{ "metadata": { "total_size": 26693187840 }, "weight_map": { "model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.norm.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.input_linear.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.output_linear.weight": "model-00001-of-00006.safetensors", "model.layers.0.shared_mlp.input_linear.weight": "model-00001-of-00006.safetensors", "model.layers.0.shared_mlp.output_linear.weight": "model-00001-of-00006.safetensors", "model.layers.0.mamba.conv1d.weight": "model-00001-of-00006.safetensors", "model.layers.0.mamba.conv1d.bias": "model-00001-of-00006.safetensors", "model.layers.0.mamba.in_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mamba.dt_bias": "model-00001-of-00006.safetensors", "model.layers.0.mamba.A_log": "model-00001-of-00006.safetensors", "model.layers.0.mamba.D": "model-00001-of-00006.safetensors", "model.layers.0.mamba.out_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mamba.norm.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.input_linear.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.output_linear.weight": "model-00001-of-00006.safetensors", "model.layers.1.shared_mlp.input_linear.weight": "model-00001-of-00006.safetensors", "model.layers.1.shared_mlp.output_linear.weight": "model-00001-of-00006.safetensors", "model.layers.1.mamba.conv1d.weight": "model-00001-of-00006.safetensors", "model.layers.1.mamba.conv1d.bias": "model-00001-of-00006.safetensors", "model.layers.1.mamba.in_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mamba.dt_bias": "model-00001-of-00006.safetensors", "model.layers.1.mamba.A_log": "model-00001-of-00006.safetensors", "model.layers.1.mamba.D": "model-00001-of-00006.safetensors", "model.layers.1.mamba.out_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mamba.norm.weight": "model-00001-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.input_linear.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.output_linear.weight": "model-00001-of-00006.safetensors", "model.layers.2.shared_mlp.input_linear.weight": "model-00001-of-00006.safetensors", "model.layers.2.shared_mlp.output_linear.weight": "model-00001-of-00006.safetensors", "model.layers.2.mamba.conv1d.weight": "model-00001-of-00006.safetensors", "model.layers.2.mamba.conv1d.bias": "model-00001-of-00006.safetensors", "model.layers.2.mamba.in_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.mamba.dt_bias": "model-00001-of-00006.safetensors", "model.layers.2.mamba.A_log": "model-00001-of-00006.safetensors", "model.layers.2.mamba.D": "model-00001-of-00006.safetensors", "model.layers.2.mamba.out_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.mamba.norm.weight": "model-00001-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.input_linear.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.output_linear.weight": "model-00001-of-00006.safetensors", "model.layers.3.shared_mlp.input_linear.weight": "model-00001-of-00006.safetensors", "model.layers.3.shared_mlp.output_linear.weight": "model-00001-of-00006.safetensors", "model.layers.3.mamba.conv1d.weight": "model-00001-of-00006.safetensors", "model.layers.3.mamba.conv1d.bias": "model-00001-of-00006.safetensors", "model.layers.3.mamba.in_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.mamba.dt_bias": "model-00001-of-00006.safetensors", "model.layers.3.mamba.A_log": "model-00001-of-00006.safetensors", "model.layers.3.mamba.D": "model-00001-of-00006.safetensors", "model.layers.3.mamba.out_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.mamba.norm.weight": "model-00001-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.input_linear.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.output_linear.weight": "model-00001-of-00006.safetensors", "model.layers.4.shared_mlp.input_linear.weight": "model-00001-of-00006.safetensors", "model.layers.4.shared_mlp.output_linear.weight": "model-00001-of-00006.safetensors", "model.layers.4.mamba.conv1d.weight": "model-00001-of-00006.safetensors", "model.layers.4.mamba.conv1d.bias": "model-00001-of-00006.safetensors", "model.layers.4.mamba.in_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.mamba.dt_bias": "model-00001-of-00006.safetensors", "model.layers.4.mamba.A_log": "model-00001-of-00006.safetensors", "model.layers.4.mamba.D": "model-00001-of-00006.safetensors", "model.layers.4.mamba.out_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.mamba.norm.weight": "model-00001-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.input_linear.