| { | |
| "metadata": { | |
| "total_size": 19560470784 | |
| }, | |
| "weight_map": { | |
| "lm_head.weight": "model-00004-of-00004.safetensors", | |
| "model.embed_tokens.weight": "model-00001-of-00004.safetensors", | |
| "model.final_layernorm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.0.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.mamba.A_log": "model-00001-of-00004.safetensors", | |
| "model.layers.0.mamba.D": "model-00001-of-00004.safetensors", | |
| "model.layers.0.mamba.conv1d.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.0.mamba.conv1d.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.mamba.dt_bias": "model-00001-of-00004.safetensors", | |
| "model.layers.0.mamba.in_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.mamba.norm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.mamba.out_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.mamba.A_log": "model-00001-of-00004.safetensors", | |
| "model.layers.1.mamba.D": "model-00001-of-00004.safetensors", | |
| "model.layers.1.mamba.conv1d.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.1.mamba.conv1d.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.mamba.dt_bias": "model-00001-of-00004.safetensors", | |
| "model.layers.1.mamba.in_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.mamba.norm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.mamba.out_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.mamba.A_log": "model-00002-of-00004.safetensors", | |
| "model.layers.10.mamba.D": "model-00002-of-00004.safetensors", | |
| "model.layers.10.mamba.conv1d.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.10.mamba.conv1d.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.mamba.dt_bias": "model-00002-of-00004.safetensors", | |
| "model.layers.10.mamba.in_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.mamba.norm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.mamba.out_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.mamba.A_log": "model-00002-of-00004.safetensors", | |
| "model.layers.11.mamba.D": "model-00002-of-00004.safetensors", | |
| "model.layers.11.mamba.conv1d.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.11.mamba.conv1d.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.mamba.dt_bias": "model-00002-of-00004.safetensors", | |
| "model.layers.11.mamba.in_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.mamba.norm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.mamba.out_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.mamba.A_log": "model-00002-of-00004.safetensors", | |
| "model.layers.12.mamba.D": "model-00002-of-00004.safetensors", | |
| "model.layers.12.mamba.conv1d.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.12.mamba.conv1d.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.mamba.dt_bias": "model-00002-of-00004.safetensors", | |
| "model.layers.12.mamba.in_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.mamba.norm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.mamba.out_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.mamba.A_log": "model-00002-of-00004.safetensors", | |
| "model.layers.13.mamba.D": "model-00002-of-00004.safetensors", | |
| "model.layers.13.mamba.conv1d.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.13.mamba.conv1d.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.mamba.dt_bias": "model-00002-of-00004.safetensors", | |
| "model.layers.13.mamba.in_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.mamba.norm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.mamba.out_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.mamba.A_log": "model-00002-of-00004.safetensors", | |
| "model.layers.14.mamba.D": "model-00002-of-00004.safetensors", | |
| "model.layers.14.mamba.conv1d.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.14.mamba.conv1d.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.mamba.dt_bias": "model-00002-of-00004.safetensors", | |
| "model.layers.14.mamba.in_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.mamba.norm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.mamba.out_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.mamba.A_log": "model-00002-of-00004.safetensors", | |
| "model.layers.15.mamba.D": "model-00002-of-00004.safetensors", | |
| "model.layers.15.mamba.conv1d.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.15.mamba.conv1d.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.mamba.dt_bias": "model-00002-of-00004.safetensors", | |
| "model.layers.15.mamba.in_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.mamba.norm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.mamba.out_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.16.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.16.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.mamba.A_log": "model-00002-of-00004.safetensors", | |
| "model.layers.16.mamba.D": "model-00002-of-00004.safetensors", | |
| "model.layers.16.mamba.conv1d.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.16.mamba.conv1d.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.16.mamba.dt_bias": "model-00002-of-00004.safetensors", | |
| "model.layers.16.mamba.in_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.16.mamba.norm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.16.mamba.out_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.16.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.17.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.17.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.17.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.17.mamba.A_log": "model-00003-of-00004.safetensors", | |
| "model.layers.17.mamba.D": "model-00003-of-00004.safetensors", | |
| "model.layers.17.mamba.conv1d.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.17.mamba.conv1d.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.17.mamba.dt_bias": "model-00003-of-00004.safetensors", | |
| "model.layers.17.mamba.in_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.17.mamba.norm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.17.mamba.out_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.17.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.18.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.18.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.18.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.18.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.mamba.A_log": "model-00003-of-00004.safetensors", | |
