| { |
| "metadata": { |
| "total_size": 68878190592 |
| }, |
| "weight_map": { |
| "lm_head.weight": "model-00015-of-00015.safetensors", |
| "model.embed_tokens.weight": "model-00001-of-00015.safetensors", |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors", |
| "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", |
| "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00015.safetensors", |
| "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00015.safetensors", |
| "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors", |
| "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", |
| "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00015.safetensors", |
| "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00015.safetensors", |
| "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.A_log": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.a_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.alpha_proj.bias": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.alpha_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.b_proj.bias": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.b_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.dt_bias": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.g_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.k_conv1d.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.k_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.k_rep": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.o_norm.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.o_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.proj_k.linearA.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.proj_k.linearB.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.proj_v.linearA.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.proj_v.linearB.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.q_conv1d.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.q_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.v_conv1d.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.v_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.10.gka.v_rep": "model-00003-of-00015.safetensors", |
| "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.A_log": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.a_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.alpha_proj.bias": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.alpha_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.b_proj.bias": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.b_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.dt_bias": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.g_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.k_conv1d.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.k_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.k_rep": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.o_norm.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.o_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.proj_k.linearA.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.proj_k.linearB.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.proj_v.linearA.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.proj_v.linearB.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.q_conv1d.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.q_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.v_conv1d.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.v_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.11.gka.v_rep": "model-00003-of-00015.safetensors", |
| "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", |
| "model.layers.12.input_layernorm.weight": "model-00003-of-00015.safetensors", |
| "model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.12.mlp.up_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.12.gka.A_log": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.a_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.alpha_proj.bias": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.alpha_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.b_proj.bias": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.b_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.dt_bias": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.g_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.k_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.k_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.k_rep": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.o_norm.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.o_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.proj_k.linearA.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.proj_k.linearB.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.proj_v.linearA.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.proj_v.linearB.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.q_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.q_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.v_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.v_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.12.gka.v_rep": "model-00004-of-00015.safetensors", |
| "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", |
| "model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.mlp.down_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.A_log": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.a_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.alpha_proj.bias": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.alpha_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.b_proj.bias": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.b_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.dt_bias": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.g_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.k_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.k_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.k_rep": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.o_norm.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.o_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.proj_k.linearA.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.proj_k.linearB.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.proj_v.linearA.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.proj_v.linearB.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.q_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.q_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.v_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.v_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.13.gka.v_rep": "model-00004-of-00015.safetensors", |
| "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.A_log": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.a_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.alpha_proj.bias": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.alpha_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.b_proj.bias": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.b_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.dt_bias": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.g_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.k_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.k_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.k_rep": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.o_norm.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.o_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.proj_k.linearA.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.proj_k.linearB.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.proj_v.linearA.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.proj_v.linearB.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.q_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.q_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.v_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.v_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.14.gka.v_rep": "model-00004-of-00015.safetensors", |
| "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.A_log": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.a_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.alpha_proj.bias": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.alpha_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.b_proj.bias": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.b_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.dt_bias": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.g_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.k_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.k_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.k_rep": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.o_norm.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.o_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.proj_k.linearA.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.proj_k.linearB.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.proj_v.linearA.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.proj_v.linearB.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.q_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.q_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.v_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.v_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.15.gka.v_rep": "model-00004-of-00015.safetensors", |
| "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.input_layernorm.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.mlp.down_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.mlp.up_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.A_log": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.a_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.alpha_proj.bias": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.alpha_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.b_proj.bias": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.b_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.dt_bias": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.g_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.k_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.k_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.k_rep": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.o_norm.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.o_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.proj_k.linearA.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.proj_k.linearB.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.proj_v.linearA.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.proj_v.linearB.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.q_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.q_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.v_conv1d.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.v_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.16.gka.v_rep": "model-00004-of-00015.safetensors", |
| "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", |
| "model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.17.self_attn.k_norm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.17.self_attn.q_norm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", |
| "model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.18.mlp.up_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.18.self_attn.k_norm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.18.self_attn.q_norm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.19.input_layernorm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.19.mlp.down_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.19.mlp.up_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.19.self_attn.k_norm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.19.self_attn.q_norm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.A_log": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.a_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.alpha_proj.bias": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.alpha_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.b_proj.bias": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.b_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.dt_bias": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.g_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.k_conv1d.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.k_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.k_rep": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.o_norm.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.o_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.proj_k.linearA.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.proj_k.linearB.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.proj_v.linearA.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.proj_v.linearB.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.q_conv1d.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.q_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.v_conv1d.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.v_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.2.gka.v_rep": "model-00001-of-00015.safetensors", |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", |