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.output_linear.weight": "model-00001-of-00006.safetensors", "model.layers.5.shared_mlp.input_linear.weight": "model-00001-of-00006.safetensors", "model.layers.5.shared_mlp.output_linear.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.6.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors", "model.layers.6.block_sparse_moe.input_linear.weight": "model-00001-of-00006.safetensors", "model.layers.6.block_sparse_moe.output_linear.weight": "model-00001-of-00006.safetensors", "model.layers.6.shared_mlp.input_linear.weight": "model-00001-of-00006.safetensors", "model.layers.6.shared_mlp.output_linear.weight": "model-00001-of-00006.safetensors", "model.layers.6.mamba.conv1d.weight": "model-00001-of-00006.safetensors", "model.layers.6.mamba.conv1d.bias": "model-00001-of-00006.safetensors", "model.layers.6.mamba.in_proj.weight": "model-00001-of-00006.safetensors", "model.layers.6.mamba.dt_bias": "model-00001-of-00006.safetensors", "model.layers.6.mamba.A_log": "model-00001-of-00006.safetensors", "model.layers.6.mamba.D": "model-00001-of-00006.safetensors", "model.layers.6.mamba.out_proj.weight": "model-00001-of-00006.safetensors", "model.layers.6.mamba.norm.weight": "model-00001-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.7.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors", "model.layers.7.block_sparse_moe.input_linear.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.output_linear.weight": "model-00002-of-00006.safetensors", "model.layers.7.shared_mlp.input_linear.weight": "model-00002-of-00006.safetensors", "model.layers.7.shared_mlp.output_linear.weight": "model-00002-of-00006.safetensors", "model.layers.7.mamba.conv1d.weight": "model-00002-of-00006.safetensors", "model.layers.7.mamba.conv1d.bias": "model-00002-of-00006.safetensors", "model.layers.7.mamba.in_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.mamba.dt_bias": "model-00002-of-00006.safetensors", "model.layers.7.mamba.A_log": "model-00002-of-00006.safetensors", "model.layers.7.mamba.D": "model-00002-of-00006.safetensors", "model.layers.7.mamba.out_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.mamba.norm.weight": "model-00002-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.router.layer.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.input_linear.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.output_linear.weight": "model-00002-of-00006.safetensors", "model.layers.8.shared_mlp.input_linear.weight": "model-00002-of-00006.safetensors", "model.layers.8.shared_mlp.output_linear.weight": "model-00002-of-00006.safetensors", "model.layers.8.mamba.conv1d.weight": "model-00002-of-00006.safetensors", "model.layers.8.mamba.conv1d.bias": "model-00002-of-00006.safetensors", "model.layers.8.mamba.in_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.mamba.dt_bias": "model-00002-of-00006.safetensors", "model.layers.8.mamba.A_log": "model-00002-of-00006.safetensors", "model.layers.8.mamba.D": "model-00002-of-00006.safetensors", "model.layers.8.mamba.out_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.mamba.norm.weight": "model-00002-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.router.layer.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.input_linear.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.output_linear.weight": "model-00002-of-00006.safetensors", "model.layers.9.shared_mlp.input_linear.weight": "model-00002-of-00006.safetensors", "model.layers.9.shared_mlp.output_linear.weight": "model-00002-of-00006.safetensors", "model.layers.9.mamba.conv1d.weight": "model-00002-of-00006.safetensors", "model.layers.9.mamba.conv1d.bias": "model-00002-of-00006.safetensors", "model.layers.9.mamba.in_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.mamba.dt_bias": "model-00002-of-00006.safetensors", "model.layers.9.mamba.A_log": "model-00002-of-00006.safetensors", "model.layers.9.mamba.D": "model-00002-of-00006.safetensors", "model.layers.9.mamba.out_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.mamba.norm.weight": "model-00002-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.router.layer.