| "model.layers.19.mamba.D": "model-00003-of-00004.safetensors", | |
| "model.layers.19.mamba.conv1d.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.19.mamba.conv1d.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.mamba.dt_bias": "model-00003-of-00004.safetensors", | |
| "model.layers.19.mamba.in_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.mamba.norm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.mamba.out_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.2.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.mamba.A_log": "model-00001-of-00004.safetensors", | |
| "model.layers.2.mamba.D": "model-00001-of-00004.safetensors", | |
| "model.layers.2.mamba.conv1d.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.2.mamba.conv1d.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.mamba.dt_bias": "model-00001-of-00004.safetensors", | |
| "model.layers.2.mamba.in_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.mamba.norm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.mamba.out_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.20.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.mamba.A_log": "model-00003-of-00004.safetensors", | |
| "model.layers.20.mamba.D": "model-00003-of-00004.safetensors", | |
| "model.layers.20.mamba.conv1d.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.20.mamba.conv1d.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.mamba.dt_bias": "model-00003-of-00004.safetensors", | |
| "model.layers.20.mamba.in_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.mamba.norm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.mamba.out_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.mamba.A_log": "model-00003-of-00004.safetensors", | |
| "model.layers.21.mamba.D": "model-00003-of-00004.safetensors", | |
| "model.layers.21.mamba.conv1d.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.21.mamba.conv1d.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.mamba.dt_bias": "model-00003-of-00004.safetensors", | |
| "model.layers.21.mamba.in_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.mamba.norm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.mamba.out_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.mamba.A_log": "model-00003-of-00004.safetensors", | |
| "model.layers.22.mamba.D": "model-00003-of-00004.safetensors", | |
| "model.layers.22.mamba.conv1d.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.22.mamba.conv1d.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.mamba.dt_bias": "model-00003-of-00004.safetensors", | |
| "model.layers.22.mamba.in_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.mamba.norm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.mamba.out_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.mamba.A_log": "model-00003-of-00004.safetensors", | |
| "model.layers.23.mamba.D": "model-00003-of-00004.safetensors", | |
| "model.layers.23.mamba.conv1d.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.23.mamba.conv1d.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.mamba.dt_bias": "model-00003-of-00004.safetensors", | |
| "model.layers.23.mamba.in_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.mamba.norm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.mamba.out_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.mamba.A_log": "model-00003-of-00004.safetensors", | |
| "model.layers.24.mamba.D": "model-00003-of-00004.safetensors", | |
| "model.layers.24.mamba.conv1d.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.24.mamba.conv1d.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.mamba.dt_bias": "model-00003-of-00004.safetensors", | |
| "model.layers.24.mamba.in_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.mamba.norm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.mamba.out_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.25.feed_forward.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.25.feed_forward.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.25.feed_forward.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.25.mamba.A_log": "model-00003-of-00004.safetensors", | |
| "model.layers.25.mamba.D": "model-00003-of-00004.safetensors", | |
| "model.layers.25.mamba.conv1d.bias": "model-00004-of-00004.safetensors", | |
| "model.layers.25.mamba.conv1d.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.25.mamba.dt_bias": "model-00003-of-00004.safetensors", | |
| "model.layers.25.mamba.in_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.25.mamba.norm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.25.mamba.out_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.25.pre_ff_layernorm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.26.feed_forward.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.26.feed_forward.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.26.feed_forward.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.26.mamba.A_log": "model-00004-of-00004.safetensors", | |
| "model.layers.26.mamba.D": "model-00004-of-00004.safetensors", | |
| "model.layers.26.mamba.conv1d.bias": "model-00004-of-00004.safetensors", | |
| "model.layers.26.mamba.conv1d.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.26.mamba.dt_bias": "model-00004-of-00004.safetensors", | |
| "model.layers.26.mamba.in_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.26.mamba.norm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.26.mamba.out_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.26.pre_ff_layernorm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.27.feed_forward.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.27.feed_forward.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.27.feed_forward.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.27.pre_ff_layernorm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.28.feed_forward.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.28.feed_forward.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.28.feed_forward.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.28.mamba.A_log": "model-00004-of-00004.safetensors", | |
| "model.layers.28.mamba.D": "model-00004-of-00004.safetensors", | |
| "model.layers.28.mamba.conv1d.bias": "model-00004-of-00004.safetensors", | |
| "model.layers.28.mamba.conv1d.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.28.mamba.dt_bias": "model-00004-of-00004.safetensors", | |
