{ "metadata": { "total_size": 5403448320 }, "weight_map": { "lm_head.weight": "model-00002-of-00002.safetensors", "model.embeddings.weight": "model-00001-of-00002.safetensors", "model.layers.0.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.0.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.1.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.1.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.10.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.10.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.11.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.11.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.12.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.12.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.13.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.13.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.14.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.14.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.15.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.15.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.16.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.16.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.17.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.17.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.18.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.18.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.19.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.19.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.2.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.2.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.20.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.20.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.21.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.21.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.22.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.22.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.23.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.23.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.24.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.24.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.25.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.25.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.26.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.26.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.27.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.27.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.28.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.28.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.29.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.29.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.3.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.3.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.30.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.30.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.attn_norm.weight": "model-00001-of-00002.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp_norm.weight": "model-00001-of-00002.safetensors", "model.layers.31.attn.f_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.attn.g_norm.weight": "model-00002-of-00002.safetensors", "model.layers.31.attn.i_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.attn_norm.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp_norm.weight": "model-00002-of-00002.safetensors", "model.layers.4.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.4.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.5.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.5.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.6.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.6.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.7.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.7.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.8.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.8.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.layers.9.attn.f_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.attn.g_norm.weight": "model-00001-of-00002.safetensors", "model.layers.9.attn.i_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.attn_norm.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_norm.weight": "model-00001-of-00002.safetensors", "model.lower_bounds": "model-00001-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors" } }