| { |
| "metadata": { |
| "total_size": 10849197696, |
| "total_parameters": 34660608768 |
| }, |
| "weight_map": { |
| "language_model.lm_head.biases": "model-00003-of-00003.safetensors", |
| "language_model.lm_head.scales": "model-00003-of-00003.safetensors", |
| "language_model.lm_head.weight": "model-00003-of-00003.safetensors", |
| "language_model.model.embed_tokens.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.embed_tokens.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.A_log": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.dt_bias": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.in_proj_a.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.in_proj_a.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.in_proj_b.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.in_proj_b.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.in_proj_qkv.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.in_proj_qkv.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.in_proj_z.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.in_proj_z.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.out_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.out_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.shared_expert.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.shared_expert.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.shared_expert.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.shared_expert.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.shared_expert.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.shared_expert.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.shared_expert_gate.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.shared_expert_gate.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.shared_expert_gate.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.A_log": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.dt_bias": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.in_proj_a.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.in_proj_a.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.in_proj_b.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.in_proj_b.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.in_proj_qkv.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.in_proj_qkv.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.in_proj_z.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.in_proj_z.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.out_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.out_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.shared_expert.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.shared_expert.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.shared_expert.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.shared_expert.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.shared_expert.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.shared_expert.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.shared_expert_gate.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.shared_expert_gate.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.shared_expert_gate.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.norm.weight": "model-00002-of-00003.safetensors" |
| } |
| } |
