{ "metadata": { "total_size": 14539791008 }, "weight_map": { "lm_head.weight": "pytorch_model-00003-of-00003.bin", "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.gnn.activation.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin", "model.layers.0.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin", "model.layers.0.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin", "model.layers.0.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.0.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.0.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.gnn_norm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.0.trainable_scale": "pytorch_model-00001-of-00003.bin", "model.layers.1.gnn.activation.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin", "model.layers.1.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin", "model.layers.1.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin", "model.layers.1.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.1.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.1.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.gnn_norm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.1.trainable_scale": "pytorch_model-00001-of-00003.bin", "model.layers.10.gnn.activation.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin", "model.layers.10.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin", "model.layers.10.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin", "model.layers.10.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.10.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.10.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.gnn_norm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.10.trainable_scale": "pytorch_model-00002-of-00003.bin", "model.layers.11.gnn.activation.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin", "model.layers.11.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin", "model.layers.11.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin", "model.layers.11.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.11.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.11.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.gnn_norm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.11.trainable_scale": "pytorch_model-00002-of-00003.bin", "model.layers.12.gnn.activation.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin", "model.layers.12.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin", "model.layers.12.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin", "model.layers.12.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.12.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.12.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.gnn_norm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.12.trainable_scale": "pytorch_model-00002-of-00003.bin", "model.layers.13.gnn.activation.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin", "model.layers.13.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin", "model.layers.13.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin", "model.layers.13.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.13.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.13.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.gnn_norm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.13.trainable_scale": "pytorch_model-00002-of-00003.bin", "model.layers.14.gnn.activation.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin", "model.layers.14.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin", "model.layers.14.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin", "model.layers.14.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.14.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.14.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.gnn_norm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.14.trainable_scale": "pytorch_model-00002-of-00003.bin", "model.layers.15.gnn.activation.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin", "model.layers.15.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin", "model.layers.15.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin", "model.layers.15.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.15.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.15.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.gnn_norm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.15.trainable_scale": "pytorch_model-00002-of-00003.bin", "model.layers.16.gnn.activation.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin", "model.layers.16.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin", "model.layers.16.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin", "model.layers.16.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.16.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.16.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.gnn_norm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.16.trainable_scale": "pytorch_model-00002-of-00003.bin", "model.layers.17.gnn.activation.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin", "model.layers.17.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin", "model.layers.17.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin", "model.layers.17.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.17.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.17.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.gnn_norm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.17.trainable_scale": "pytorch_model-00002-of-00003.bin", "model.layers.18.gnn.activation.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin", "model.layers.18.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin", "model.layers.18.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin", "model.layers.18.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.18.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.18.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.gnn_norm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.18.trainable_scale": "pytorch_model-00002-of-00003.bin", "model.layers.19.gnn.activation.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin", "model.layers.19.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin", "model.layers.19.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin", "model.layers.19.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.19.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.19.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.gnn_norm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.19.trainable_scale": "pytorch_model-00002-of-00003.bin", "model.layers.2.gnn.activation.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin", "model.layers.2.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin", "model.layers.2.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin", "model.layers.2.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.2.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.2.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.gnn_norm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.2.trainable_scale": "pytorch_model-00001-of-00003.bin", "model.layers.20.gnn.activation.weight": "pytorch_model-00003-of-00003.bin", "model.layers.20.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin", "model.layers.20.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin", "model.layers.20.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin", "model.layers.20.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin", "model.layers.20.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin", "model.layers.20.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin", "model.layers.20.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.20.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.20.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.20.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.20.gnn_norm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.20.trainable_scale": "pytorch_model-00002-of-00003.bin", "model.layers.21.gnn.activation.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin", "model.layers.21.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin", "model.layers.21.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin", "model.layers.21.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.21.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.21.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.gnn_norm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.21.trainable_scale": "pytorch_model-00003-of-00003.bin", "model.layers.22.gnn.activation.