| { |
| "method": "static_mixed_precision", |
| "base_model": "/Users/codelion/.cache/huggingface/hub/models--Kwaipilot--KAT-Coder-V2.5-Dev/snapshots/7a4a45dc6426b4951be99a9f230557c0b0b77761/", |
| "reference": "structural_rules", |
| "target_bpw": 4.5, |
| "achieved_bpw": 4.510037156886497, |
| "n_high_bits": 400, |
| "n_low_bits": 111, |
| "threshold": 0.0, |
| "per_layer": { |
| "language_model.lm_head": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.39.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.39.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.39.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.39.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.39.mlp.switch_mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.39.mlp.switch_mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.39.mlp.switch_mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.39.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.39.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.39.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.39.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.39.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.38.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.38.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.38.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.38.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.38.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.38.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.38.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.38.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.38.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.38.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.38.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.38.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.38.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.37.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.37.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.37.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.37.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.37.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.37.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.37.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.37.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.37.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.37.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.37.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.37.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.37.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.36.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.36.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.36.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.36.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.36.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.36.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.36.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.36.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.36.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.36.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.36.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.36.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.36.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.35.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.35.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.35.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.35.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.35.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.35.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.35.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.35.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.35.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.35.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.35.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.35.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.34.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.34.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.34.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.34.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.34.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.34.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.34.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.34.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.34.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.34.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.34.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.34.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.34.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.33.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.33.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.33.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.33.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.33.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.33.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.33.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.33.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.33.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.33.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.33.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.33.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.33.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.32.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.32.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.32.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.32.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.32.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.32.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.32.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.32.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.32.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.32.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.32.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.32.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.32.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.31.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.31.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.31.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.31.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.31.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.31.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.31.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.31.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.31.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.31.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.31.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.31.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.30.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.30.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.30.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.30.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.30.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.30.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.30.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.30.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.30.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.30.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.30.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.30.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.30.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.29.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.29.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.29.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.29.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.29.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.29.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.29.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.29.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.29.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.29.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.29.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.29.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.29.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.28.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.28.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.28.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.28.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.28.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.28.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.28.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.28.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.28.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.28.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.28.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.28.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.28.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.27.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.27.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.27.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.27.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.27.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.27.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.27.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.27.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.27.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.27.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.27.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.27.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.26.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.26.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.26.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.26.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.26.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.26.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.26.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.26.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.26.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.26.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.26.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.26.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.26.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.25.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.25.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.25.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.25.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.25.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.25.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.25.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.25.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.25.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.25.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.25.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.25.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.25.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.24.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.24.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.24.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.24.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.24.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.24.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.24.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.24.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.24.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.24.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.24.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.24.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.24.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.mlp.switch_mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.mlp.switch_mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.mlp.switch_mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.mlp.switch_mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.mlp.switch_mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.mlp.switch_mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.mlp.shared_expert_gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.mlp.shared_expert.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.mlp.shared_expert.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.mlp.shared_expert.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.mlp.switch_mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.mlp.switch_mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.mlp.switch_mlp.gate_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.mlp.gate": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.linear_attn.in_proj_a": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.linear_attn.in_proj_b": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| } |
| } |
| } |
