Falcon-H1-34B-Instruct / model.safetensors.index.json
ybelkada's picture
Upload folder using huggingface_hub
3efc39f verified
{
"metadata": {
"total_size": 67285032448
},
"weight_map": {
"lm_head.weight": "model-00014-of-00014.safetensors",
"model.embed_tokens.weight": "model-00001-of-00014.safetensors",
"model.final_layernorm.weight": "model-00014-of-00014.safetensors",
"model.layers.0.feed_forward.down_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.feed_forward.up_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
"model.layers.0.mamba.A_log": "model-00001-of-00014.safetensors",
"model.layers.0.mamba.D": "model-00001-of-00014.safetensors",
"model.layers.0.mamba.conv1d.bias": "model-00001-of-00014.safetensors",
"model.layers.0.mamba.conv1d.weight": "model-00001-of-00014.safetensors",
"model.layers.0.mamba.dt_bias": "model-00001-of-00014.safetensors",
"model.layers.0.mamba.in_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.mamba.norm.weight": "model-00001-of-00014.safetensors",
"model.layers.0.mamba.out_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.pre_ff_layernorm.weight": "model-00001-of-00014.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.feed_forward.down_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.feed_forward.up_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
"model.layers.1.mamba.A_log": "model-00001-of-00014.safetensors",
"model.layers.1.mamba.D": "model-00001-of-00014.safetensors",
"model.layers.1.mamba.conv1d.bias": "model-00001-of-00014.safetensors",
"model.layers.1.mamba.conv1d.weight": "model-00001-of-00014.safetensors",
"model.layers.1.mamba.dt_bias": "model-00001-of-00014.safetensors",
"model.layers.1.mamba.in_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.mamba.norm.weight": "model-00001-of-00014.safetensors",
"model.layers.1.mamba.out_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.pre_ff_layernorm.weight": "model-00001-of-00014.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.10.feed_forward.down_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.feed_forward.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.feed_forward.up_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.10.mamba.A_log": "model-00003-of-00014.safetensors",
"model.layers.10.mamba.D": "model-00003-of-00014.safetensors",
"model.layers.10.mamba.conv1d.bias": "model-00003-of-00014.safetensors",
"model.layers.10.mamba.conv1d.weight": "model-00003-of-00014.safetensors",
"model.layers.10.mamba.dt_bias": "model-00003-of-00014.safetensors",
"model.layers.10.mamba.in_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.mamba.norm.weight": "model-00003-of-00014.safetensors",
"model.layers.10.mamba.out_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.pre_ff_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.feed_forward.down_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.feed_forward.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.feed_forward.up_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.11.mamba.A_log": "model-00003-of-00014.safetensors",
"model.layers.11.mamba.D": "model-00003-of-00014.safetensors",
"model.layers.11.mamba.conv1d.bias": "model-00003-of-00014.safetensors",
"model.layers.11.mamba.conv1d.weight": "model-00003-of-00014.safetensors",
"model.layers.11.mamba.dt_bias": "model-00003-of-00014.safetensors",
"model.layers.11.mamba.in_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.mamba.norm.weight": "model-00003-of-00014.safetensors",
"model.layers.11.mamba.out_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.pre_ff_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.12.feed_forward.down_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.12.feed_forward.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.12.feed_forward.up_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.12.mamba.A_log": "model-00003-of-00014.safetensors",
"model.layers.12.mamba.D": "model-00003-of-00014.safetensors",
"model.layers.12.mamba.conv1d.bias": "model-00003-of-00014.safetensors",
"model.layers.12.mamba.conv1d.weight": "model-00003-of-00014.safetensors",
"model.layers.12.mamba.dt_bias": "model-00003-of-00014.safetensors",
"model.layers.12.mamba.in_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.12.mamba.norm.weight": "model-00003-of-00014.safetensors",
"model.layers.12.mamba.out_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.12.pre_ff_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.13.feed_forward.down_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.13.feed_forward.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.13.feed_forward.up_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.13.input_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.13.mamba.A_log": "model-00003-of-00014.safetensors",
"model.layers.13.mamba.D": "model-00003-of-00014.safetensors",
"model.layers.13.mamba.conv1d.bias": "model-00003-of-00014.safetensors",
"model.layers.13.mamba.conv1d.weight": "model-00003-of-00014.safetensors",
"model.layers.13.mamba.dt_bias": "model-00003-of-00014.safetensors",
"model.layers.13.mamba.in_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.13.mamba.norm.weight": "model-00003-of-00014.safetensors",
"model.layers.13.mamba.out_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.13.pre_ff_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.14.feed_forward.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.feed_forward.gate_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.feed_forward.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.14.mamba.A_log": "model-00004-of-00014.safetensors",
"model.layers.14.mamba.D": "model-00004-of-00014.safetensors",
"model.layers.14.mamba.conv1d.bias": "model-00004-of-00014.safetensors",
"model.layers.14.mamba.conv1d.weight": "model-00004-of-00014.safetensors",
"model.layers.14.mamba.dt_bias": "model-00004-of-00014.safetensors",
"model.layers.14.mamba.in_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.mamba.norm.weight": "model-00004-of-00014.safetensors",
"model.layers.14.mamba.out_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.pre_ff_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.feed_forward.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.feed_forward.gate_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.feed_forward.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.15.mamba.A_log": "model-00004-of-00014.safetensors",
"model.layers.15.mamba.D": "model-00004-of-00014.safetensors",
"model.layers.15.mamba.conv1d.bias": "model-00004-of-00014.safetensors",
"model.layers.15.mamba.conv1d.weight": "model-00004-of-00014.safetensors",
"model.layers.15.mamba.dt_bias": "model-00004-of-00014.safetensors",
"model.layers.15.mamba.in_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.mamba.norm.weight": "model-00004-of-00014.safetensors",
"model.layers.15.mamba.out_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.pre_ff_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.16.feed_forward.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.16.feed_forward.gate_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.16.feed_forward.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.16.mamba.A_log": "model-00004-of-00014.safetensors",
"model.layers.16.mamba.D": "model-00004-of-00014.safetensors",
"model.layers.16.mamba.conv1d.bias": "model-00004-of-00014.safetensors",
"model.layers.16.mamba.conv1d.weight": "model-00004-of-00014.safetensors",
"model.layers.16.mamba.dt_bias": "model-00004-of-00014.safetensors",
"model.layers.16.mamba.in_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.16.mamba.norm.weight": "model-00004-of-00014.safetensors",
"model.layers.16.mamba.out_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.16.pre_ff_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.17.feed_forward.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.17.feed_forward.gate_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.17.feed_forward.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.17.mamba.A_log": "model-00004-of-00014.safetensors",
"model.layers.17.mamba.D": "model-00004-of-00014.safetensors",
"model.layers.17.mamba.conv1d.bias": "model-00004-of-00014.safetensors",
"model.layers.17.mamba.conv1d.weight": "model-00004-of-00014.safetensors",
"model.layers.17.mamba.dt_bias": "model-00004-of-00014.safetensors",
"model.layers.17.mamba.in_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.17.mamba.norm.weight": "model-00004-of-00014.safetensors",