| "model.layers.20.input_layernorm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.mlp.down_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.mlp.up_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.A_log": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.a_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.alpha_proj.bias": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.alpha_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.b_proj.bias": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.b_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.dt_bias": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.g_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.k_conv1d.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.k_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.k_rep": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.o_norm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.o_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.proj_k.linearA.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.proj_k.linearB.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.proj_v.linearA.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.proj_v.linearB.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.q_conv1d.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.q_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.v_conv1d.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.v_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.20.gka.v_rep": "model-00005-of-00015.safetensors", |
| "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.21.input_layernorm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.21.mlp.down_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.21.mlp.up_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.21.self_attn.k_norm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.21.self_attn.q_norm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", |
| "model.layers.22.input_layernorm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.22.mlp.down_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.mlp.up_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.A_log": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.a_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.alpha_proj.bias": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.alpha_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.b_proj.bias": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.b_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.dt_bias": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.g_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.k_conv1d.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.k_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.k_rep": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.o_norm.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.o_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.proj_k.linearA.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.proj_k.linearB.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.proj_v.linearA.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.proj_v.linearB.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.q_conv1d.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.q_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.v_conv1d.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.v_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.22.gka.v_rep": "model-00006-of-00015.safetensors", |
| "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", |
| "model.layers.23.input_layernorm.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.mlp.down_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.mlp.up_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.A_log": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.a_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.alpha_proj.bias": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.alpha_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.b_proj.bias": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.b_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.dt_bias": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.g_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.k_conv1d.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.k_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.k_rep": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.o_norm.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.o_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.proj_k.linearA.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.proj_k.linearB.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.proj_v.linearA.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.proj_v.linearB.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.q_conv1d.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.q_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.v_conv1d.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.v_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.23.gka.v_rep": "model-00006-of-00015.safetensors", |
| "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.input_layernorm.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.mlp.down_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.mlp.up_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.A_log": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.a_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.alpha_proj.bias": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.alpha_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.b_proj.bias": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.b_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.dt_bias": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.g_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.k_conv1d.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.k_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.k_rep": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.o_norm.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.o_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.proj_k.linearA.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.proj_k.linearB.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.proj_v.linearA.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.proj_v.linearB.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.q_conv1d.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.q_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.v_conv1d.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.v_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.24.gka.v_rep": "model-00006-of-00015.safetensors", |
| "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", |
| "model.layers.25.input_layernorm.weight": "model-00006-of-00015.safetensors", |
| "model.layers.25.mlp.down_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.25.mlp.up_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", |
| "model.layers.25.self_attn.k_norm.weight": "model-00006-of-00015.safetensors", |
| "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.25.self_attn.q_norm.weight": "model-00006-of-00015.safetensors", |
| "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.26.input_layernorm.weight": "model-00006-of-00015.safetensors", |
| "model.layers.26.mlp.down_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.26.mlp.up_proj.weight": "model-00006-of-00015.safetensors", |
| "model.layers.26.gka.A_log": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.a_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.alpha_proj.bias": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.alpha_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.b_proj.bias": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.b_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.dt_bias": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.g_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.k_conv1d.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.k_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.k_rep": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.o_norm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.o_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.proj_k.linearA.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.proj_k.linearB.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.proj_v.linearA.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.proj_v.linearB.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.q_conv1d.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.q_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.v_conv1d.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.v_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.26.gka.v_rep": "model-00007-of-00015.safetensors", |
| "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", |
| "model.layers.27.input_layernorm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.mlp.down_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.mlp.up_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.A_log": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.a_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.alpha_proj.bias": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.alpha_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.b_proj.bias": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.b_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.dt_bias": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.g_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.k_conv1d.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.k_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.k_rep": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.o_norm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.o_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.proj_k.linearA.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.proj_k.linearB.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.proj_v.linearA.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.proj_v.linearB.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.q_conv1d.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.q_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.v_conv1d.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.v_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.27.gka.v_rep": "model-00007-of-00015.safetensors", |
| "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.input_layernorm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.mlp.down_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.mlp.up_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.A_log": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.a_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.alpha_proj.bias": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.alpha_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.b_proj.bias": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.b_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.dt_bias": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.g_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.k_conv1d.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.k_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.k_rep": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.o_norm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.o_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.proj_k.linearA.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.proj_k.linearB.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.proj_v.linearA.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.proj_v.linearB.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.q_conv1d.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.q_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.v_conv1d.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.v_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.28.gka.v_rep": "model-00007-of-00015.safetensors", |