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.input_linear.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.output_linear.weight": "model-00002-of-00006.safetensors", "model.layers.10.shared_mlp.input_linear.weight": "model-00002-of-00006.safetensors", "model.layers.10.shared_mlp.output_linear.weight": "model-00002-of-00006.safetensors", "model.layers.10.mamba.conv1d.weight": "model-00002-of-00006.safetensors", "model.layers.10.mamba.conv1d.bias": "model-00002-of-00006.safetensors", "model.layers.10.mamba.in_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.mamba.dt_bias": "model-00002-of-00006.safetensors", "model.layers.10.mamba.A_log": "model-00002-of-00006.safetensors", "model.layers.10.mamba.D": "model-00002-of-00006.safetensors", "model.layers.10.mamba.out_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.mamba.norm.weight": "model-00002-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.11.block_sparse_moe.router.layer.weight": "model-00002-of-00006.safetensors", "model.layers.11.block_sparse_moe.input_linear.weight": "model-00002-of-00006.safetensors", "model.layers.11.block_sparse_moe.output_linear.weight": "model-00002-of-00006.safetensors", "model.layers.11.shared_mlp.input_linear.weight": "model-00002-of-00006.safetensors", "model.layers.11.shared_mlp.output_linear.weight": "model-00002-of-00006.safetensors", "model.layers.11.mamba.conv1d.weight": "model-00002-of-00006.safetensors", "model.layers.11.mamba.conv1d.bias": "model-00002-of-00006.safetensors", "model.layers.11.mamba.in_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.mamba.dt_bias": "model-00002-of-00006.safetensors", "model.layers.11.mamba.A_log": "model-00002-of-00006.safetensors", "model.layers.11.mamba.D": "model-00002-of-00006.safetensors", "model.layers.11.mamba.out_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.mamba.norm.weight": "model-00002-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.12.block_sparse_moe.router.layer.weight": "model-00002-of-00006.safetensors", "model.layers.12.block_sparse_moe.input_linear.weight": "model-00002-of-00006.safetensors", "model.layers.12.block_sparse_moe.output_linear.weight": "model-00002-of-00006.safetensors", "model.layers.12.shared_mlp.input_linear.weight": "model-00002-of-00006.safetensors", "model.layers.12.shared_mlp.output_linear.weight": "model-00002-of-00006.safetensors", "model.layers.12.mamba.conv1d.weight": "model-00002-of-00006.safetensors", "model.layers.12.mamba.conv1d.bias": "model-00002-of-00006.safetensors", "model.layers.12.mamba.in_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.mamba.dt_bias": "model-00002-of-00006.safetensors", "model.layers.12.mamba.A_log": "model-00002-of-00006.safetensors", "model.layers.12.mamba.D": "model-00002-of-00006.safetensors", "model.layers.12.mamba.out_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.mamba.norm.weight": "model-00002-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.block_sparse_moe.router.layer.weight": "model-00002-of-00006.safetensors", "model.layers.13.block_sparse_moe.input_linear.weight": "model-00002-of-00006.safetensors", "model.layers.13.block_sparse_moe.output_linear.weight": "model-00002-of-00006.safetensors", "model.layers.13.shared_mlp.input_linear.weight": "model-00002-of-00006.safetensors", "model.layers.13.shared_mlp.output_linear.weight": "model-00002-of-00006.safetensors", "model.layers.13.mamba.conv1d.weight": "model-00002-of-00006.safetensors", "model.layers.13.mamba.conv1d.bias": "model-00002-of-00006.safetensors", "model.layers.13.mamba.in_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mamba.dt_bias": "model-00002-of-00006.safetensors", "model.layers.13.mamba.A_log": "model-00002-of-00006.safetensors", "model.layers.13.mamba.D": "model-00002-of-00006.safetensors", "model.layers.13.mamba.out_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mamba.norm.weight": "model-00002-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.block_sparse_moe.router.layer.weight": "model-00002-of-00006.safetensors", "model.layers.14.