| { | |
| "metadata": { | |
| "total_size": 5340972032 | |
| }, | |
| "weight_map": { | |
| "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.0.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.0.stu.M_filters": "model-00001-of-00002.safetensors", | |
| "layers.0.stu.M_inputs": "model-00001-of-00002.safetensors", | |
| "layers.0.stu.flash_fft.f_16_fft": "model-00001-of-00002.safetensors", | |
| "layers.0.stu.flash_fft.f_16_ifft": "model-00001-of-00002.safetensors", | |
| "layers.0.stu.flash_fft.f_32_fft": "model-00001-of-00002.safetensors", | |
| "layers.0.stu.flash_fft.f_32_ifft": "model-00001-of-00002.safetensors", | |
| "layers.0.stu.flash_fft.twiddle_factors_fft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.0.stu.flash_fft.twiddle_factors_fft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.0.stu.flash_fft.twiddle_factors_ifft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.0.stu.flash_fft.twiddle_factors_ifft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.0.stu_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.1.attn.c_attn.weight": "model-00001-of-00002.safetensors", | |
| "layers.1.attn.c_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.1.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.1.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.10.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.10.stu.M_filters": "model-00001-of-00002.safetensors", | |
| "layers.10.stu.M_inputs": "model-00001-of-00002.safetensors", | |
| "layers.10.stu.flash_fft.f_16_fft": "model-00001-of-00002.safetensors", | |
| "layers.10.stu.flash_fft.f_16_ifft": "model-00001-of-00002.safetensors", | |
| "layers.10.stu.flash_fft.f_32_fft": "model-00001-of-00002.safetensors", | |
| "layers.10.stu.flash_fft.f_32_ifft": "model-00001-of-00002.safetensors", | |
| "layers.10.stu.flash_fft.twiddle_factors_fft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.10.stu.flash_fft.twiddle_factors_fft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.10.stu.flash_fft.twiddle_factors_ifft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.10.stu.flash_fft.twiddle_factors_ifft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.10.stu_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.11.attn.c_attn.weight": "model-00001-of-00002.safetensors", | |
| "layers.11.attn.c_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.11.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.11.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.12.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.12.stu.M_filters": "model-00001-of-00002.safetensors", | |
| "layers.12.stu.M_inputs": "model-00001-of-00002.safetensors", | |
| "layers.12.stu.flash_fft.f_16_fft": "model-00001-of-00002.safetensors", | |
| "layers.12.stu.flash_fft.f_16_ifft": "model-00001-of-00002.safetensors", | |
| "layers.12.stu.flash_fft.f_32_fft": "model-00001-of-00002.safetensors", | |
| "layers.12.stu.flash_fft.f_32_ifft": "model-00001-of-00002.safetensors", | |
| "layers.12.stu.flash_fft.twiddle_factors_fft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.12.stu.flash_fft.twiddle_factors_fft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.12.stu.flash_fft.twiddle_factors_ifft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.12.stu.flash_fft.twiddle_factors_ifft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.12.stu_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.13.attn.c_attn.weight": "model-00001-of-00002.safetensors", | |
| "layers.13.attn.c_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.13.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.13.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.14.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.14.stu.M_filters": "model-00001-of-00002.safetensors", | |
| "layers.14.stu.M_inputs": "model-00001-of-00002.safetensors", | |
| "layers.14.stu.flash_fft.f_16_fft": "model-00001-of-00002.safetensors", | |
| "layers.14.stu.flash_fft.f_16_ifft": "model-00001-of-00002.safetensors", | |
| "layers.14.stu.flash_fft.f_32_fft": "model-00001-of-00002.safetensors", | |
| "layers.14.stu.flash_fft.f_32_ifft": "model-00001-of-00002.safetensors", | |
| "layers.14.stu.flash_fft.twiddle_factors_fft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.14.stu.flash_fft.twiddle_factors_fft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.14.stu.flash_fft.twiddle_factors_ifft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.14.stu.flash_fft.twiddle_factors_ifft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.14.stu_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.15.attn.c_attn.weight": "model-00001-of-00002.safetensors", | |
| "layers.15.attn.c_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.15.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.15.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.16.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.16.stu.M_filters": "model-00001-of-00002.safetensors", | |
| "layers.16.stu.M_inputs": "model-00001-of-00002.safetensors", | |
| "layers.16.stu.flash_fft.f_16_fft": "model-00001-of-00002.safetensors", | |
| "layers.16.stu.flash_fft.f_16_ifft": "model-00001-of-00002.safetensors", | |
| "layers.16.stu.flash_fft.f_32_fft": "model-00001-of-00002.safetensors", | |