"model.layers.17.mamba.out_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.17.pre_ff_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.18.feed_forward.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.18.feed_forward.gate_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.18.feed_forward.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.18.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.18.mamba.A_log": "model-00004-of-00014.safetensors",
"model.layers.18.mamba.D": "model-00004-of-00014.safetensors",
"model.layers.18.mamba.conv1d.bias": "model-00004-of-00014.safetensors",
"model.layers.18.mamba.conv1d.weight": "model-00004-of-00014.safetensors",
"model.layers.18.mamba.dt_bias": "model-00004-of-00014.safetensors",
"model.layers.18.mamba.in_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.18.mamba.norm.weight": "model-00004-of-00014.safetensors",
"model.layers.18.mamba.out_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.18.pre_ff_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.19.feed_forward.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.19.feed_forward.gate_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.19.feed_forward.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.19.mamba.A_log": "model-00004-of-00014.safetensors",
"model.layers.19.mamba.D": "model-00004-of-00014.safetensors",
"model.layers.19.mamba.conv1d.bias": "model-00004-of-00014.safetensors",
"model.layers.19.mamba.conv1d.weight": "model-00004-of-00014.safetensors",
"model.layers.19.mamba.dt_bias": "model-00004-of-00014.safetensors",
"model.layers.19.mamba.in_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.19.mamba.norm.weight": "model-00005-of-00014.safetensors",
"model.layers.19.mamba.out_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.19.pre_ff_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.2.feed_forward.down_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.2.feed_forward.up_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.2.mamba.A_log": "model-00002-of-00014.safetensors",
"model.layers.2.mamba.D": "model-00002-of-00014.safetensors",
"model.layers.2.mamba.conv1d.bias": "model-00002-of-00014.safetensors",
"model.layers.2.mamba.conv1d.weight": "model-00002-of-00014.safetensors",
"model.layers.2.mamba.dt_bias": "model-00002-of-00014.safetensors",
"model.layers.2.mamba.in_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.mamba.norm.weight": "model-00002-of-00014.safetensors",
"model.layers.2.mamba.out_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.pre_ff_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.20.feed_forward.down_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.20.feed_forward.gate_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.20.feed_forward.up_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.20.mamba.A_log": "model-00005-of-00014.safetensors",
"model.layers.20.mamba.D": "model-00005-of-00014.safetensors",
"model.layers.20.mamba.conv1d.bias": "model-00005-of-00014.safetensors",
"model.layers.20.mamba.conv1d.weight": "model-00005-of-00014.safetensors",
"model.layers.20.mamba.dt_bias": "model-00005-of-00014.safetensors",
"model.layers.20.mamba.in_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.20.mamba.norm.weight": "model-00005-of-00014.safetensors",
"model.layers.20.mamba.out_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.20.pre_ff_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.21.feed_forward.down_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.21.feed_forward.gate_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.21.feed_forward.up_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.21.mamba.A_log": "model-00005-of-00014.safetensors",
"model.layers.21.mamba.D": "model-00005-of-00014.safetensors",
"model.layers.21.mamba.conv1d.bias": "model-00005-of-00014.safetensors",
"model.layers.21.mamba.conv1d.weight": "model-00005-of-00014.safetensors",
"model.layers.21.mamba.dt_bias": "model-00005-of-00014.safetensors",
"model.layers.21.mamba.in_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.21.mamba.norm.weight": "model-00005-of-00014.safetensors",
"model.layers.21.mamba.out_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.21.pre_ff_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.22.feed_forward.down_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.22.feed_forward.gate_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.22.feed_forward.up_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.22.mamba.A_log": "model-00005-of-00014.safetensors",
"model.layers.22.mamba.D": "model-00005-of-00014.safetensors",
"model.layers.22.mamba.conv1d.bias": "model-00005-of-00014.safetensors",
"model.layers.22.mamba.conv1d.weight": "model-00005-of-00014.safetensors",
"model.layers.22.mamba.dt_bias": "model-00005-of-00014.safetensors",
"model.layers.22.mamba.in_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.22.mamba.norm.weight": "model-00005-of-00014.safetensors",
"model.layers.22.mamba.out_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.22.pre_ff_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.23.feed_forward.down_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.23.feed_forward.gate_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.23.feed_forward.up_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.23.input_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.23.mamba.A_log": "model-00005-of-00014.safetensors",
"model.layers.23.mamba.D": "model-00005-of-00014.safetensors",
"model.layers.23.mamba.conv1d.bias": "model-00005-of-00014.safetensors",
"model.layers.23.mamba.conv1d.weight": "model-00005-of-00014.safetensors",
"model.layers.23.mamba.dt_bias": "model-00005-of-00014.safetensors",
"model.layers.23.mamba.in_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.23.mamba.norm.weight": "model-00005-of-00014.safetensors",
"model.layers.23.mamba.out_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.23.pre_ff_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.24.feed_forward.down_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.24.feed_forward.gate_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.24.feed_forward.up_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.24.input_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.24.mamba.A_log": "model-00005-of-00014.safetensors",
"model.layers.24.mamba.D": "model-00005-of-00014.safetensors",
"model.layers.24.mamba.conv1d.bias": "model-00005-of-00014.safetensors",
"model.layers.24.mamba.conv1d.weight": "model-00005-of-00014.safetensors",
"model.layers.24.mamba.dt_bias": "model-00005-of-00014.safetensors",
"model.layers.24.mamba.in_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.24.mamba.norm.weight": "model-00005-of-00014.safetensors",
"model.layers.24.mamba.out_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.24.pre_ff_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.25.feed_forward.down_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.25.feed_forward.gate_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.25.feed_forward.up_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.25.mamba.A_log": "model-00006-of-00014.safetensors",
"model.layers.25.mamba.D": "model-00006-of-00014.safetensors",
"model.layers.25.mamba.conv1d.bias": "model-00006-of-00014.safetensors",
"model.layers.25.mamba.conv1d.weight": "model-00006-of-00014.safetensors",
"model.layers.25.mamba.dt_bias": "model-00006-of-00014.safetensors",
"model.layers.25.mamba.in_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.25.mamba.norm.weight": "model-00006-of-00014.safetensors",
"model.layers.25.mamba.out_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.25.pre_ff_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.26.feed_forward.down_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.26.feed_forward.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.26.feed_forward.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.26.mamba.A_log": "model-00006-of-00014.safetensors",
"model.layers.26.mamba.D": "model-00006-of-00014.safetensors",
"model.layers.26.mamba.conv1d.bias": "model-00006-of-00014.safetensors",
"model.layers.26.mamba.conv1d.weight": "model-00006-of-00014.safetensors",
"model.layers.26.mamba.dt_bias": "model-00006-of-00014.safetensors",
"model.layers.26.mamba.in_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.26.mamba.norm.weight": "model-00006-of-00014.safetensors",
"model.layers.26.mamba.out_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.26.pre_ff_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.27.feed_forward.down_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.27.feed_forward.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.27.feed_forward.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.27.mamba.A_log": "model-00006-of-00014.safetensors",
"model.layers.27.mamba.D": "model-00006-of-00014.safetensors",