| "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.input_layernorm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.mlp.down_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.mlp.up_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.A_log": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.a_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.alpha_proj.bias": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.alpha_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.b_proj.bias": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.b_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.dt_bias": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.g_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.k_conv1d.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.k_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.k_rep": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.o_norm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.o_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.proj_k.linearA.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.proj_k.linearB.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.proj_v.linearA.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.proj_v.linearB.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.q_conv1d.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.q_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.v_conv1d.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.v_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.29.gka.v_rep": "model-00007-of-00015.safetensors", |
| "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00015.safetensors", |
| "model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", |
| "model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.A_log": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.a_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.alpha_proj.bias": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.alpha_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.b_proj.bias": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.b_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.dt_bias": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.g_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.k_conv1d.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.k_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.k_rep": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.o_norm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.o_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.proj_k.linearA.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.proj_k.linearB.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.proj_v.linearA.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.proj_v.linearB.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.q_conv1d.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.q_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.v_conv1d.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.v_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.3.gka.v_rep": "model-00002-of-00015.safetensors", |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", |
| "model.layers.30.input_layernorm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.30.mlp.down_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.30.mlp.up_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.30.self_attn.k_norm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.30.self_attn.q_norm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.31.input_layernorm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.31.mlp.down_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.31.mlp.up_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.31.self_attn.k_norm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.31.self_attn.q_norm.weight": "model-00007-of-00015.safetensors", |
| "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", |
| "model.layers.32.input_layernorm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.mlp.down_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.mlp.up_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.A_log": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.a_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.alpha_proj.bias": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.alpha_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.b_proj.bias": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.b_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.dt_bias": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.g_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.k_conv1d.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.k_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.k_rep": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.o_norm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.o_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.proj_k.linearA.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.proj_k.linearB.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.proj_v.linearA.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.proj_v.linearB.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.q_conv1d.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.q_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.v_conv1d.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.v_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.32.gka.v_rep": "model-00008-of-00015.safetensors", |
| "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.input_layernorm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.mlp.down_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.mlp.up_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.A_log": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.a_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.alpha_proj.bias": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.alpha_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.b_proj.bias": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.b_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.dt_bias": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.g_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.k_conv1d.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.k_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.k_rep": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.o_norm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.o_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.proj_k.linearA.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.proj_k.linearB.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.proj_v.linearA.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.proj_v.linearB.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.q_conv1d.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.q_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.v_conv1d.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.v_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.33.gka.v_rep": "model-00008-of-00015.safetensors", |
| "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.34.input_layernorm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.34.mlp.down_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.34.mlp.up_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.34.self_attn.k_norm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.34.self_attn.q_norm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.input_layernorm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.mlp.down_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.mlp.up_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.A_log": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.a_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.alpha_proj.bias": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.alpha_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.b_proj.bias": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.b_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.dt_bias": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.g_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.k_conv1d.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.k_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.k_rep": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.o_norm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.o_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.proj_k.linearA.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.proj_k.linearB.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.proj_v.linearA.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.proj_v.linearB.weight": "model-00009-of-00015.safetensors", |
| "model.layers.35.gka.q_conv1d.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.q_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.v_conv1d.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.v_proj.weight": "model-00008-of-00015.safetensors", |
| "model.layers.35.gka.v_rep": "model-00008-of-00015.safetensors", |
| "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", |
| "model.layers.36.input_layernorm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.mlp.down_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.mlp.up_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.A_log": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.a_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.alpha_proj.bias": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.alpha_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.b_proj.bias": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.b_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.dt_bias": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.g_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.k_conv1d.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.k_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.k_rep": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.o_norm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.o_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.proj_k.linearA.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.proj_k.linearB.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.proj_v.linearA.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.proj_v.linearB.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.q_conv1d.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.q_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.v_conv1d.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.v_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.36.gka.v_rep": "model-00009-of-00015.safetensors", |
