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

@@ -3,128 +3,81 @@
     "total_size": 30314648192
   },
   "weight_map": {
-    "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",
-    "layers.5.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.5.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.input_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.6.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.input_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.7.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.input_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.8.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.input_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "layers.9.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "lidar_proj_in.bias": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "lidar_proj_in.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "lidar_proj_out.bias": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "lidar_proj_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "norm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "norm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "proj_in.bias": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "proj_in.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "proj_out.bias": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "proj_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "rig_view_embed.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "time_embedder.linear_1.bias": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "time_embedder.linear_1.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "time_embedder.linear_2.bias": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
-    "time_embedder.linear_2.weight": "transformer/diffusion_pytorch_model-00006-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.18.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
     "layers.18.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
     "layers.18.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00003-of-00006.safetensors",
@@ -278,81 +231,6 @@
     "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",
@@ -506,159 +384,128 @@
     "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",
-    "layers.11.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.11.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.11.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.11.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.11.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.11.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.11.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.11.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.11.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.11.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.11.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.11.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.12.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.13.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.14.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.15.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.16.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.17.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.18.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.18.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "layers.18.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
-    "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.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",
+    "layers.5.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.5.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.input_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.6.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.input_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.7.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.input_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.8.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.input_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "layers.9.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "lidar_proj_in.bias": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "lidar_proj_in.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "lidar_proj_out.bias": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "lidar_proj_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "norm.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "norm_moe_gen.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "proj_in.bias": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "proj_in.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "proj_out.bias": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "proj_out.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "rig_view_embed.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "time_embedder.linear_1.bias": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "time_embedder.linear_1.weight": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "time_embedder.linear_2.bias": "transformer/diffusion_pytorch_model-00006-of-00006.safetensors",
+    "time_embedder.linear_2.weight": "transformer/diffusion_pytorch_model-00006-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",
@@ -811,6 +658,159 @@
     "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.gate_proj.weight": "transformer/diffusion_pytorch_model-00004-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",
+    "layers.11.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.11.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.11.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.11.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.11.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.11.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.11.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.11.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.11.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.11.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.11.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.11.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.12.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.13.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.14.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.15.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.16.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.mlp.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.mlp.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.mlp_moe_gen.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.mlp_moe_gen.gate_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.mlp_moe_gen.up_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.post_attention_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.post_attention_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.self_attn.add_k_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.self_attn.add_q_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.self_attn.add_v_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.self_attn.norm_added_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.self_attn.norm_added_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.self_attn.norm_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.self_attn.norm_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.self_attn.to_add_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.self_attn.to_k.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.self_attn.to_out.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.self_attn.to_q.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.17.self_attn.to_v.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.18.input_layernorm.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.18.input_layernorm_moe_gen.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "layers.18.mlp.down_proj.weight": "transformer/diffusion_pytorch_model-00002-of-00006.safetensors",
+    "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"
   }
 }

model_index.json

@@ -6,8 +6,8 @@
     "checkpoint_iteration": 1800,
     "schema_version": 1
   },
-  "_diffusers_version": "0.39.0",
-  "default_use_system_prompt": true,
+  "_diffusers_version": "0.40.0",
+  "default_use_system_prompt": false,
   "enable_safety_checker": false,
   "safety_checker": [
     null,
@@ -23,7 +23,7 @@
   ],
   "text_tokenizer": [
     "transformers",
-    "Qwen2TokenizerFast"
+    "Qwen2Tokenizer"
   ],
   "transformer": [
     "diffusers",

modular_model_index.json

@@ -7,19 +7,21 @@
     "checkpoint_iteration": 1800,
     "schema_version": 1
   },
-  "_diffusers_version": "0.39.0",
+  "_diffusers_version": "0.40.0",
+  "default_use_system_prompt": false,
   "distilled_sigmas": [
     1.0,
     0.9375,
     0.8333333333333334,
     0.625
   ],
+  "enable_safety_checker": false,
   "is_distilled": true,
   "scheduler": [
     "diffusers",
     "FlowMatchEulerDiscreteScheduler",
     {
-      "pretrained_model_name_or_path": "diffusers_format2",
+      "pretrained_model_name_or_path": "diffusers_format7",
       "subfolder": "scheduler",
       "type_hint": [
         "diffusers",
@@ -30,13 +32,13 @@
   ],
   "text_tokenizer": [
     "transformers",
-    "Qwen2TokenizerFast",
+    "Qwen2Tokenizer",
     {
-      "pretrained_model_name_or_path": "diffusers_format2",
+      "pretrained_model_name_or_path": "diffusers_format7",
       "subfolder": "text_tokenizer",
       "type_hint": [
         "transformers",
-        "Qwen2TokenizerFast"
+        "Qwen2Tokenizer"
       ],
       "variant": null
     }
@@ -45,7 +47,7 @@
     "diffusers",
     "Cosmos3OmniTransformer",
     {
-      "pretrained_model_name_or_path": "diffusers_format2",
+      "pretrained_model_name_or_path": "diffusers_format7",
       "subfolder": "transformer",
       "type_hint": [
         "diffusers",
@@ -54,11 +56,12 @@
       "variant": null
     }
   ],
+  "use_native_flow_schedule": false,
   "vae": [
     "diffusers",
     "AutoencoderKLWan",
     {
-      "pretrained_model_name_or_path": "diffusers_format2",
+      "pretrained_model_name_or_path": "diffusers_format7",
       "subfolder": "vae",
       "type_hint": [
         "diffusers",

scheduler/scheduler_config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "FlowMatchEulerDiscreteScheduler",
-  "_diffusers_version": "0.39.0",
+  "_diffusers_version": "0.40.0",
   "base_image_seq_len": 256,
   "base_shift": 0.5,
   "fixed_step_requires_explicit_sigmas": true,

text_tokenizer/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
-size 11422654
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

text_tokenizer/tokenizer_config.json

@@ -1,217 +1,11 @@
 {
-  "add_bos_token": false,
   "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151665": {
-      "content": "<tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151666": {
-      "content": "</tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151667": {
-      "content": "<think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151668": {
-      "content": "</think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
     "<|im_start|>",
     "<|im_end|>",
     "<|object_ref_start|>",
@@ -226,11 +20,8 @@
     "<|image_pad|>",
     "<|video_pad|>"
   ],
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
+  "is_local": false,
+  "local_files_only": false,
   "model_max_length": 262144,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,

transformer/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "Cosmos3OmniTransformer",
-  "_diffusers_version": "0.39.0",
+  "_diffusers_version": "0.40.0",
   "action_dim": 32,
   "action_gen": false,
   "attention_bias": false,
@@ -224,6 +224,7 @@
       20,
       20
     ],
+    "rope_theta": 5000000,
     "rope_type": "default"
   },
   "rope_theta": 5000000,

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKLWan",
-  "_diffusers_version": "0.39.0",
+  "_diffusers_version": "0.40.0",
   "_name_or_path": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
   "attn_scales": [],
   "base_dim": 160,