"model.layers.27.mamba.conv1d.bias": "model-00006-of-00014.safetensors",
"model.layers.27.mamba.conv1d.weight": "model-00006-of-00014.safetensors",
"model.layers.27.mamba.dt_bias": "model-00006-of-00014.safetensors",
"model.layers.27.mamba.in_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.27.mamba.norm.weight": "model-00006-of-00014.safetensors",
"model.layers.27.mamba.out_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.27.pre_ff_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.28.feed_forward.down_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.28.feed_forward.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.28.feed_forward.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.28.input_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.28.mamba.A_log": "model-00006-of-00014.safetensors",
"model.layers.28.mamba.D": "model-00006-of-00014.safetensors",
"model.layers.28.mamba.conv1d.bias": "model-00006-of-00014.safetensors",
"model.layers.28.mamba.conv1d.weight": "model-00006-of-00014.safetensors",
"model.layers.28.mamba.dt_bias": "model-00006-of-00014.safetensors",
"model.layers.28.mamba.in_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.28.mamba.norm.weight": "model-00006-of-00014.safetensors",
"model.layers.28.mamba.out_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.28.pre_ff_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.29.feed_forward.down_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.29.feed_forward.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.29.feed_forward.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.29.input_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.29.mamba.A_log": "model-00006-of-00014.safetensors",
"model.layers.29.mamba.D": "model-00006-of-00014.safetensors",
"model.layers.29.mamba.conv1d.bias": "model-00006-of-00014.safetensors",
"model.layers.29.mamba.conv1d.weight": "model-00006-of-00014.safetensors",
"model.layers.29.mamba.dt_bias": "model-00006-of-00014.safetensors",
"model.layers.29.mamba.in_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.29.mamba.norm.weight": "model-00006-of-00014.safetensors",
"model.layers.29.mamba.out_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.29.pre_ff_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.3.feed_forward.down_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.feed_forward.gate_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.feed_forward.up_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.3.mamba.A_log": "model-00002-of-00014.safetensors",
"model.layers.3.mamba.D": "model-00002-of-00014.safetensors",
"model.layers.3.mamba.conv1d.bias": "model-00002-of-00014.safetensors",
"model.layers.3.mamba.conv1d.weight": "model-00002-of-00014.safetensors",
"model.layers.3.mamba.dt_bias": "model-00002-of-00014.safetensors",
"model.layers.3.mamba.in_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.mamba.norm.weight": "model-00002-of-00014.safetensors",
"model.layers.3.mamba.out_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.pre_ff_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.30.feed_forward.down_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.30.feed_forward.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.30.feed_forward.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.30.input_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.30.mamba.A_log": "model-00006-of-00014.safetensors",
"model.layers.30.mamba.D": "model-00006-of-00014.safetensors",
"model.layers.30.mamba.conv1d.bias": "model-00006-of-00014.safetensors",
"model.layers.30.mamba.conv1d.weight": "model-00006-of-00014.safetensors",
"model.layers.30.mamba.dt_bias": "model-00006-of-00014.safetensors",
"model.layers.30.mamba.in_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.30.mamba.norm.weight": "model-00006-of-00014.safetensors",
"model.layers.30.mamba.out_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.30.pre_ff_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.31.feed_forward.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.31.feed_forward.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.31.feed_forward.up_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.31.mamba.A_log": "model-00007-of-00014.safetensors",
"model.layers.31.mamba.D": "model-00007-of-00014.safetensors",
"model.layers.31.mamba.conv1d.bias": "model-00007-of-00014.safetensors",
"model.layers.31.mamba.conv1d.weight": "model-00007-of-00014.safetensors",
"model.layers.31.mamba.dt_bias": "model-00007-of-00014.safetensors",
"model.layers.31.mamba.in_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.31.mamba.norm.weight": "model-00007-of-00014.safetensors",
"model.layers.31.mamba.out_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.31.pre_ff_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.32.feed_forward.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.32.feed_forward.gate_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.32.feed_forward.up_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.32.mamba.A_log": "model-00007-of-00014.safetensors",
"model.layers.32.mamba.D": "model-00007-of-00014.safetensors",
"model.layers.32.mamba.conv1d.bias": "model-00007-of-00014.safetensors",
"model.layers.32.mamba.conv1d.weight": "model-00007-of-00014.safetensors",
"model.layers.32.mamba.dt_bias": "model-00007-of-00014.safetensors",
"model.layers.32.mamba.in_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.32.mamba.norm.weight": "model-00007-of-00014.safetensors",
"model.layers.32.mamba.out_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.32.pre_ff_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.33.feed_forward.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.33.feed_forward.gate_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.33.feed_forward.up_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.33.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.33.mamba.A_log": "model-00007-of-00014.safetensors",
"model.layers.33.mamba.D": "model-00007-of-00014.safetensors",
"model.layers.33.mamba.conv1d.bias": "model-00007-of-00014.safetensors",
"model.layers.33.mamba.conv1d.weight": "model-00007-of-00014.safetensors",
"model.layers.33.mamba.dt_bias": "model-00007-of-00014.safetensors",
"model.layers.33.mamba.in_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.33.mamba.norm.weight": "model-00007-of-00014.safetensors",
"model.layers.33.mamba.out_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.33.pre_ff_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.34.feed_forward.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.34.feed_forward.gate_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.34.feed_forward.up_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.34.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.34.mamba.A_log": "model-00007-of-00014.safetensors",
"model.layers.34.mamba.D": "model-00007-of-00014.safetensors",
"model.layers.34.mamba.conv1d.bias": "model-00007-of-00014.safetensors",
"model.layers.34.mamba.conv1d.weight": "model-00007-of-00014.safetensors",
"model.layers.34.mamba.dt_bias": "model-00007-of-00014.safetensors",
"model.layers.34.mamba.in_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.34.mamba.norm.weight": "model-00007-of-00014.safetensors",
"model.layers.34.mamba.out_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.34.pre_ff_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.35.feed_forward.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.35.feed_forward.gate_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.35.feed_forward.up_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.35.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.35.mamba.A_log": "model-00007-of-00014.safetensors",
"model.layers.35.mamba.D": "model-00007-of-00014.safetensors",
"model.layers.35.mamba.conv1d.bias": "model-00007-of-00014.safetensors",
"model.layers.35.mamba.conv1d.weight": "model-00007-of-00014.safetensors",
"model.layers.35.mamba.dt_bias": "model-00007-of-00014.safetensors",
"model.layers.35.mamba.in_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.35.mamba.norm.weight": "model-00007-of-00014.safetensors",
"model.layers.35.mamba.out_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.35.pre_ff_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.36.feed_forward.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.36.feed_forward.gate_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.36.feed_forward.up_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.36.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.36.mamba.A_log": "model-00007-of-00014.safetensors",
"model.layers.36.mamba.D": "model-00007-of-00014.safetensors",
"model.layers.36.mamba.conv1d.bias": "model-00007-of-00014.safetensors",
