{ "weight_map": { "model.layers.layers.0.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.0.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "model.layers.layers.0.mixer.bcdt_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.0.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.2.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.2.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "model.layers.layers.2.mixer.bcdt_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.2.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.4.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.4.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "model.layers.layers.4.mixer.bcdt_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.4.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.6.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.6.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "model.layers.layers.6.mixer.bcdt_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.6.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.8.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.8.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "model.layers.layers.8.mixer.bcdt_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.8.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.10.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.10.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "model.layers.layers.10.mixer.bcdt_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.10.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.12.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.12.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "model.layers.layers.12.mixer.bcdt_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.12.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.14.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.14.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "model.layers.layers.14.mixer.bcdt_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.14.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.1.mixer.qkv_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.1.mixer.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.3.mixer.qkv_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.3.mixer.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.5.mixer.qkv_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.5.mixer.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.7.mixer.qkv_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.7.mixer.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.9.mixer.qkv_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.9.mixer.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.11.mixer.qkv_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.11.mixer.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.13.mixer.qkv_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.13.mixer.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.15.mixer.qkv_proj.weight": "model-00002-of-00007.safetensors", "model.layers.layers.15.mixer.o_proj.weight": "model-00002-of-00007.safetensors", "model.embed_tokens.weight": "model-00003-of-00007.safetensors", "model.layers.layers.0.mixer.dt_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.0.mixer.B_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.0.mixer.C_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.0.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.0.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.0.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.0.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.1.mixer.q_weight": "model-00004-of-00007.safetensors", "model.layers.layers.1.mixer.k_weight": "model-00004-of-00007.safetensors", "model.layers.layers.1.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.1.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.1.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.1.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.2.mixer.dt_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.2.mixer.B_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.2.mixer.C_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.2.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.2.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.2.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.2.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.3.mixer.q_weight": "model-00004-of-00007.safetensors", "model.layers.layers.3.mixer.k_weight": "model-00004-of-00007.safetensors", "model.layers.layers.3.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.3.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.3.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.3.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.4.mixer.dt_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.4.mixer.B_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.4.mixer.C_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.4.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.4.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.4.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.4.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.5.mixer.q_weight": "model-00004-of-00007.safetensors", "model.layers.layers.5.mixer.k_weight": "model-00004-of-00007.safetensors", "model.layers.layers.5.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.5.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.5.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.5.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.6.mixer.dt_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.6.mixer.B_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.6.mixer.C_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.6.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.6.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.6.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.6.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.7.mixer.q_weight": "model-00004-of-00007.safetensors", "model.layers.layers.7.mixer.k_weight": "model-00004-of-00007.safetensors", "model.layers.layers.7.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.7.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.7.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.7.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.8.mixer.dt_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.8.mixer.B_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.8.mixer.C_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.8.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.8.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.8.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.8.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.9.mixer.q_weight": "model-00004-of-00007.safetensors", "model.layers.layers.9.mixer.k_weight": "model-00004-of-00007.safetensors", "model.layers.layers.9.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.9.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.9.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.9.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.10.mixer.dt_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.10.mixer.B_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.10.mixer.C_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.10.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.10.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.10.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.10.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.11.mixer.q_weight": "model-00004-of-00007.safetensors", "model.layers.layers.11.mixer.k_weight": "model-00004-of-00007.safetensors", "model.layers.layers.11.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.11.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.11.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.11.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.12.mixer.dt_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.12.mixer.B_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.12.mixer.C_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.12.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.12.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.12.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.12.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.13.mixer.q_weight": "model-00004-of-00007.safetensors", "model.layers.layers.13.mixer.k_weight": "model-00004-of-00007.safetensors", "model.layers.layers.13.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.13.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.13.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.13.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.14.mixer.dt_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.14.mixer.B_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.14.mixer.C_norm_weight": "model-00004-of-00007.safetensors", "model.layers.layers.14.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.14.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.14.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.14.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.15.mixer.q_weight": "model-00004-of-00007.safetensors", "model.layers.layers.15.mixer.k_weight": "model-00004-of-00007.safetensors", "model.layers.layers.15.pre_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.15.post_mixer_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.15.pre_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.15.post_mlp_norm.weight": "model-00004-of-00007.safetensors", "model.norm.weight": "model-00004-of-00007.safetensors", "model.layers.layers.0.mixer.dt_proj.weight": "model-00005-of-00007.safetensors", "model.layers.layers.2.mixer.dt_proj.weight": "model-00005-of-00007.safetensors", "model.layers.layers.4.mixer.dt_proj.weight": "model-00005-of-00007.safetensors", "model.layers.layers.6.mixer.dt_proj.weight": "model-00005-of-00007.safetensors", "model.layers.layers.8.mixer.dt_proj.weight": "model-00005-of-00007.safetensors", "model.layers.layers.10.mixer.dt_proj.weight": "model-00005-of-00007.safetensors", "model.layers.layers.12.mixer.dt_proj.weight": "model-00005-of-00007.safetensors", "model.layers.layers.14.mixer.dt_proj.weight": "model-00005-of-00007.safetensors", "model.layers.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.9.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.10.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.11.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.12.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.13.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.14.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.15.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.layers.0.mixer.dt_bias": "model-00006-of-00007.safetensors", "model.layers.layers.0.mixer.A_log": "model-00006-of-00007.safetensors", "model.layers.layers.0.mixer.D": "model-00006-of-00007.safetensors", "model.layers.layers.2.mixer.dt_bias": "model-00006-of-00007.safetensors", "model.layers.layers.2.mixer.A_log": "model-00006-of-00007.safetensors", "model.layers.layers.2.mixer.D": "model-00006-of-00007.safetensors", "model.layers.layers.4.mixer.dt_bias": "model-00006-of-00007.safetensors", "model.layers.layers.4.mixer.A_log": "model-00006-of-00007.safetensors", "model.layers.layers.4.mixer.D": "model-00006-of-00007.safetensors", "model.layers.layers.6.mixer.dt_bias": "model-00006-of-00007.safetensors", "model.layers.layers.6.mixer.A_log": "model-00006-of-00007.safetensors", "model.layers.layers.6.mixer.D": "model-00006-of-00007.safetensors", "model.layers.layers.8.mixer.dt_bias": "model-00006-of-00007.safetensors", "model.layers.layers.8.mixer.A_log": "model-00006-of-00007.safetensors", "model.layers.layers.8.mixer.D": "model-00006-of-00007.safetensors", "model.layers.layers.10.mixer.dt_bias": "model-00006-of-00007.safetensors", "model.layers.layers.10.mixer.A_log": "model-00006-of-00007.safetensors", "model.layers.layers.10.mixer.D": "model-00006-of-00007.safetensors", "model.layers.layers.12.mixer.dt_bias": "model-00006-of-00007.safetensors", "model.layers.layers.12.mixer.A_log": "model-00006-of-00007.safetensors", "model.layers.layers.12.mixer.D": "model-00006-of-00007.safetensors", "model.layers.layers.14.mixer.dt_bias": "model-00006-of-00007.safetensors", "model.layers.layers.14.mixer.A_log": "model-00006-of-00007.safetensors", "model.layers.layers.14.mixer.D": "model-00006-of-00007.safetensors" }, "metadata": {} }