| "layers.16.stu.flash_fft.f_32_ifft": "model-00001-of-00002.safetensors", | |
| "layers.16.stu.flash_fft.twiddle_factors_fft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.16.stu.flash_fft.twiddle_factors_fft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.16.stu.flash_fft.twiddle_factors_ifft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.16.stu.flash_fft.twiddle_factors_ifft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.16.stu_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.17.attn.c_attn.weight": "model-00001-of-00002.safetensors", | |
| "layers.17.attn.c_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.17.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.17.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.18.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.18.stu.M_filters": "model-00001-of-00002.safetensors", | |
| "layers.18.stu.M_inputs": "model-00001-of-00002.safetensors", | |
| "layers.18.stu.flash_fft.f_16_fft": "model-00001-of-00002.safetensors", | |
| "layers.18.stu.flash_fft.f_16_ifft": "model-00001-of-00002.safetensors", | |
| "layers.18.stu.flash_fft.f_32_fft": "model-00001-of-00002.safetensors", | |
| "layers.18.stu.flash_fft.f_32_ifft": "model-00001-of-00002.safetensors", | |
| "layers.18.stu.flash_fft.twiddle_factors_fft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.18.stu.flash_fft.twiddle_factors_fft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.18.stu.flash_fft.twiddle_factors_ifft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.18.stu.flash_fft.twiddle_factors_ifft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.18.stu_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.19.attn.c_attn.weight": "model-00001-of-00002.safetensors", | |
| "layers.19.attn.c_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.19.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.19.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.2.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.2.stu.M_filters": "model-00001-of-00002.safetensors", | |
| "layers.2.stu.M_inputs": "model-00001-of-00002.safetensors", | |
| "layers.2.stu.flash_fft.f_16_fft": "model-00001-of-00002.safetensors", | |
| "layers.2.stu.flash_fft.f_16_ifft": "model-00001-of-00002.safetensors", | |
| "layers.2.stu.flash_fft.f_32_fft": "model-00001-of-00002.safetensors", | |
| "layers.2.stu.flash_fft.f_32_ifft": "model-00001-of-00002.safetensors", | |
| "layers.2.stu.flash_fft.twiddle_factors_fft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.2.stu.flash_fft.twiddle_factors_fft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.2.stu.flash_fft.twiddle_factors_ifft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.2.stu.flash_fft.twiddle_factors_ifft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.2.stu_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.20.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.20.stu.M_filters": "model-00001-of-00002.safetensors", | |
| "layers.20.stu.M_inputs": "model-00001-of-00002.safetensors", | |
| "layers.20.stu.flash_fft.f_16_fft": "model-00001-of-00002.safetensors", | |
| "layers.20.stu.flash_fft.f_16_ifft": "model-00001-of-00002.safetensors", | |
| "layers.20.stu.flash_fft.f_32_fft": "model-00001-of-00002.safetensors", | |
| "layers.20.stu.flash_fft.f_32_ifft": "model-00001-of-00002.safetensors", | |
| "layers.20.stu.flash_fft.twiddle_factors_fft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.20.stu.flash_fft.twiddle_factors_fft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.20.stu.flash_fft.twiddle_factors_ifft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.20.stu.flash_fft.twiddle_factors_ifft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.20.stu_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.21.attn.c_attn.weight": "model-00001-of-00002.safetensors", | |
| "layers.21.attn.c_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.21.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.21.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.22.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.22.stu.M_filters": "model-00001-of-00002.safetensors", | |
| "layers.22.stu.M_inputs": "model-00001-of-00002.safetensors", | |
| "layers.22.stu.flash_fft.f_16_fft": "model-00001-of-00002.safetensors", | |
| "layers.22.stu.flash_fft.f_16_ifft": "model-00001-of-00002.safetensors", | |
| "layers.22.stu.flash_fft.f_32_fft": "model-00001-of-00002.safetensors", | |
| "layers.22.stu.flash_fft.f_32_ifft": "model-00001-of-00002.safetensors", | |
| "layers.22.stu.flash_fft.twiddle_factors_fft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.22.stu.flash_fft.twiddle_factors_fft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.22.stu.flash_fft.twiddle_factors_ifft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.22.stu.flash_fft.twiddle_factors_ifft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.22.stu_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.23.attn.c_attn.weight": "model-00001-of-00002.safetensors", | |
| "layers.23.attn.c_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.23.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.23.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "layers.24.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.24.stu.M_filters": "model-00001-of-00002.safetensors", | |
