{ "metadata": { "total_size": 6739314048 }, "weight_map": { "action_modality_embed": "diffusion_pytorch_model-00001-of-00002.safetensors", "action_proj_in.bias.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "action_proj_in.fc.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "action_proj_out.bias.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "action_proj_out.fc.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "embed_tokens.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.0.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.1.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.10.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.11.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.12.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.13.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.14.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.15.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.16.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.17.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.18.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.19.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.2.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.20.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.21.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.22.input_layernorm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.22.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.22.mlp.down_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.22.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.22.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.22.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.22.post_attention_layernorm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.22.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.22.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.22.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.22.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.22.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.22.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.22.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.22.self_attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.22.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.22.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.22.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.22.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.23.input_layernorm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.mlp.down_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.post_attention_layernorm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.self_attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.self_attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.self_attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.self_attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.23.self_attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.input_layernorm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.mlp.down_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.post_attention_layernorm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.self_attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.self_attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.self_attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.self_attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.24.self_attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.input_layernorm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.mlp.down_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.post_attention_layernorm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.self_attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.self_attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.self_attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.self_attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.25.self_attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.input_layernorm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.mlp.down_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.post_attention_layernorm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.self_attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.self_attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.self_attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.self_attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.26.self_attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.input_layernorm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.mlp.down_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.post_attention_layernorm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.self_attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.self_attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.self_attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.self_attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.27.self_attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "layers.3.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.3.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.4.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.5.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.6.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.7.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.8.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.input_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.input_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.mlp.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.mlp_moe_gen.down_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.mlp_moe_gen.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.post_attention_layernorm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.post_attention_layernorm_moe_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.self_attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.self_attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.self_attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.self_attn.k_norm_und_for_gen.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.self_attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.self_attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.self_attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.self_attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.self_attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.self_attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "layers.9.self_attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors", "lm_head.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "norm_moe_gen.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "proj_in.bias": "diffusion_pytorch_model-00002-of-00002.safetensors", "proj_in.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "proj_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors", "proj_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "time_embedder.linear_1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors", "time_embedder.linear_1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors", "time_embedder.linear_2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors", "time_embedder.linear_2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors" } }