| { | |
| "metadata": { | |
| "total_size": 6895749120 | |
| }, | |
| "weight_map": { | |
| "model.embed_tokens.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.0.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.0.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.0.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.0.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.1.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.1.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.1.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.1.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.10.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.10.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.10.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.10.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.11.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.11.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.11.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.11.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.12.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.12.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.12.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.12.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.input_layernorm.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.14.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.14.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.14.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.14.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.15.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.15.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.15.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.15.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.16.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.16.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.16.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.16.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.17.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.17.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.17.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.17.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.input_layernorm.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.19.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.19.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.19.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.19.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.mamba.out_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.2.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.2.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.2.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.2.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mamba.A_log": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mamba.B_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mamba.C_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mamba.D": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mamba.conv1d.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mamba.conv1d.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mamba.dt_proj.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mamba.dt_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mamba.dt_proj_down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mamba.in_proj_x.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mamba.in_proj_z.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mamba.out_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mamba.A_log": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mamba.B_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mamba.C_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mamba.D": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mamba.conv1d.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mamba.conv1d.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mamba.dt_proj.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mamba.dt_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mamba.dt_proj_down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mamba.in_proj_x.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mamba.in_proj_z.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mamba.out_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mamba.A_log": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mamba.B_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mamba.C_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mamba.D": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mamba.conv1d.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mamba.conv1d.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mamba.dt_proj.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mamba.dt_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mamba.dt_proj_down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mamba.in_proj_x.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mamba.in_proj_z.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mamba.out_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mamba.A_log": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mamba.B_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mamba.C_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mamba.D": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mamba.conv1d.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mamba.conv1d.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mamba.dt_proj.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mamba.dt_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mamba.dt_proj_down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mamba.in_proj_x.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mamba.in_proj_z.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mamba.out_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mamba.A_log": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mamba.B_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mamba.C_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mamba.D": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mamba.conv1d.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mamba.conv1d.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mamba.dt_proj.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mamba.dt_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mamba.dt_proj_down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mamba.in_proj_x.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mamba.in_proj_z.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mamba.out_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mamba.A_log": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mamba.B_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mamba.C_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mamba.D": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mamba.conv1d.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mamba.conv1d.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mamba.dt_proj.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mamba.dt_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mamba.dt_proj_down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mamba.in_proj_x.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mamba.in_proj_z.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mamba.out_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.3.input_layernorm.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.4.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.4.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.4.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.4.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.5.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.5.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.5.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.5.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.6.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.6.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.6.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.6.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.7.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.7.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.7.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.7.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.input_layernorm.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.mamba.A_log": "model-00001-of-00002.safetensors", | |
| "model.layers.9.mamba.B_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.mamba.C_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.mamba.D": "model-00001-of-00002.safetensors", | |
| "model.layers.9.mamba.conv1d.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.9.mamba.conv1d.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.mamba.dt_proj.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.9.mamba.dt_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.mamba.dt_proj_down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.mamba.in_proj_x.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.mamba.in_proj_z.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.mamba.out_proj.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.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.norm.weight": "model-00002-of-00002.safetensors" | |
| } | |
| } | |