{
  "metadata": {
    "total_size": 6036127936
  },
  "weight_map": {
    "lm_head.weight": "model-00002-of-00002.safetensors",
    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.0.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.1.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.10.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.11.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.12.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.13.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.14.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.15.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.2.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.3.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.4.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.5.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.6.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.7.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.8.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.trainable_scale": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.convs.0.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.convs.0.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.convs.0.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.convs.0.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.convs.0.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.convs.0.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.convs.0.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.convs.1.epsilon": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.convs.1.linear1.bias": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.convs.1.linear1.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.convs.1.linear2.bias": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.convs.1.linear2.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.convs.1.norm.bias": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.convs.1.norm.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.input_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.input_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.output_projection.bias": "model-00001-of-00002.safetensors",
    "model.layers.9.gnn.output_projection.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.trainable_scale": "model-00001-of-00002.safetensors",
    "model.norm.weight": "model-00001-of-00002.safetensors"
  }
}