"model.layers.36.mamba.conv1d.weight": "model-00007-of-00014.safetensors",
"model.layers.36.mamba.dt_bias": "model-00007-of-00014.safetensors",
"model.layers.36.mamba.in_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.36.mamba.norm.weight": "model-00007-of-00014.safetensors",
"model.layers.36.mamba.out_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.36.pre_ff_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.36.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.36.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.36.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.36.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.37.feed_forward.down_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.37.feed_forward.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.37.feed_forward.up_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.37.mamba.A_log": "model-00008-of-00014.safetensors",
"model.layers.37.mamba.D": "model-00008-of-00014.safetensors",
"model.layers.37.mamba.conv1d.bias": "model-00008-of-00014.safetensors",
"model.layers.37.mamba.conv1d.weight": "model-00008-of-00014.safetensors",
"model.layers.37.mamba.dt_bias": "model-00008-of-00014.safetensors",
"model.layers.37.mamba.in_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.37.mamba.norm.weight": "model-00008-of-00014.safetensors",
"model.layers.37.mamba.out_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.37.pre_ff_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.38.feed_forward.down_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.38.feed_forward.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.38.feed_forward.up_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.38.input_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.38.mamba.A_log": "model-00008-of-00014.safetensors",
"model.layers.38.mamba.D": "model-00008-of-00014.safetensors",
"model.layers.38.mamba.conv1d.bias": "model-00008-of-00014.safetensors",
"model.layers.38.mamba.conv1d.weight": "model-00008-of-00014.safetensors",
"model.layers.38.mamba.dt_bias": "model-00008-of-00014.safetensors",
"model.layers.38.mamba.in_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.38.mamba.norm.weight": "model-00008-of-00014.safetensors",
"model.layers.38.mamba.out_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.38.pre_ff_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.39.feed_forward.down_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.39.feed_forward.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.39.feed_forward.up_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.39.input_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.39.mamba.A_log": "model-00008-of-00014.safetensors",
"model.layers.39.mamba.D": "model-00008-of-00014.safetensors",
"model.layers.39.mamba.conv1d.bias": "model-00008-of-00014.safetensors",
"model.layers.39.mamba.conv1d.weight": "model-00008-of-00014.safetensors",
"model.layers.39.mamba.dt_bias": "model-00008-of-00014.safetensors",
"model.layers.39.mamba.in_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.39.mamba.norm.weight": "model-00008-of-00014.safetensors",
"model.layers.39.mamba.out_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.39.pre_ff_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.39.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.39.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.39.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.39.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.4.feed_forward.down_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.4.feed_forward.gate_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.4.feed_forward.up_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.4.mamba.A_log": "model-00002-of-00014.safetensors",
"model.layers.4.mamba.D": "model-00002-of-00014.safetensors",
"model.layers.4.mamba.conv1d.bias": "model-00002-of-00014.safetensors",
"model.layers.4.mamba.conv1d.weight": "model-00002-of-00014.safetensors",
"model.layers.4.mamba.dt_bias": "model-00002-of-00014.safetensors",
"model.layers.4.mamba.in_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.4.mamba.norm.weight": "model-00002-of-00014.safetensors",
"model.layers.4.mamba.out_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.4.pre_ff_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.40.feed_forward.down_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.40.feed_forward.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.40.feed_forward.up_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.40.input_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.40.mamba.A_log": "model-00008-of-00014.safetensors",
"model.layers.40.mamba.D": "model-00008-of-00014.safetensors",
"model.layers.40.mamba.conv1d.bias": "model-00008-of-00014.safetensors",
"model.layers.40.mamba.conv1d.weight": "model-00008-of-00014.safetensors",
"model.layers.40.mamba.dt_bias": "model-00008-of-00014.safetensors",
"model.layers.40.mamba.in_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.40.mamba.norm.weight": "model-00008-of-00014.safetensors",
"model.layers.40.mamba.out_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.40.pre_ff_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.40.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.40.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.40.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.40.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.41.feed_forward.down_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.41.feed_forward.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.41.feed_forward.up_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.41.input_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.41.mamba.A_log": "model-00008-of-00014.safetensors",
"model.layers.41.mamba.D": "model-00008-of-00014.safetensors",
"model.layers.41.mamba.conv1d.bias": "model-00008-of-00014.safetensors",
"model.layers.41.mamba.conv1d.weight": "model-00008-of-00014.safetensors",
"model.layers.41.mamba.dt_bias": "model-00008-of-00014.safetensors",
"model.layers.41.mamba.in_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.41.mamba.norm.weight": "model-00008-of-00014.safetensors",
"model.layers.41.mamba.out_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.41.pre_ff_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.41.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.41.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.41.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.41.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.42.feed_forward.down_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.42.feed_forward.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.42.feed_forward.up_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.42.mamba.A_log": "model-00008-of-00014.safetensors",
"model.layers.42.mamba.D": "model-00008-of-00014.safetensors",
"model.layers.42.mamba.conv1d.bias": "model-00008-of-00014.safetensors",
"model.layers.42.mamba.conv1d.weight": "model-00008-of-00014.safetensors",
"model.layers.42.mamba.dt_bias": "model-00008-of-00014.safetensors",
"model.layers.42.mamba.in_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.42.mamba.norm.weight": "model-00009-of-00014.safetensors",
"model.layers.42.mamba.out_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.42.pre_ff_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.43.feed_forward.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.43.feed_forward.gate_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.43.feed_forward.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.43.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.43.mamba.A_log": "model-00009-of-00014.safetensors",
"model.layers.43.mamba.D": "model-00009-of-00014.safetensors",
"model.layers.43.mamba.conv1d.bias": "model-00009-of-00014.safetensors",
"model.layers.43.mamba.conv1d.weight": "model-00009-of-00014.safetensors",
"model.layers.43.mamba.dt_bias": "model-00009-of-00014.safetensors",
"model.layers.43.mamba.in_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.43.mamba.norm.weight": "model-00009-of-00014.safetensors",
"model.layers.43.mamba.out_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.43.pre_ff_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.44.feed_forward.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.44.feed_forward.gate_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.44.feed_forward.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.44.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.44.mamba.A_log": "model-00009-of-00014.safetensors",
"model.layers.44.mamba.D": "model-00009-of-00014.safetensors",