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin", "model.layers.22.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin", "model.layers.22.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin", "model.layers.22.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.22.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.22.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.gnn_norm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.22.trainable_scale": "pytorch_model-00003-of-00003.bin", "model.layers.23.gnn.activation.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin", "model.layers.23.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin", "model.layers.23.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin", "model.layers.23.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.23.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.23.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.gnn_norm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.23.trainable_scale": "pytorch_model-00003-of-00003.bin", "model.layers.24.gnn.activation.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin", "model.layers.24.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin", "model.layers.24.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin", "model.layers.24.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.24.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.24.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.gnn_norm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.24.trainable_scale": "pytorch_model-00003-of-00003.bin", "model.layers.25.gnn.activation.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin", "model.layers.25.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin", "model.layers.25.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin", "model.layers.25.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.25.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.25.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.gnn_norm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.25.trainable_scale": "pytorch_model-00003-of-00003.bin", "model.layers.26.gnn.activation.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin", "model.layers.26.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin", "model.layers.26.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin", "model.layers.26.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.26.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.26.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.gnn_norm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.26.trainable_scale": "pytorch_model-00003-of-00003.bin", "model.layers.27.gnn.activation.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.gnn.convs.0.activation_fn.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.gnn.convs.0.epsilon": "pytorch_model-00003-of-00003.bin", "model.layers.27.gnn.convs.0.linear1.bias": "pytorch_model-00003-of-00003.bin", "model.layers.27.gnn.convs.0.linear1.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.gnn.convs.0.linear2.bias": "pytorch_model-00003-of-00003.bin", "model.layers.27.gnn.convs.0.linear2.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.gnn.input_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.27.gnn.input_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.gnn.output_projection.bias": "pytorch_model-00003-of-00003.bin", "model.layers.27.gnn.output_projection.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.gnn_norm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", "model.layers.27.trainable_scale": "pytorch_model-00003-of-00003.bin", "model.layers.3.gnn.activation.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin", "model.layers.3.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin", "model.layers.3.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin", "model.layers.3.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.3.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.3.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.gnn_norm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.3.trainable_scale": "pytorch_model-00001-of-00003.bin", "model.layers.4.gnn.activation.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin", "model.layers.4.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin", "model.layers.4.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin", "model.layers.4.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.4.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.4.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.gnn_norm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.4.trainable_scale": "pytorch_model-00001-of-00003.bin", "model.layers.5.gnn.activation.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin", "model.layers.5.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin", "model.layers.5.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin", "model.layers.5.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.5.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.5.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.gnn_norm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.5.trainable_scale": "pytorch_model-00001-of-00003.bin", "model.layers.6.gnn.activation.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin", "model.layers.6.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin", "model.layers.6.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin", "model.layers.6.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.6.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.6.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.gnn_norm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.6.trainable_scale": "pytorch_model-00001-of-00003.bin", "model.layers.7.gnn.activation.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.gnn.convs.0.activation_fn.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.gnn.convs.0.epsilon": "pytorch_model-00001-of-00003.bin", "model.layers.7.gnn.convs.0.linear1.bias": "pytorch_model-00001-of-00003.bin", "model.layers.7.gnn.convs.0.linear1.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.gnn.convs.0.linear2.bias": "pytorch_model-00001-of-00003.bin", "model.layers.7.gnn.convs.0.linear2.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.gnn.input_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.7.gnn.input_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.gnn.output_projection.bias": "pytorch_model-00001-of-00003.bin", "model.layers.7.gnn.output_projection.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.gnn_norm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.7.trainable_scale": "pytorch_model-00001-of-00003.bin", "model.layers.8.gnn.activation.weight": "pytorch_model-00002-of-00003.bin", "model.layers.8.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin", "model.layers.8.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin", "model.layers.8.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin", "model.layers.8.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin", "model.layers.8.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin", "model.layers.8.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin", "model.layers.8.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.8.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.8.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.8.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.8.gnn_norm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", "model.layers.8.trainable_scale": "pytorch_model-00001-of-00003.bin", "model.layers.9.gnn.activation.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.gnn.convs.0.activation_fn.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.gnn.convs.0.epsilon": "pytorch_model-00002-of-00003.bin", "model.layers.9.gnn.convs.0.linear1.bias": "pytorch_model-00002-of-00003.bin", "model.layers.9.gnn.convs.0.linear1.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.gnn.convs.0.linear2.bias": "pytorch_model-00002-of-00003.bin", "model.layers.9.gnn.convs.0.linear2.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.gnn.input_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.9.gnn.input_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.gnn.output_projection.bias": "pytorch_model-00002-of-00003.bin", "model.layers.9.gnn.output_projection.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.gnn_norm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", "model.layers.9.trainable_scale": "pytorch_model-00002-of-00003.bin", "model.norm.weight": "pytorch_model-00003-of-00003.bin" } }