| "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.37.input_layernorm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.37.mlp.down_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.37.mlp.up_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.37.self_attn.k_norm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.37.self_attn.q_norm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.38.input_layernorm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.38.mlp.down_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.38.mlp.up_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.38.self_attn.k_norm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.38.self_attn.q_norm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.input_layernorm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.mlp.down_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.mlp.up_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.A_log": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.a_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.alpha_proj.bias": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.alpha_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.b_proj.bias": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.b_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.dt_bias": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.g_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.k_conv1d.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.k_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.k_rep": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.o_norm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.o_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.proj_k.linearA.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.proj_k.linearB.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.proj_v.linearA.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.proj_v.linearB.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.q_conv1d.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.q_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.v_conv1d.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.v_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.39.gka.v_rep": "model-00009-of-00015.safetensors", |
| "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.40.input_layernorm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.40.mlp.down_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.40.mlp.up_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.40.gka.A_log": "model-00009-of-00015.safetensors", |
| "model.layers.40.gka.a_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.alpha_proj.bias": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.alpha_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.b_proj.bias": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.b_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.dt_bias": "model-00009-of-00015.safetensors", |
| "model.layers.40.gka.g_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.k_conv1d.weight": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.k_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.40.gka.k_rep": "model-00009-of-00015.safetensors", |
| "model.layers.40.gka.o_norm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.o_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.proj_k.linearA.weight": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.proj_k.linearB.weight": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.proj_v.linearA.weight": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.proj_v.linearB.weight": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.q_conv1d.weight": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.q_proj.weight": "model-00009-of-00015.safetensors", |
| "model.layers.40.gka.v_conv1d.weight": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.v_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.40.gka.v_rep": "model-00009-of-00015.safetensors", |
| "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", |
| "model.layers.41.input_layernorm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.mlp.down_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.mlp.up_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.A_log": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.a_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.alpha_proj.bias": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.alpha_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.b_proj.bias": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.b_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.dt_bias": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.g_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.k_conv1d.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.k_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.k_rep": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.o_norm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.o_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.proj_k.linearA.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.proj_k.linearB.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.proj_v.linearA.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.proj_v.linearB.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.q_conv1d.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.q_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.v_conv1d.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.v_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.41.gka.v_rep": "model-00010-of-00015.safetensors", |
| "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.42.input_layernorm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.42.mlp.down_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.42.mlp.up_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.42.self_attn.k_norm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.42.self_attn.q_norm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.input_layernorm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.mlp.down_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.mlp.up_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.A_log": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.a_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.alpha_proj.bias": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.alpha_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.b_proj.bias": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.b_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.dt_bias": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.g_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.k_conv1d.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.k_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.k_rep": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.o_norm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.o_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.proj_k.linearA.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.proj_k.linearB.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.proj_v.linearA.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.proj_v.linearB.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.q_conv1d.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.q_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.v_conv1d.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.v_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.43.gka.v_rep": "model-00010-of-00015.safetensors", |
| "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.input_layernorm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.mlp.down_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.mlp.up_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.A_log": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.a_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.alpha_proj.bias": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.alpha_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.b_proj.bias": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.b_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.dt_bias": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.g_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.k_conv1d.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.k_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.k_rep": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.o_norm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.o_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.proj_k.linearA.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.proj_k.linearB.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.proj_v.linearA.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.proj_v.linearB.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.q_conv1d.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.q_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.v_conv1d.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.v_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.44.gka.v_rep": "model-00010-of-00015.safetensors", |
| "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.45.input_layernorm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.45.mlp.down_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.45.mlp.up_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.45.self_attn.k_norm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.45.self_attn.q_norm.weight": "model-00010-of-00015.safetensors", |
| "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", |
| "model.layers.46.input_layernorm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.46.mlp.down_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.46.mlp.up_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.46.self_attn.k_norm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.46.self_attn.q_norm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.47.input_layernorm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.47.mlp.down_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.47.mlp.up_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.47.self_attn.k_norm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.47.self_attn.q_norm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.48.input_layernorm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.48.mlp.down_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.48.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.48.mlp.up_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.48.self_attn.k_norm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.48.self_attn.q_norm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.49.input_layernorm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.49.mlp.down_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.49.mlp.up_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.49.self_attn.k_norm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.49.self_attn.q_norm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.50.input_layernorm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.50.mlp.down_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.50.self_attn.k_norm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.50.self_attn.q_norm.weight": "model-00011-of-00015.safetensors", |
| "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", |
| "model.layers.51.input_layernorm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.51.mlp.down_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.51.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.51.mlp.up_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.51.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.51.self_attn.k_norm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.51.self_attn.q_norm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.52.input_layernorm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.52.mlp.down_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.52.mlp.up_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.52.self_attn.k_norm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.52.self_attn.q_norm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.53.input_layernorm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.53.mlp.down_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.53.mlp.up_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.53.self_attn.k_norm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.53.self_attn.q_norm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.54.input_layernorm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.54.mlp.down_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.54.mlp.up_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.54.self_attn.k_norm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.54.self_attn.q_norm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.55.input_layernorm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.55.mlp.down_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.55.mlp.up_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.55.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.55.self_attn.k_norm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.55.self_attn.q_norm.weight": "model-00012-of-00015.safetensors", |
| "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", |