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.output_linear.weight": "model-00003-of-00006.safetensors", "model.layers.14.shared_mlp.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.14.shared_mlp.output_linear.weight": "model-00003-of-00006.safetensors", "model.layers.14.mamba.conv1d.weight": "model-00003-of-00006.safetensors", "model.layers.14.mamba.conv1d.bias": "model-00003-of-00006.safetensors", "model.layers.14.mamba.in_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.mamba.dt_bias": "model-00003-of-00006.safetensors", "model.layers.14.mamba.A_log": "model-00003-of-00006.safetensors", "model.layers.14.mamba.D": "model-00003-of-00006.safetensors", "model.layers.14.mamba.out_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.mamba.norm.weight": "model-00003-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.router.layer.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.output_linear.weight": "model-00003-of-00006.safetensors", "model.layers.15.shared_mlp.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.15.shared_mlp.output_linear.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.router.layer.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.output_linear.weight": "model-00003-of-00006.safetensors", "model.layers.16.shared_mlp.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.16.shared_mlp.output_linear.weight": "model-00003-of-00006.safetensors", "model.layers.16.mamba.conv1d.weight": "model-00003-of-00006.safetensors", "model.layers.16.mamba.conv1d.bias": "model-00003-of-00006.safetensors", "model.layers.16.mamba.in_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.mamba.dt_bias": "model-00003-of-00006.safetensors", "model.layers.16.mamba.A_log": "model-00003-of-00006.safetensors", "model.layers.16.mamba.D": "model-00003-of-00006.safetensors", "model.layers.16.mamba.out_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.mamba.norm.weight": "model-00003-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.router.layer.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.output_linear.weight": "model-00003-of-00006.safetensors", "model.layers.17.shared_mlp.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.17.shared_mlp.output_linear.weight": "model-00003-of-00006.safetensors", "model.layers.17.mamba.conv1d.weight": "model-00003-of-00006.safetensors", "model.layers.17.mamba.conv1d.bias": "model-00003-of-00006.safetensors", "model.layers.17.mamba.in_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.mamba.dt_bias": "model-00003-of-00006.safetensors", "model.layers.17.mamba.A_log": "model-00003-of-00006.safetensors", "model.layers.17.mamba.D": "model-00003-of-00006.safetensors", "model.layers.17.mamba.out_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.mamba.norm.weight": "model-00003-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.18.block_sparse_moe.router.layer.weight": "model-00003-of-00006.safetensors", "model.layers.18.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.18.block_sparse_moe.output_linear.weight": "model-00003-of-00006.safetensors", "model.layers.18.shared_mlp.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.18.shared_mlp.output_linear.weight": "model-00003-of-00006.safetensors", "model.layers.18.mamba.conv1d.weight": "model-00003-of-00006.safetensors", "model.layers.18.mamba.conv1d.bias": "model-00003-of-00006.safetensors", "model.layers.18.mamba.in_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.mamba.dt_bias": "model-00003-of-00006.safetensors", "model.layers.18.mamba.A_log": "model-00003-of-00006.safetensors", "model.layers.18.mamba.D": "model-00003-of-00006.safetensors", "model.layers.18.mamba.out_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.mamba.norm.weight": "model-00003-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.19.block_sparse_moe.router.layer.weight": "model-00003-of-00006.safetensors", "model.layers.19.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.19.block_sparse_moe.output_linear.weight": "model-00003-of-00006.safetensors", "model.layers.19.shared_mlp.