| "model.layers.28.mamba.in_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.28.mamba.norm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.28.mamba.out_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.28.pre_ff_layernorm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.29.feed_forward.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.29.feed_forward.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.29.feed_forward.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.29.mamba.A_log": "model-00004-of-00004.safetensors", | |
| "model.layers.29.mamba.D": "model-00004-of-00004.safetensors", | |
| "model.layers.29.mamba.conv1d.bias": "model-00004-of-00004.safetensors", | |
| "model.layers.29.mamba.conv1d.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.29.mamba.dt_bias": "model-00004-of-00004.safetensors", | |
| "model.layers.29.mamba.in_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.29.mamba.norm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.29.mamba.out_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.29.pre_ff_layernorm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.3.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.mamba.A_log": "model-00001-of-00004.safetensors", | |
| "model.layers.3.mamba.D": "model-00001-of-00004.safetensors", | |
| "model.layers.3.mamba.conv1d.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.3.mamba.conv1d.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.mamba.dt_bias": "model-00001-of-00004.safetensors", | |
| "model.layers.3.mamba.in_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.mamba.norm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.mamba.out_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.30.feed_forward.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.30.feed_forward.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.30.feed_forward.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.30.mamba.A_log": "model-00004-of-00004.safetensors", | |
| "model.layers.30.mamba.D": "model-00004-of-00004.safetensors", | |
| "model.layers.30.mamba.conv1d.bias": "model-00004-of-00004.safetensors", | |
| "model.layers.30.mamba.conv1d.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.30.mamba.dt_bias": "model-00004-of-00004.safetensors", | |
| "model.layers.30.mamba.in_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.30.mamba.norm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.30.mamba.out_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.30.pre_ff_layernorm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.31.feed_forward.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.31.feed_forward.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.31.feed_forward.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.31.mamba.A_log": "model-00004-of-00004.safetensors", | |
| "model.layers.31.mamba.D": "model-00004-of-00004.safetensors", | |
| "model.layers.31.mamba.conv1d.bias": "model-00004-of-00004.safetensors", | |
| "model.layers.31.mamba.conv1d.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.31.mamba.dt_bias": "model-00004-of-00004.safetensors", | |
| "model.layers.31.mamba.in_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.31.mamba.norm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.31.mamba.out_proj.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.31.pre_ff_layernorm.weight": "model-00004-of-00004.safetensors", | |
| "model.layers.4.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.mamba.A_log": "model-00001-of-00004.safetensors", | |
| "model.layers.4.mamba.D": "model-00001-of-00004.safetensors", | |
| "model.layers.4.mamba.conv1d.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.4.mamba.conv1d.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.mamba.dt_bias": "model-00001-of-00004.safetensors", | |
| "model.layers.4.mamba.in_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.mamba.norm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.mamba.out_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.mamba.A_log": "model-00001-of-00004.safetensors", | |
| "model.layers.5.mamba.D": "model-00001-of-00004.safetensors", | |
| "model.layers.5.mamba.conv1d.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.5.mamba.conv1d.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.mamba.dt_bias": "model-00001-of-00004.safetensors", | |
| "model.layers.5.mamba.in_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.mamba.norm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.mamba.out_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.mamba.A_log": "model-00001-of-00004.safetensors", | |
| "model.layers.6.mamba.D": "model-00001-of-00004.safetensors", | |
| "model.layers.6.mamba.conv1d.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.6.mamba.conv1d.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.mamba.dt_bias": "model-00001-of-00004.safetensors", | |
| "model.layers.6.mamba.in_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.mamba.norm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.mamba.out_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.7.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.7.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.mamba.A_log": "model-00001-of-00004.safetensors", | |
| "model.layers.7.mamba.D": "model-00001-of-00004.safetensors", | |
| "model.layers.7.mamba.conv1d.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.7.mamba.conv1d.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.7.mamba.dt_bias": "model-00001-of-00004.safetensors", | |
| "model.layers.7.mamba.in_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.7.mamba.norm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.7.mamba.out_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.7.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.8.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.8.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.8.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.8.mamba.A_log": "model-00002-of-00004.safetensors", | |
| "model.layers.8.mamba.D": "model-00002-of-00004.safetensors", | |
| "model.layers.8.mamba.conv1d.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.8.mamba.conv1d.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.8.mamba.dt_bias": "model-00002-of-00004.safetensors", | |
| "model.layers.8.mamba.in_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.8.mamba.norm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.8.mamba.out_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.8.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors" | |
| } | |
| } | |