| "model.layers.56.input_layernorm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.56.mlp.down_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.56.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.56.mlp.up_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.56.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.56.self_attn.k_norm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.56.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.56.self_attn.q_norm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.56.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.56.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.input_layernorm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.mlp.down_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.mlp.up_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.A_log": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.a_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.alpha_proj.bias": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.alpha_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.b_proj.bias": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.b_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.dt_bias": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.g_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.k_conv1d.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.k_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.k_rep": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.o_norm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.o_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.proj_k.linearA.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.proj_k.linearB.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.proj_v.linearA.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.proj_v.linearB.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.q_conv1d.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.q_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.v_conv1d.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.v_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.57.gka.v_rep": "model-00013-of-00015.safetensors", |
| "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.58.input_layernorm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.58.mlp.down_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.58.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.58.mlp.up_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.58.self_attn.k_norm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.58.self_attn.q_norm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.59.input_layernorm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.59.mlp.down_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.59.mlp.up_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.59.self_attn.k_norm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.59.self_attn.q_norm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.60.input_layernorm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.60.mlp.down_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", |
| "model.layers.60.mlp.up_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.A_log": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.a_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.alpha_proj.bias": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.alpha_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.b_proj.bias": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.b_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.dt_bias": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.g_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.k_conv1d.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.k_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.k_rep": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.o_norm.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.o_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.proj_k.linearA.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.proj_k.linearB.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.proj_v.linearA.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.proj_v.linearB.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.q_conv1d.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.q_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.v_conv1d.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.v_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.60.gka.v_rep": "model-00014-of-00015.safetensors", |
| "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", |
| "model.layers.61.input_layernorm.weight": "model-00014-of-00015.safetensors", |
| "model.layers.61.mlp.down_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.61.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.61.mlp.up_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.61.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", |
| "model.layers.61.self_attn.k_norm.weight": "model-00014-of-00015.safetensors", |
| "model.layers.61.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.61.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.61.self_attn.q_norm.weight": "model-00014-of-00015.safetensors", |
| "model.layers.61.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.61.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.62.input_layernorm.weight": "model-00014-of-00015.safetensors", |
| "model.layers.62.mlp.down_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.62.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.62.mlp.up_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.62.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", |
| "model.layers.62.self_attn.k_norm.weight": "model-00014-of-00015.safetensors", |
| "model.layers.62.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.62.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.62.self_attn.q_norm.weight": "model-00014-of-00015.safetensors", |
| "model.layers.62.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.62.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.input_layernorm.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.mlp.down_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.mlp.up_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.A_log": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.a_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.alpha_proj.bias": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.alpha_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.b_proj.bias": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.b_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.dt_bias": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.g_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.k_conv1d.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.k_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.k_rep": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.o_norm.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.o_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.proj_k.linearA.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.proj_k.linearB.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.proj_v.linearA.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.proj_v.linearB.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.q_conv1d.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.q_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.v_conv1d.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.v_proj.weight": "model-00014-of-00015.safetensors", |
| "model.layers.63.gka.v_rep": "model-00014-of-00015.safetensors", |
| "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", |
| "model.layers.7.input_layernorm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.mlp.down_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.A_log": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.a_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.alpha_proj.bias": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.alpha_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.b_proj.bias": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.b_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.dt_bias": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.g_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.k_conv1d.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.k_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.k_rep": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.o_norm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.o_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.proj_k.linearA.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.proj_k.linearB.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.proj_v.linearA.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.proj_v.linearB.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.q_conv1d.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.q_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.v_conv1d.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.v_proj.weight": "model-00002-of-00015.safetensors", |
| "model.layers.7.gka.v_rep": "model-00002-of-00015.safetensors", |
| "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.8.input_layernorm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.A_log": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.a_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.alpha_proj.bias": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.alpha_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.b_proj.bias": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.b_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.dt_bias": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.g_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.k_conv1d.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.k_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.k_rep": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.o_norm.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.o_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.proj_k.linearA.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.proj_k.linearB.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.proj_v.linearA.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.proj_v.linearB.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.q_conv1d.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.q_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.v_conv1d.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.v_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.8.gka.v_rep": "model-00003-of-00015.safetensors", |
| "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", |
| "model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.mlp.down_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.mlp.up_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.A_log": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.a_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.alpha_proj.bias": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.alpha_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.b_proj.bias": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.b_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.dt_bias": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.g_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.k_conv1d.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.k_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.k_rep": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.o_norm.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.o_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.proj_k.linearA.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.proj_k.linearB.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.proj_v.linearA.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.proj_v.linearB.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.q_conv1d.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.q_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.v_conv1d.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.v_proj.weight": "model-00003-of-00015.safetensors", |
| "model.layers.9.gka.v_rep": "model-00003-of-00015.safetensors", |
| "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", |
| "model.norm.weight": "model-00014-of-00015.safetensors" |
| } |
| } |