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.19.shared_mlp.output_linear.weight": "model-00003-of-00006.safetensors", "model.layers.19.mamba.conv1d.weight": "model-00003-of-00006.safetensors", "model.layers.19.mamba.conv1d.bias": "model-00003-of-00006.safetensors", "model.layers.19.mamba.in_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.mamba.dt_bias": "model-00003-of-00006.safetensors", "model.layers.19.mamba.A_log": "model-00003-of-00006.safetensors", "model.layers.19.mamba.D": "model-00003-of-00006.safetensors", "model.layers.19.mamba.out_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.mamba.norm.weight": "model-00003-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.block_sparse_moe.router.layer.weight": "model-00003-of-00006.safetensors", "model.layers.20.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.20.block_sparse_moe.output_linear.weight": "model-00003-of-00006.safetensors", "model.layers.20.shared_mlp.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.20.shared_mlp.output_linear.weight": "model-00003-of-00006.safetensors", "model.layers.20.mamba.conv1d.weight": "model-00003-of-00006.safetensors", "model.layers.20.mamba.conv1d.bias": "model-00003-of-00006.safetensors", "model.layers.20.mamba.in_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.mamba.dt_bias": "model-00003-of-00006.safetensors", "model.layers.20.mamba.A_log": "model-00003-of-00006.safetensors", "model.layers.20.mamba.D": "model-00003-of-00006.safetensors", "model.layers.20.mamba.out_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.mamba.norm.weight": "model-00003-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.21.block_sparse_moe.router.layer.weight": "model-00003-of-00006.safetensors", "model.layers.21.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors", "model.layers.21.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.21.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.21.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.21.mamba.conv1d.weight": "model-00004-of-00006.safetensors", "model.layers.21.mamba.conv1d.bias": "model-00004-of-00006.safetensors", "model.layers.21.mamba.in_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.mamba.dt_bias": "model-00004-of-00006.safetensors", "model.layers.21.mamba.A_log": "model-00004-of-00006.safetensors", "model.layers.21.mamba.D": "model-00004-of-00006.safetensors", "model.layers.21.mamba.out_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.mamba.norm.weight": "model-00004-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.22.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.22.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.22.mamba.conv1d.weight": "model-00004-of-00006.safetensors", "model.layers.22.mamba.conv1d.bias": "model-00004-of-00006.safetensors", "model.layers.22.mamba.in_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.mamba.dt_bias": "model-00004-of-00006.safetensors", "model.layers.22.mamba.A_log": "model-00004-of-00006.safetensors", "model.layers.22.mamba.D": "model-00004-of-00006.safetensors", "model.layers.22.mamba.out_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.mamba.norm.weight": "model-00004-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.23.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.23.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.23.mamba.conv1d.weight": "model-00004-of-00006.safetensors", "model.layers.23.mamba.conv1d.bias": "model-00004-of-00006.safetensors", "model.layers.23.mamba.in_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.mamba.dt_bias": "model-00004-of-00006.safetensors", "model.layers.23.mamba.A_log": "model-00004-of-00006.safetensors", "model.layers.23.mamba.D": "model-00004-of-00006.safetensors", "model.layers.23.mamba.out_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.mamba.norm.weight": "model-00004-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.24.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.24.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.24.mamba.conv1d.weight": "model-00004-of-00006.safetensors", "model.layers.24.mamba.conv1d.bias": "model-00004-of-00006.safetensors", "model.layers.24.mamba.in_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.mamba.dt_bias": "model-00004-of-00006.safetensors", "model.layers.24.mamba.A_log": "model-00004-of-00006.safetensors", "model.layers.24.mamba.D": "model-00004-of-00006.safetensors", "model.layers.24.mamba.out_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.mamba.norm.weight": "model-00004-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.25.