
  "solver_type": "bh2",
 
29
  "use_dynamic_shifting": false,
30
  "use_exponential_sigmas": false,
31
  "use_flow_sigmas": true,
32
+ "use_karras_sigmas": false
33
  }