| { |
| "metadata": { |
| "total_size": 17000491008 |
| }, |
| "weight_map": { |
| "lm_head.weight": "model-00004-of-00004.safetensors", |
| "model.embed_tokens.weight": "model-00001-of-00004.safetensors", |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.A_log": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.a_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.alpha_proj.bias": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.alpha_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.b_proj.bias": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.b_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.dt_bias": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.g_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.k_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.k_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.o_norm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.o_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.q_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.q_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.v_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.gka.v_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.A_log": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.a_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.alpha_proj.bias": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.alpha_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.b_proj.bias": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.b_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.dt_bias": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.g_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.k_conv1d.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.k_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.o_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.o_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.q_conv1d.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.q_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.v_conv1d.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.gka.v_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.A_log": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.a_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.alpha_proj.bias": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.alpha_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.b_proj.bias": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.b_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.dt_bias": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.g_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.k_conv1d.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.k_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.o_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.o_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.q_conv1d.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.q_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.v_conv1d.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.gka.v_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.A_log": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.a_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.alpha_proj.bias": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.alpha_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.b_proj.bias": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.b_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.dt_bias": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.g_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.k_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.k_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.o_norm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.o_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.q_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.q_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.v_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.gka.v_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.A_log": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.a_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.alpha_proj.bias": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.alpha_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.b_proj.bias": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.b_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.dt_bias": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.g_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.k_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.k_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.o_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.o_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.q_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.q_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.v_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.gka.v_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.A_log": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.a_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.alpha_proj.bias": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.alpha_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.b_proj.bias": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.b_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.dt_bias": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.g_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.k_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.k_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.o_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.o_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.q_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.q_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.v_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.gka.v_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.A_log": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.a_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.alpha_proj.bias": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.alpha_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.b_proj.bias": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.b_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.dt_bias": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.g_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.k_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.k_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.o_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.o_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.q_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.q_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.v_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.gka.v_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.A_log": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.a_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.alpha_proj.bias": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.alpha_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.b_proj.bias": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.b_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.dt_bias": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.g_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.k_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.k_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.o_norm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.o_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.q_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.q_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.v_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.gka.v_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.A_log": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.a_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.alpha_proj.bias": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.alpha_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.b_proj.bias": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.b_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.dt_bias": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.g_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.k_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.k_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.o_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.o_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.q_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.q_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.v_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.gka.v_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.A_log": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.a_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.alpha_proj.bias": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.alpha_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.b_proj.bias": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.b_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.dt_bias": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.g_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.k_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.k_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.o_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.o_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.q_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.q_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.v_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.gka.v_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.A_log": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.a_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.alpha_proj.bias": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.alpha_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.b_proj.bias": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.b_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.dt_bias": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.g_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.k_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.k_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.o_norm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.o_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.q_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.q_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.v_conv1d.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.gka.v_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.33.gka.A_log": "model-00003-of-00004.safetensors", |
| "model.layers.33.gka.a_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.33.gka.alpha_proj.bias": "model-00004-of-00004.safetensors", |
| "model.layers.33.gka.alpha_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.33.gka.b_proj.bias": "model-00004-of-00004.safetensors", |
| "model.layers.33.gka.b_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.33.gka.dt_bias": "model-00003-of-00004.safetensors", |
| "model.layers.33.gka.g_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.33.gka.k_conv1d.weight": "model-00004-of-00004.safetensors", |
| "model.layers.33.gka.k_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.33.gka.o_norm.weight": "model-00004-of-00004.safetensors", |
| "model.layers.33.gka.o_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.33.gka.q_conv1d.weight": "model-00004-of-00004.safetensors", |
| "model.layers.33.gka.q_proj.weight": "model-00003-of-00004.safetensors", |
| "model.layers.33.gka.v_conv1d.weight": "model-00004-of-00004.safetensors", |
| "model.layers.33.gka.v_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
| "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.A_log": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.a_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.alpha_proj.bias": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.alpha_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.b_proj.bias": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.b_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.dt_bias": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.g_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.k_conv1d.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.k_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.o_norm.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.o_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.q_conv1d.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.q_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.v_conv1d.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.gka.v_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.A_log": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.a_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.alpha_proj.bias": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.alpha_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.b_proj.bias": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.b_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.dt_bias": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.g_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.k_conv1d.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.k_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.o_norm.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.o_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.q_conv1d.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.q_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.v_conv1d.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.gka.v_proj.weight": "model-00004-of-00004.safetensors", |
| "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.A_log": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.a_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.alpha_proj.bias": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.alpha_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.b_proj.bias": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.b_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.dt_bias": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.g_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.k_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.k_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.o_norm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.o_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.q_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.q_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.v_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.gka.v_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.A_log": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.a_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.alpha_proj.bias": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.alpha_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.b_proj.bias": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.b_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.dt_bias": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.g_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.k_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.k_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.o_norm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.o_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.q_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.q_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.v_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.gka.v_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.A_log": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.a_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.alpha_proj.bias": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.alpha_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.b_proj.bias": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.b_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.dt_bias": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.g_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.k_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.k_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.o_norm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.o_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.q_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.q_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.v_conv1d.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.gka.v_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
| "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.A_log": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.a_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.alpha_proj.bias": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.alpha_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.b_proj.bias": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.b_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.dt_bias": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.g_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.k_conv1d.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.k_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.o_norm.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.o_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.q_conv1d.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.q_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.v_conv1d.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.gka.v_proj.weight": "model-00002-of-00004.safetensors", |
| "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
| "model.norm.weight": "model-00004-of-00004.safetensors" |
| } |
| } |