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.25.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.26.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.26.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.26.mamba.conv1d.weight": "model-00004-of-00006.safetensors", "model.layers.26.mamba.conv1d.bias": "model-00004-of-00006.safetensors", "model.layers.26.mamba.in_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.mamba.dt_bias": "model-00004-of-00006.safetensors", "model.layers.26.mamba.A_log": "model-00004-of-00006.safetensors", "model.layers.26.mamba.D": "model-00004-of-00006.safetensors", "model.layers.26.mamba.out_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.mamba.norm.weight": "model-00004-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.27.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.27.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.27.mamba.conv1d.weight": "model-00004-of-00006.safetensors", "model.layers.27.mamba.conv1d.bias": "model-00004-of-00006.safetensors", "model.layers.27.mamba.in_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.mamba.dt_bias": "model-00004-of-00006.safetensors", "model.layers.27.mamba.A_log": "model-00004-of-00006.safetensors", "model.layers.27.mamba.D": "model-00004-of-00006.safetensors", "model.layers.27.mamba.out_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.mamba.norm.weight": "model-00004-of-00006.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.28.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.28.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors", "model.layers.28.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors", "model.layers.28.mamba.conv1d.weight": "model-00004-of-00006.safetensors", "model.layers.28.mamba.conv1d.bias": "model-00004-of-00006.safetensors", "model.layers.28.mamba.in_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.mamba.dt_bias": "model-00004-of-00006.safetensors", "model.layers.28.mamba.A_log": "model-00004-of-00006.safetensors", "model.layers.28.mamba.D": "model-00004-of-00006.safetensors", "model.layers.28.mamba.out_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.mamba.norm.weight": "model-00004-of-00006.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.29.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors", "model.layers.29.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.29.block_sparse_moe.output_linear.weight": "model-00005-of-00006.safetensors", "model.layers.29.shared_mlp.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.29.shared_mlp.output_linear.weight": "model-00005-of-00006.safetensors", "model.layers.29.mamba.conv1d.weight": "model-00005-of-00006.safetensors", "model.layers.29.mamba.conv1d.bias": "model-00005-of-00006.safetensors", "model.layers.29.mamba.in_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.mamba.dt_bias": "model-00005-of-00006.safetensors", "model.layers.29.mamba.A_log": "model-00005-of-00006.safetensors", "model.layers.29.mamba.D": "model-00005-of-00006.safetensors", "model.layers.29.mamba.out_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.mamba.norm.weight": "model-00005-of-00006.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.router.layer.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.output_linear.weight": "model-00005-of-00006.safetensors", "model.layers.30.shared_mlp.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.30.shared_mlp.output_linear.weight": "model-00005-of-00006.safetensors", "model.layers.30.mamba.conv1d.weight": "model-00005-of-00006.safetensors", "model.layers.30.mamba.conv1d.bias": "model-00005-of-00006.safetensors", "model.layers.30.mamba.in_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.mamba.dt_bias": "model-00005-of-00006.safetensors", "model.layers.30.mamba.A_log": "model-00005-of-00006.safetensors", "model.layers.30.mamba.D": "model-00005-of-00006.safetensors", "model.layers.30.mamba.out_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.mamba.norm.weight": "model-00005-of-00006.