Update config

config.json

@@ -119,6 +119,8 @@
             "sensor_to_sensor_bounds": null
           }
         },
+        "maskless_cross_view_action_attends_action": false,
+        "maskless_cross_view_attends_action": false,
         "maskless_cross_view_band_keys": "other_views",
         "maskless_cross_view_band_radius": 0,
         "maskless_cross_view_include_frame_zero": false,
@@ -283,6 +285,8 @@
             "sensor_to_sensor_bounds": null
           }
         },
+        "maskless_cross_view_action_attends_action": false,
+        "maskless_cross_view_attends_action": false,
         "maskless_cross_view_band_keys": "other_views",
         "maskless_cross_view_band_radius": 0,
         "maskless_cross_view_include_frame_zero": false,

model.safetensors.index.json

@@ -3,6 +3,234 @@
     "total_size": 30314648192
   },
   "weight_map": {
+    "layers.24.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.24.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.25.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.26.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.27.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.28.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.29.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.3.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.30.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.30.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.30.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "layers.30.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
+    "embed_tokens.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.0.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.1.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.10.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.11.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.11.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.11.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.11.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.11.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.11.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "layers.11.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
+    "lm_head.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
     "layers.5.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
     "layers.5.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
     "layers.5.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
@@ -278,234 +506,6 @@
     "layers.24.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
     "layers.24.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
     "layers.24.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
-    "embed_tokens.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.0.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.1.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.10.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.11.input_layernorm.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.11.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.11.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.11.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.11.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.11.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.11.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "lm_head.weight": "transformer/diffusion_pytorch_model-00001-of-00006.safetensors",
-    "layers.30.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.30.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.input_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.31.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.input_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.32.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.input_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.33.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.input_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.34.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.input_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.35.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.input_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.4.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.5.input_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.5.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
-    "layers.5.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
     "layers.11.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
     "layers.11.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
     "layers.11.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
@@ -659,158 +659,158 @@
     "layers.18.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
     "layers.18.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
     "layers.18.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.24.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.24.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.25.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.26.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.27.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.28.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.29.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.3.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.30.input_layernorm.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.30.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.30.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors",
-    "layers.30.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-of-00006.safetensors"
+    "layers.30.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.30.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.input_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.31.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.input_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.32.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.input_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.33.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.input_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.34.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.input_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.35.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.input_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.4.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.5.input_layernorm.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.5.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors",
+    "layers.5.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00005-of-00006.safetensors"
   }
 }

model_index.json

@@ -7,7 +7,7 @@
     "schema_version": 1
   },
   "_diffusers_version": "0.39.0",
-  "default_use_system_prompt": true,
+  "default_use_system_prompt": false,
   "enable_safety_checker": false,
   "safety_checker": [
     null,

modular_model_index.json

@@ -19,7 +19,7 @@
     "diffusers",
     "FlowMatchEulerDiscreteScheduler",
     {
-      "pretrained_model_name_or_path": "diffusers_format2",
+      "pretrained_model_name_or_path": "diffusers_format6",
       "subfolder": "scheduler",
       "type_hint": [
         "diffusers",
@@ -32,7 +32,7 @@
     "transformers",
     "Qwen2TokenizerFast",
     {
-      "pretrained_model_name_or_path": "diffusers_format2",
+      "pretrained_model_name_or_path": "diffusers_format6",
       "subfolder": "text_tokenizer",
       "type_hint": [
         "transformers",
@@ -45,7 +45,7 @@
     "diffusers",
     "Cosmos3OmniTransformer",
     {
-      "pretrained_model_name_or_path": "diffusers_format2",
+      "pretrained_model_name_or_path": "diffusers_format6",
       "subfolder": "transformer",
       "type_hint": [
         "diffusers",
@@ -58,7 +58,7 @@
     "diffusers",
     "AutoencoderKLWan",
     {
-      "pretrained_model_name_or_path": "diffusers_format2",
+      "pretrained_model_name_or_path": "diffusers_format6",
       "subfolder": "vae",
       "type_hint": [
         "diffusers",