"model.layers.44.mamba.conv1d.bias": "model-00009-of-00014.safetensors",
"model.layers.44.mamba.conv1d.weight": "model-00009-of-00014.safetensors",
"model.layers.44.mamba.dt_bias": "model-00009-of-00014.safetensors",
"model.layers.44.mamba.in_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.44.mamba.norm.weight": "model-00009-of-00014.safetensors",
"model.layers.44.mamba.out_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.44.pre_ff_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.44.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.44.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.44.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.44.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.45.feed_forward.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.45.feed_forward.gate_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.45.feed_forward.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.45.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.45.mamba.A_log": "model-00009-of-00014.safetensors",
"model.layers.45.mamba.D": "model-00009-of-00014.safetensors",
"model.layers.45.mamba.conv1d.bias": "model-00009-of-00014.safetensors",
"model.layers.45.mamba.conv1d.weight": "model-00009-of-00014.safetensors",
"model.layers.45.mamba.dt_bias": "model-00009-of-00014.safetensors",
"model.layers.45.mamba.in_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.45.mamba.norm.weight": "model-00009-of-00014.safetensors",
"model.layers.45.mamba.out_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.45.pre_ff_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.45.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.45.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.45.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.45.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.46.feed_forward.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.46.feed_forward.gate_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.46.feed_forward.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.46.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.46.mamba.A_log": "model-00009-of-00014.safetensors",
"model.layers.46.mamba.D": "model-00009-of-00014.safetensors",
"model.layers.46.mamba.conv1d.bias": "model-00009-of-00014.safetensors",
"model.layers.46.mamba.conv1d.weight": "model-00009-of-00014.safetensors",
"model.layers.46.mamba.dt_bias": "model-00009-of-00014.safetensors",
"model.layers.46.mamba.in_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.46.mamba.norm.weight": "model-00009-of-00014.safetensors",
"model.layers.46.mamba.out_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.46.pre_ff_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.46.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.46.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.46.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.46.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.47.feed_forward.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.47.feed_forward.gate_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.47.feed_forward.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.47.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.47.mamba.A_log": "model-00009-of-00014.safetensors",
"model.layers.47.mamba.D": "model-00009-of-00014.safetensors",
"model.layers.47.mamba.conv1d.bias": "model-00009-of-00014.safetensors",
"model.layers.47.mamba.conv1d.weight": "model-00009-of-00014.safetensors",
"model.layers.47.mamba.dt_bias": "model-00009-of-00014.safetensors",
"model.layers.47.mamba.in_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.47.mamba.norm.weight": "model-00009-of-00014.safetensors",
"model.layers.47.mamba.out_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.47.pre_ff_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.47.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.47.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.47.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.47.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.48.feed_forward.down_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.48.feed_forward.gate_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.48.feed_forward.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.48.input_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.48.mamba.A_log": "model-00010-of-00014.safetensors",
"model.layers.48.mamba.D": "model-00010-of-00014.safetensors",
"model.layers.48.mamba.conv1d.bias": "model-00010-of-00014.safetensors",
"model.layers.48.mamba.conv1d.weight": "model-00010-of-00014.safetensors",
"model.layers.48.mamba.dt_bias": "model-00010-of-00014.safetensors",
"model.layers.48.mamba.in_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.48.mamba.norm.weight": "model-00010-of-00014.safetensors",
"model.layers.48.mamba.out_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.48.pre_ff_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.49.feed_forward.down_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.49.feed_forward.gate_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.49.feed_forward.up_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.49.input_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.49.mamba.A_log": "model-00010-of-00014.safetensors",
"model.layers.49.mamba.D": "model-00010-of-00014.safetensors",
"model.layers.49.mamba.conv1d.bias": "model-00010-of-00014.safetensors",
"model.layers.49.mamba.conv1d.weight": "model-00010-of-00014.safetensors",
"model.layers.49.mamba.dt_bias": "model-00010-of-00014.safetensors",
"model.layers.49.mamba.in_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.49.mamba.norm.weight": "model-00010-of-00014.safetensors",
"model.layers.49.mamba.out_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.49.pre_ff_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.49.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.49.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.49.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.49.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.5.feed_forward.down_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.5.feed_forward.gate_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.5.feed_forward.up_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.5.mamba.A_log": "model-00002-of-00014.safetensors",
"model.layers.5.mamba.D": "model-00002-of-00014.safetensors",
"model.layers.5.mamba.conv1d.bias": "model-00002-of-00014.safetensors",
"model.layers.5.mamba.conv1d.weight": "model-00002-of-00014.safetensors",
"model.layers.5.mamba.dt_bias": "model-00002-of-00014.safetensors",
"model.layers.5.mamba.in_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.5.mamba.norm.weight": "model-00002-of-00014.safetensors",
"model.layers.5.mamba.out_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.5.pre_ff_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.50.feed_forward.down_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.50.feed_forward.gate_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.50.feed_forward.up_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.50.input_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.50.mamba.A_log": "model-00010-of-00014.safetensors",
"model.layers.50.mamba.D": "model-00010-of-00014.safetensors",
"model.layers.50.mamba.conv1d.bias": "model-00010-of-00014.safetensors",
"model.layers.50.mamba.conv1d.weight": "model-00010-of-00014.safetensors",
"model.layers.50.mamba.dt_bias": "model-00010-of-00014.safetensors",
"model.layers.50.mamba.in_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.50.mamba.norm.weight": "model-00010-of-00014.safetensors",
"model.layers.50.mamba.out_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.50.pre_ff_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.50.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.50.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.50.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.50.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.51.feed_forward.down_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.51.feed_forward.gate_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.51.feed_forward.up_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.51.input_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.51.mamba.A_log": "model-00010-of-00014.safetensors",
"model.layers.51.mamba.D": "model-00010-of-00014.safetensors",
"model.layers.51.mamba.conv1d.bias": "model-00010-of-00014.safetensors",
"model.layers.51.mamba.conv1d.weight": "model-00010-of-00014.safetensors",
"model.layers.51.mamba.dt_bias": "model-00010-of-00014.safetensors",
"model.layers.51.mamba.in_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.51.mamba.norm.weight": "model-00010-of-00014.safetensors",