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.router.layer.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.output_linear.weight": "model-00005-of-00006.safetensors", "model.layers.31.shared_mlp.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.31.shared_mlp.output_linear.weight": "model-00005-of-00006.safetensors", "model.layers.31.mamba.conv1d.weight": "model-00005-of-00006.safetensors", "model.layers.31.mamba.conv1d.bias": "model-00005-of-00006.safetensors", "model.layers.31.mamba.in_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.mamba.dt_bias": "model-00005-of-00006.safetensors", "model.layers.31.mamba.A_log": "model-00005-of-00006.safetensors", "model.layers.31.mamba.D": "model-00005-of-00006.safetensors", "model.layers.31.mamba.out_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.mamba.norm.weight": "model-00005-of-00006.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.32.block_sparse_moe.router.layer.weight": "model-00005-of-00006.safetensors", "model.layers.32.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.32.block_sparse_moe.output_linear.weight": "model-00005-of-00006.safetensors", "model.layers.32.shared_mlp.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.32.shared_mlp.output_linear.weight": "model-00005-of-00006.safetensors", "model.layers.32.mamba.conv1d.weight": "model-00005-of-00006.safetensors", "model.layers.32.mamba.conv1d.bias": "model-00005-of-00006.safetensors", "model.layers.32.mamba.in_proj.weight": "model-00005-of-00006.safetensors", "model.layers.32.mamba.dt_bias": "model-00005-of-00006.safetensors", "model.layers.32.mamba.A_log": "model-00005-of-00006.safetensors", "model.layers.32.mamba.D": "model-00005-of-00006.safetensors", "model.layers.32.mamba.out_proj.weight": "model-00005-of-00006.safetensors", "model.layers.32.mamba.norm.weight": "model-00005-of-00006.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.33.block_sparse_moe.router.layer.weight": "model-00005-of-00006.safetensors", "model.layers.33.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.33.block_sparse_moe.output_linear.weight": "model-00005-of-00006.safetensors", "model.layers.33.shared_mlp.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.33.shared_mlp.output_linear.weight": "model-00005-of-00006.safetensors", "model.layers.33.mamba.conv1d.weight": "model-00005-of-00006.safetensors", "model.layers.33.mamba.conv1d.bias": "model-00005-of-00006.safetensors", "model.layers.33.mamba.in_proj.weight": "model-00005-of-00006.safetensors", "model.layers.33.mamba.dt_bias": "model-00005-of-00006.safetensors", "model.layers.33.mamba.A_log": "model-00005-of-00006.safetensors", "model.layers.33.mamba.D": "model-00005-of-00006.safetensors", "model.layers.33.mamba.out_proj.weight": "model-00005-of-00006.safetensors", "model.layers.33.mamba.norm.weight": "model-00005-of-00006.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.34.block_sparse_moe.router.layer.weight": "model-00005-of-00006.safetensors", "model.layers.34.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.34.block_sparse_moe.output_linear.weight": "model-00005-of-00006.safetensors", "model.layers.34.shared_mlp.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.34.shared_mlp.output_linear.weight": "model-00005-of-00006.safetensors", "model.layers.34.mamba.conv1d.weight": "model-00005-of-00006.safetensors", "model.layers.34.mamba.conv1d.bias": "model-00005-of-00006.safetensors", "model.layers.34.mamba.in_proj.weight": "model-00005-of-00006.safetensors", "model.layers.34.mamba.dt_bias": "model-00005-of-00006.safetensors", "model.layers.34.mamba.A_log": "model-00005-of-00006.safetensors", "model.layers.34.mamba.D": "model-00005-of-00006.safetensors", "model.layers.34.mamba.out_proj.weight": "model-00005-of-00006.safetensors", "model.layers.34.mamba.norm.weight": "model-00005-of-00006.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.35.block_sparse_moe.router.layer.weight": "model-00005-of-00006.safetensors", "model.layers.35.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.35.block_sparse_moe.output_linear.weight": "model-00005-of-00006.safetensors", "model.layers.35.shared_mlp.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.35.shared_mlp.output_linear.weight": "model-00005-of-00006.