| "layers.24.stu.M_inputs": "model-00001-of-00002.safetensors", | |
| "layers.24.stu.flash_fft.f_16_fft": "model-00001-of-00002.safetensors", | |
| "layers.24.stu.flash_fft.f_16_ifft": "model-00001-of-00002.safetensors", | |
| "layers.24.stu.flash_fft.f_32_fft": "model-00001-of-00002.safetensors", | |
| "layers.24.stu.flash_fft.f_32_ifft": "model-00001-of-00002.safetensors", | |
| "layers.24.stu.flash_fft.twiddle_factors_fft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.24.stu.flash_fft.twiddle_factors_fft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.24.stu.flash_fft.twiddle_factors_ifft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.24.stu.flash_fft.twiddle_factors_ifft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.24.stu_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.25.attn.c_attn.weight": "model-00002-of-00002.safetensors", | |
| "layers.25.attn.c_proj.weight": "model-00002-of-00002.safetensors", | |
| "layers.25.attn_norm.weight": "model-00002-of-00002.safetensors", | |
| "layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "layers.25.mlp_norm.weight": "model-00002-of-00002.safetensors", | |
| "layers.3.attn.c_attn.weight": "model-00001-of-00002.safetensors", | |
| "layers.3.attn.c_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.3.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.3.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.4.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.4.stu.M_filters": "model-00001-of-00002.safetensors", | |
| "layers.4.stu.M_inputs": "model-00001-of-00002.safetensors", | |
| "layers.4.stu.flash_fft.f_16_fft": "model-00001-of-00002.safetensors", | |
| "layers.4.stu.flash_fft.f_16_ifft": "model-00001-of-00002.safetensors", | |
| "layers.4.stu.flash_fft.f_32_fft": "model-00001-of-00002.safetensors", | |
| "layers.4.stu.flash_fft.f_32_ifft": "model-00001-of-00002.safetensors", | |
| "layers.4.stu.flash_fft.twiddle_factors_fft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.4.stu.flash_fft.twiddle_factors_fft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.4.stu.flash_fft.twiddle_factors_ifft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.4.stu.flash_fft.twiddle_factors_ifft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.4.stu_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.5.attn.c_attn.weight": "model-00001-of-00002.safetensors", | |
| "layers.5.attn.c_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.5.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.5.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.6.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.6.stu.M_filters": "model-00001-of-00002.safetensors", | |
| "layers.6.stu.M_inputs": "model-00001-of-00002.safetensors", | |
| "layers.6.stu.flash_fft.f_16_fft": "model-00001-of-00002.safetensors", | |
| "layers.6.stu.flash_fft.f_16_ifft": "model-00001-of-00002.safetensors", | |
| "layers.6.stu.flash_fft.f_32_fft": "model-00001-of-00002.safetensors", | |
| "layers.6.stu.flash_fft.f_32_ifft": "model-00001-of-00002.safetensors", | |
| "layers.6.stu.flash_fft.twiddle_factors_fft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.6.stu.flash_fft.twiddle_factors_fft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.6.stu.flash_fft.twiddle_factors_ifft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.6.stu.flash_fft.twiddle_factors_ifft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.6.stu_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.7.attn.c_attn.weight": "model-00001-of-00002.safetensors", | |
| "layers.7.attn.c_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.7.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.7.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.8.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.8.stu.M_filters": "model-00001-of-00002.safetensors", | |
| "layers.8.stu.M_inputs": "model-00001-of-00002.safetensors", | |
| "layers.8.stu.flash_fft.f_16_fft": "model-00001-of-00002.safetensors", | |
| "layers.8.stu.flash_fft.f_16_ifft": "model-00001-of-00002.safetensors", | |
| "layers.8.stu.flash_fft.f_32_fft": "model-00001-of-00002.safetensors", | |
| "layers.8.stu.flash_fft.f_32_ifft": "model-00001-of-00002.safetensors", | |
| "layers.8.stu.flash_fft.twiddle_factors_fft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.8.stu.flash_fft.twiddle_factors_fft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.8.stu.flash_fft.twiddle_factors_ifft_16_1K": "model-00001-of-00002.safetensors", | |
| "layers.8.stu.flash_fft.twiddle_factors_ifft_32_32": "model-00001-of-00002.safetensors", | |
| "layers.8.stu_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.9.attn.c_attn.weight": "model-00001-of-00002.safetensors", | |
| "layers.9.attn.c_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.9.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "layers.9.mlp_norm.weight": "model-00001-of-00002.safetensors", | |
| "lm_head.weight": "model-00001-of-00002.safetensors", | |
| "norm.weight": "model-00002-of-00002.safetensors", | |
| "tok_emb.weight": "model-00001-of-00002.safetensors" | |
| } | |
| } |