"model.layers.51.mamba.out_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.51.pre_ff_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.51.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.51.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.51.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.51.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.52.feed_forward.down_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.52.feed_forward.gate_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.52.feed_forward.up_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.52.input_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.52.mamba.A_log": "model-00010-of-00014.safetensors",
"model.layers.52.mamba.D": "model-00010-of-00014.safetensors",
"model.layers.52.mamba.conv1d.bias": "model-00010-of-00014.safetensors",
"model.layers.52.mamba.conv1d.weight": "model-00010-of-00014.safetensors",
"model.layers.52.mamba.dt_bias": "model-00010-of-00014.safetensors",
"model.layers.52.mamba.in_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.52.mamba.norm.weight": "model-00010-of-00014.safetensors",
"model.layers.52.mamba.out_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.52.pre_ff_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.52.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.52.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.52.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.52.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.53.feed_forward.down_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.53.feed_forward.gate_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.53.feed_forward.up_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.53.input_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.53.mamba.A_log": "model-00010-of-00014.safetensors",
"model.layers.53.mamba.D": "model-00010-of-00014.safetensors",
"model.layers.53.mamba.conv1d.bias": "model-00010-of-00014.safetensors",
"model.layers.53.mamba.conv1d.weight": "model-00010-of-00014.safetensors",
"model.layers.53.mamba.dt_bias": "model-00010-of-00014.safetensors",
"model.layers.53.mamba.in_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.53.mamba.norm.weight": "model-00010-of-00014.safetensors",
"model.layers.53.mamba.out_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.53.pre_ff_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.53.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.53.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.53.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.53.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.54.feed_forward.down_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.54.feed_forward.gate_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.54.feed_forward.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.54.input_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.54.mamba.A_log": "model-00011-of-00014.safetensors",
"model.layers.54.mamba.D": "model-00011-of-00014.safetensors",
"model.layers.54.mamba.conv1d.bias": "model-00011-of-00014.safetensors",
"model.layers.54.mamba.conv1d.weight": "model-00011-of-00014.safetensors",
"model.layers.54.mamba.dt_bias": "model-00011-of-00014.safetensors",
"model.layers.54.mamba.in_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.54.mamba.norm.weight": "model-00011-of-00014.safetensors",
"model.layers.54.mamba.out_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.54.pre_ff_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.54.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.54.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.54.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.54.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.55.feed_forward.down_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.55.feed_forward.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.55.feed_forward.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.55.input_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.55.mamba.A_log": "model-00011-of-00014.safetensors",
"model.layers.55.mamba.D": "model-00011-of-00014.safetensors",
"model.layers.55.mamba.conv1d.bias": "model-00011-of-00014.safetensors",
"model.layers.55.mamba.conv1d.weight": "model-00011-of-00014.safetensors",
"model.layers.55.mamba.dt_bias": "model-00011-of-00014.safetensors",
"model.layers.55.mamba.in_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.55.mamba.norm.weight": "model-00011-of-00014.safetensors",
"model.layers.55.mamba.out_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.55.pre_ff_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.55.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.55.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.55.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.55.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.56.feed_forward.down_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.56.feed_forward.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.56.feed_forward.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.56.input_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.56.mamba.A_log": "model-00011-of-00014.safetensors",
"model.layers.56.mamba.D": "model-00011-of-00014.safetensors",
"model.layers.56.mamba.conv1d.bias": "model-00011-of-00014.safetensors",
"model.layers.56.mamba.conv1d.weight": "model-00011-of-00014.safetensors",
"model.layers.56.mamba.dt_bias": "model-00011-of-00014.safetensors",
"model.layers.56.mamba.in_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.56.mamba.norm.weight": "model-00011-of-00014.safetensors",
"model.layers.56.mamba.out_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.56.pre_ff_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.56.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.56.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.56.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.56.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.57.feed_forward.down_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.57.feed_forward.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.57.feed_forward.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.57.input_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.57.mamba.A_log": "model-00011-of-00014.safetensors",
"model.layers.57.mamba.D": "model-00011-of-00014.safetensors",
"model.layers.57.mamba.conv1d.bias": "model-00011-of-00014.safetensors",
"model.layers.57.mamba.conv1d.weight": "model-00011-of-00014.safetensors",
"model.layers.57.mamba.dt_bias": "model-00011-of-00014.safetensors",
"model.layers.57.mamba.in_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.57.mamba.norm.weight": "model-00011-of-00014.safetensors",
"model.layers.57.mamba.out_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.57.pre_ff_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.57.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.57.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.57.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.57.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.58.feed_forward.down_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.58.feed_forward.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.58.feed_forward.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.58.input_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.58.mamba.A_log": "model-00011-of-00014.safetensors",
"model.layers.58.mamba.D": "model-00011-of-00014.safetensors",
"model.layers.58.mamba.conv1d.bias": "model-00011-of-00014.safetensors",
"model.layers.58.mamba.conv1d.weight": "model-00011-of-00014.safetensors",
"model.layers.58.mamba.dt_bias": "model-00011-of-00014.safetensors",
"model.layers.58.mamba.in_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.58.mamba.norm.weight": "model-00011-of-00014.safetensors",
"model.layers.58.mamba.out_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.58.pre_ff_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.58.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.58.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.58.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.58.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.59.feed_forward.down_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.59.feed_forward.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.59.feed_forward.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.59.input_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.59.mamba.A_log": "model-00011-of-00014.safetensors",
"model.layers.59.mamba.D": "model-00011-of-00014.safetensors",
"model.layers.59.mamba.conv1d.bias": "model-00011-of-00014.safetensors",