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.36.block_sparse_moe.router.layer.weight": "model-00005-of-00006.safetensors", "model.layers.36.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors", "model.layers.36.block_sparse_moe.output_linear.weight": "model-00006-of-00006.safetensors", "model.layers.36.shared_mlp.input_linear.weight": "model-00006-of-00006.safetensors", "model.layers.36.shared_mlp.output_linear.weight": "model-00006-of-00006.safetensors", "model.layers.36.mamba.conv1d.weight": "model-00006-of-00006.safetensors", "model.layers.36.mamba.conv1d.bias": "model-00006-of-00006.safetensors", "model.layers.36.mamba.in_proj.weight": "model-00006-of-00006.safetensors", "model.layers.36.mamba.dt_bias": "model-00006-of-00006.safetensors", "model.layers.36.mamba.A_log": "model-00006-of-00006.safetensors", "model.layers.36.mamba.D": "model-00006-of-00006.safetensors", "model.layers.36.mamba.out_proj.weight": "model-00006-of-00006.safetensors", "model.layers.36.mamba.norm.weight": "model-00006-of-00006.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.37.block_sparse_moe.router.layer.weight": "model-00006-of-00006.safetensors", "model.layers.37.block_sparse_moe.input_linear.weight": "model-00006-of-00006.safetensors", "model.layers.37.block_sparse_moe.output_linear.weight": "model-00006-of-00006.safetensors", "model.layers.37.shared_mlp.input_linear.weight": "model-00006-of-00006.safetensors", "model.layers.37.shared_mlp.output_linear.weight": "model-00006-of-00006.safetensors", "model.layers.37.mamba.conv1d.weight": "model-00006-of-00006.safetensors", "model.layers.37.mamba.conv1d.bias": "model-00006-of-00006.safetensors", "model.layers.37.mamba.in_proj.weight": "model-00006-of-00006.safetensors", "model.layers.37.mamba.dt_bias": "model-00006-of-00006.safetensors", "model.layers.37.mamba.A_log": "model-00006-of-00006.safetensors", "model.layers.37.mamba.D": "model-00006-of-00006.safetensors", "model.layers.37.mamba.out_proj.weight": "model-00006-of-00006.safetensors", "model.layers.37.mamba.norm.weight": "model-00006-of-00006.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.38.block_sparse_moe.router.layer.weight": "model-00006-of-00006.safetensors", "model.layers.38.block_sparse_moe.input_linear.weight": "model-00006-of-00006.safetensors", "model.layers.38.block_sparse_moe.output_linear.weight": "model-00006-of-00006.safetensors", "model.layers.38.shared_mlp.input_linear.weight": "model-00006-of-00006.safetensors", "model.layers.38.shared_mlp.output_linear.weight": "model-00006-of-00006.safetensors", "model.layers.38.mamba.conv1d.weight": "model-00006-of-00006.safetensors", "model.layers.38.mamba.conv1d.bias": "model-00006-of-00006.safetensors", "model.layers.38.mamba.in_proj.weight": "model-00006-of-00006.safetensors", "model.layers.38.mamba.dt_bias": "model-00006-of-00006.safetensors", "model.layers.38.mamba.A_log": "model-00006-of-00006.safetensors", "model.layers.38.mamba.D": "model-00006-of-00006.safetensors", "model.layers.38.mamba.out_proj.weight": "model-00006-of-00006.safetensors", "model.layers.38.mamba.norm.weight": "model-00006-of-00006.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.39.block_sparse_moe.router.layer.weight": "model-00006-of-00006.safetensors", "model.layers.39.block_sparse_moe.input_linear.weight": "model-00006-of-00006.safetensors", "model.layers.39.block_sparse_moe.output_linear.weight": "model-00006-of-00006.safetensors", "model.layers.39.shared_mlp.input_linear.weight": "model-00006-of-00006.safetensors", "model.layers.39.shared_mlp.output_linear.weight": "model-00006-of-00006.safetensors", "model.layers.39.mamba.conv1d.weight": "model-00006-of-00006.safetensors", "model.layers.39.mamba.conv1d.bias": "model-00006-of-00006.safetensors", "model.layers.39.mamba.in_proj.weight": "model-00006-of-00006.safetensors", "model.layers.39.mamba.dt_bias": "model-00006-of-00006.safetensors", "model.layers.39.mamba.A_log": "model-00006-of-00006.safetensors", "model.layers.39.mamba.D": "model-00006-of-00006.safetensors", "model.layers.39.mamba.out_proj.weight": "model-00006-of-00006.safetensors", "model.layers.39.mamba.norm.weight": "model-00006-of-00006.safetensors" } }