"model.layers.59.mamba.conv1d.weight": "model-00011-of-00014.safetensors",
"model.layers.59.mamba.dt_bias": "model-00011-of-00014.safetensors",
"model.layers.59.mamba.in_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.59.mamba.norm.weight": "model-00011-of-00014.safetensors",
"model.layers.59.mamba.out_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.59.pre_ff_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.59.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.59.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.59.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.59.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.6.feed_forward.down_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.6.feed_forward.gate_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.6.feed_forward.up_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.6.mamba.A_log": "model-00002-of-00014.safetensors",
"model.layers.6.mamba.D": "model-00002-of-00014.safetensors",
"model.layers.6.mamba.conv1d.bias": "model-00002-of-00014.safetensors",
"model.layers.6.mamba.conv1d.weight": "model-00002-of-00014.safetensors",
"model.layers.6.mamba.dt_bias": "model-00002-of-00014.safetensors",
"model.layers.6.mamba.in_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.6.mamba.norm.weight": "model-00002-of-00014.safetensors",
"model.layers.6.mamba.out_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.6.pre_ff_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.60.feed_forward.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.60.feed_forward.gate_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.60.feed_forward.up_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.60.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.60.mamba.A_log": "model-00012-of-00014.safetensors",
"model.layers.60.mamba.D": "model-00012-of-00014.safetensors",
"model.layers.60.mamba.conv1d.bias": "model-00012-of-00014.safetensors",
"model.layers.60.mamba.conv1d.weight": "model-00012-of-00014.safetensors",
"model.layers.60.mamba.dt_bias": "model-00012-of-00014.safetensors",
"model.layers.60.mamba.in_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.60.mamba.norm.weight": "model-00012-of-00014.safetensors",
"model.layers.60.mamba.out_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.60.pre_ff_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.60.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.60.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.60.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.60.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.61.feed_forward.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.61.feed_forward.gate_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.61.feed_forward.up_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.61.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.61.mamba.A_log": "model-00012-of-00014.safetensors",
"model.layers.61.mamba.D": "model-00012-of-00014.safetensors",
"model.layers.61.mamba.conv1d.bias": "model-00012-of-00014.safetensors",
"model.layers.61.mamba.conv1d.weight": "model-00012-of-00014.safetensors",
"model.layers.61.mamba.dt_bias": "model-00012-of-00014.safetensors",
"model.layers.61.mamba.in_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.61.mamba.norm.weight": "model-00012-of-00014.safetensors",
"model.layers.61.mamba.out_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.61.pre_ff_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.61.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.61.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.61.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.61.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.62.feed_forward.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.62.feed_forward.gate_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.62.feed_forward.up_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.62.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.62.mamba.A_log": "model-00012-of-00014.safetensors",
"model.layers.62.mamba.D": "model-00012-of-00014.safetensors",
"model.layers.62.mamba.conv1d.bias": "model-00012-of-00014.safetensors",
"model.layers.62.mamba.conv1d.weight": "model-00012-of-00014.safetensors",
"model.layers.62.mamba.dt_bias": "model-00012-of-00014.safetensors",
"model.layers.62.mamba.in_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.62.mamba.norm.weight": "model-00012-of-00014.safetensors",
"model.layers.62.mamba.out_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.62.pre_ff_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.62.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.62.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.62.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.62.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.63.feed_forward.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.63.feed_forward.gate_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.63.feed_forward.up_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.63.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.63.mamba.A_log": "model-00012-of-00014.safetensors",
"model.layers.63.mamba.D": "model-00012-of-00014.safetensors",
"model.layers.63.mamba.conv1d.bias": "model-00012-of-00014.safetensors",
"model.layers.63.mamba.conv1d.weight": "model-00012-of-00014.safetensors",
"model.layers.63.mamba.dt_bias": "model-00012-of-00014.safetensors",
"model.layers.63.mamba.in_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.63.mamba.norm.weight": "model-00012-of-00014.safetensors",
"model.layers.63.mamba.out_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.63.pre_ff_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.63.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.63.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.63.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.63.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.64.feed_forward.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.64.feed_forward.gate_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.64.feed_forward.up_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.64.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.64.mamba.A_log": "model-00012-of-00014.safetensors",
"model.layers.64.mamba.D": "model-00012-of-00014.safetensors",
"model.layers.64.mamba.conv1d.bias": "model-00012-of-00014.safetensors",
"model.layers.64.mamba.conv1d.weight": "model-00012-of-00014.safetensors",
"model.layers.64.mamba.dt_bias": "model-00012-of-00014.safetensors",
"model.layers.64.mamba.in_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.64.mamba.norm.weight": "model-00012-of-00014.safetensors",
"model.layers.64.mamba.out_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.64.pre_ff_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.64.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.64.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.64.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.64.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.65.feed_forward.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.65.feed_forward.gate_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.65.feed_forward.up_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.65.input_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.65.mamba.A_log": "model-00012-of-00014.safetensors",
"model.layers.65.mamba.D": "model-00012-of-00014.safetensors",
"model.layers.65.mamba.conv1d.bias": "model-00012-of-00014.safetensors",
"model.layers.65.mamba.conv1d.weight": "model-00012-of-00014.safetensors",
"model.layers.65.mamba.dt_bias": "model-00012-of-00014.safetensors",
"model.layers.65.mamba.in_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.65.mamba.norm.weight": "model-00013-of-00014.safetensors",
"model.layers.65.mamba.out_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.65.pre_ff_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.65.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.65.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.65.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.65.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.66.feed_forward.down_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.66.feed_forward.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.66.feed_forward.up_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.66.input_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.66.mamba.A_log": "model-00013-of-00014.safetensors",
"model.layers.66.mamba.D": "model-00013-of-00014.safetensors",
"model.layers.66.mamba.conv1d.bias": "model-00013-of-00014.safetensors",
"model.layers.66.mamba.conv1d.weight": "model-00013-of-00014.safetensors",
"model.layers.66.mamba.dt_bias": "model-00013-of-00014.safetensors",
"model.layers.66.mamba.in_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.66.mamba.norm.weight": "model-00013-of-00014.safetensors",
"model.layers.66.mamba.out_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.66.pre_ff_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.66.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.66.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.66.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.66.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.67.feed_forward.down_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.67.feed_forward.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.67.feed_forward.up_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.67.input_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.67.mamba.A_log": "model-00013-of-00014.safetensors",
"model.layers.67.mamba.D": "model-00013-of-00014.safetensors",
"model.layers.67.mamba.conv1d.bias": "model-00013-of-00014.safetensors",
"model.layers.67.mamba.conv1d.weight": "model-00013-of-00014.safetensors",
"model.layers.67.mamba.dt_bias": "model-00013-of-00014.safetensors",
"model.layers.67.mamba.in_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.67.mamba.norm.weight": "model-00013-of-00014.safetensors",
"model.layers.67.mamba.out_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.67.pre_ff_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.67.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.67.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.67.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.67.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.68.feed_forward.down_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.68.feed_forward.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.68.feed_forward.up_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.68.input_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.68.mamba.A_log": "model-00013-of-00014.safetensors",
"model.layers.68.mamba.D": "model-00013-of-00014.safetensors",
"model.layers.68.mamba.conv1d.bias": "model-00013-of-00014.safetensors",
"model.layers.68.mamba.conv1d.weight": "model-00013-of-00014.safetensors",
"model.layers.68.mamba.dt_bias": "model-00013-of-00014.safetensors",
"model.layers.68.mamba.in_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.68.mamba.norm.weight": "model-00013-of-00014.safetensors",
"model.layers.68.mamba.out_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.68.pre_ff_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.68.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.68.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.68.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.68.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.69.feed_forward.down_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.69.feed_forward.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.69.feed_forward.up_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.69.input_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.69.mamba.A_log": "model-00013-of-00014.safetensors",
"model.layers.69.mamba.D": "model-00013-of-00014.safetensors",
"model.layers.69.mamba.conv1d.bias": "model-00013-of-00014.safetensors",
"model.layers.69.mamba.conv1d.weight": "model-00013-of-00014.safetensors",
"model.layers.69.mamba.dt_bias": "model-00013-of-00014.safetensors",
"model.layers.69.mamba.in_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.69.mamba.norm.weight": "model-00013-of-00014.safetensors",
"model.layers.69.mamba.out_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.69.pre_ff_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.69.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.69.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.69.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.69.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.7.feed_forward.down_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.7.feed_forward.gate_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.7.feed_forward.up_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.7.mamba.A_log": "model-00002-of-00014.safetensors",
"model.layers.7.mamba.D": "model-00002-of-00014.safetensors",
"model.layers.7.mamba.conv1d.bias": "model-00002-of-00014.safetensors",
"model.layers.7.mamba.conv1d.weight": "model-00002-of-00014.safetensors",
"model.layers.7.mamba.dt_bias": "model-00002-of-00014.safetensors",
"model.layers.7.mamba.in_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.7.mamba.norm.weight": "model-00002-of-00014.safetensors",
"model.layers.7.mamba.out_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.7.pre_ff_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.70.feed_forward.down_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.70.feed_forward.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.70.feed_forward.up_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.70.input_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.70.mamba.A_log": "model-00013-of-00014.safetensors",
"model.layers.70.mamba.D": "model-00013-of-00014.safetensors",
"model.layers.70.mamba.conv1d.bias": "model-00013-of-00014.safetensors",
"model.layers.70.mamba.conv1d.weight": "model-00013-of-00014.safetensors",
"model.layers.70.mamba.dt_bias": "model-00013-of-00014.safetensors",
"model.layers.70.mamba.in_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.70.mamba.norm.weight": "model-00013-of-00014.safetensors",
"model.layers.70.mamba.out_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.70.pre_ff_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.70.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.70.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.70.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.70.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.71.feed_forward.down_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.71.feed_forward.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.71.feed_forward.up_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.71.input_layernorm.weight": "model-00014-of-00014.safetensors",
"model.layers.71.mamba.A_log": "model-00014-of-00014.safetensors",
"model.layers.71.mamba.D": "model-00014-of-00014.safetensors",
"model.layers.71.mamba.conv1d.bias": "model-00014-of-00014.safetensors",
"model.layers.71.mamba.conv1d.weight": "model-00014-of-00014.safetensors",
"model.layers.71.mamba.dt_bias": "model-00014-of-00014.safetensors",
"model.layers.71.mamba.in_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.71.mamba.norm.weight": "model-00014-of-00014.safetensors",
"model.layers.71.mamba.out_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.71.pre_ff_layernorm.weight": "model-00014-of-00014.safetensors",
"model.layers.71.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.71.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.71.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.71.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.8.feed_forward.down_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.8.feed_forward.gate_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.8.feed_forward.up_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.8.mamba.A_log": "model-00003-of-00014.safetensors",
"model.layers.8.mamba.D": "model-00003-of-00014.safetensors",
"model.layers.8.mamba.conv1d.bias": "model-00003-of-00014.safetensors",
"model.layers.8.mamba.conv1d.weight": "model-00003-of-00014.safetensors",
"model.layers.8.mamba.dt_bias": "model-00003-of-00014.safetensors",
"model.layers.8.mamba.in_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.8.mamba.norm.weight": "model-00003-of-00014.safetensors",
"model.layers.8.mamba.out_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.8.pre_ff_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.9.feed_forward.down_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.9.feed_forward.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.9.feed_forward.up_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.9.mamba.A_log": "model-00003-of-00014.safetensors",
"model.layers.9.mamba.D": "model-00003-of-00014.safetensors",
"model.layers.9.mamba.conv1d.bias": "model-00003-of-00014.safetensors",
"model.layers.9.mamba.conv1d.weight": "model-00003-of-00014.safetensors",
"model.layers.9.mamba.dt_bias": "model-00003-of-00014.safetensors",
"model.layers.9.mamba.in_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.9.mamba.norm.weight": "model-00003-of-00014.safetensors",
"model.layers.9.mamba.out_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.9.pre_ff_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors"
}
}