Intern-S2-Preview-AWQ-INT4 / quant_config.json
cpatonn's picture
Upload folder using huggingface_hub
c568b80 verified
Raw
History Blame Contribute Delete
32.6 kB
{
"zero_point": true,
"q_group_size": 32,
"w_bit": 4,
"version": "gemm",
"modules_to_not_convert": [
"model.language_model.layers.0.linear_attn.out_proj",
"model.language_model.layers.0.linear_attn.in_proj_qkv",
"model.language_model.layers.0.linear_attn.in_proj_z",
"model.language_model.layers.0.linear_attn.in_proj_b",
"model.language_model.layers.0.linear_attn.in_proj_a",
"model.language_model.layers.0.mlp.shared_expert.gate_proj",
"model.language_model.layers.0.mlp.shared_expert.up_proj",
"model.language_model.layers.0.mlp.shared_expert.down_proj",
"model.language_model.layers.0.mlp.shared_expert_gate",
"model.language_model.layers.1.linear_attn.out_proj",
"model.language_model.layers.1.linear_attn.in_proj_qkv",
"model.language_model.layers.1.linear_attn.in_proj_z",
"model.language_model.layers.1.linear_attn.in_proj_b",
"model.language_model.layers.1.linear_attn.in_proj_a",
"model.language_model.layers.1.mlp.shared_expert.gate_proj",
"model.language_model.layers.1.mlp.shared_expert.up_proj",
"model.language_model.layers.1.mlp.shared_expert.down_proj",
"model.language_model.layers.1.mlp.shared_expert_gate",
"model.language_model.layers.2.linear_attn.out_proj",
"model.language_model.layers.2.linear_attn.in_proj_qkv",
"model.language_model.layers.2.linear_attn.in_proj_z",
"model.language_model.layers.2.linear_attn.in_proj_b",
"model.language_model.layers.2.linear_attn.in_proj_a",
"model.language_model.layers.2.mlp.shared_expert.gate_proj",
"model.language_model.layers.2.mlp.shared_expert.up_proj",
"model.language_model.layers.2.mlp.shared_expert.down_proj",
"model.language_model.layers.2.mlp.shared_expert_gate",
"model.language_model.layers.3.self_attn.q_proj",
"model.language_model.layers.3.self_attn.k_proj",
"model.language_model.layers.3.self_attn.v_proj",
"model.language_model.layers.3.self_attn.o_proj",
"model.language_model.layers.3.mlp.shared_expert.gate_proj",
"model.language_model.layers.3.mlp.shared_expert.up_proj",
"model.language_model.layers.3.mlp.shared_expert.down_proj",
"model.language_model.layers.3.mlp.shared_expert_gate",
"model.language_model.layers.4.linear_attn.out_proj",
"model.language_model.layers.4.linear_attn.in_proj_qkv",
"model.language_model.layers.4.linear_attn.in_proj_z",
"model.language_model.layers.4.linear_attn.in_proj_b",
"model.language_model.layers.4.linear_attn.in_proj_a",
"model.language_model.layers.4.mlp.shared_expert.gate_proj",
"model.language_model.layers.4.mlp.shared_expert.up_proj",
"model.language_model.layers.4.mlp.shared_expert.down_proj",
"model.language_model.layers.4.mlp.shared_expert_gate",
"model.language_model.layers.5.linear_attn.out_proj",
"model.language_model.layers.5.linear_attn.in_proj_qkv",
"model.language_model.layers.5.linear_attn.in_proj_z",
"model.language_model.layers.5.linear_attn.in_proj_b",
"model.language_model.layers.5.linear_attn.in_proj_a",
"model.language_model.layers.5.mlp.shared_expert.gate_proj",
"model.language_model.layers.5.mlp.shared_expert.up_proj",
"model.language_model.layers.5.mlp.shared_expert.down_proj",
"model.language_model.layers.5.mlp.shared_expert_gate",
"model.language_model.layers.6.linear_attn.out_proj",
"model.language_model.layers.6.linear_attn.in_proj_qkv",
"model.language_model.layers.6.linear_attn.in_proj_z",
"model.language_model.layers.6.linear_attn.in_proj_b",
"model.language_model.layers.6.linear_attn.in_proj_a",
"model.language_model.layers.6.mlp.shared_expert.gate_proj",
"model.language_model.layers.6.mlp.shared_expert.up_proj",
"model.language_model.layers.6.mlp.shared_expert.down_proj",
"model.language_model.layers.6.mlp.shared_expert_gate",
"model.language_model.layers.7.self_attn.q_proj",
"model.language_model.layers.7.self_attn.k_proj",
"model.language_model.layers.7.self_attn.v_proj",
"model.language_model.layers.7.self_attn.o_proj",
"model.language_model.layers.7.mlp.shared_expert.gate_proj",
"model.language_model.layers.7.mlp.shared_expert.up_proj",
"model.language_model.layers.7.mlp.shared_expert.down_proj",
"model.language_model.layers.7.mlp.shared_expert_gate",
"model.language_model.layers.8.linear_attn.out_proj",
"model.language_model.layers.8.linear_attn.in_proj_qkv",
"model.language_model.layers.8.linear_attn.in_proj_z",
"model.language_model.layers.8.linear_attn.in_proj_b",
"model.language_model.layers.8.linear_attn.in_proj_a",
"model.language_model.layers.8.mlp.shared_expert.gate_proj",
"model.language_model.layers.8.mlp.shared_expert.up_proj",
"model.language_model.layers.8.mlp.shared_expert.down_proj",
"model.language_model.layers.8.mlp.shared_expert_gate",
"model.language_model.layers.9.linear_attn.out_proj",
"model.language_model.layers.9.linear_attn.in_proj_qkv",
"model.language_model.layers.9.linear_attn.in_proj_z",
"model.language_model.layers.9.linear_attn.in_proj_b",
"model.language_model.layers.9.linear_attn.in_proj_a",
"model.language_model.layers.9.mlp.shared_expert.gate_proj",
"model.language_model.layers.9.mlp.shared_expert.up_proj",
"model.language_model.layers.9.mlp.shared_expert.down_proj",
"model.language_model.layers.9.mlp.shared_expert_gate",
"model.language_model.layers.10.linear_attn.out_proj",
"model.language_model.layers.10.linear_attn.in_proj_qkv",
"model.language_model.layers.10.linear_attn.in_proj_z",
"model.language_model.layers.10.linear_attn.in_proj_b",
"model.language_model.layers.10.linear_attn.in_proj_a",
"model.language_model.layers.10.mlp.shared_expert.gate_proj",
"model.language_model.layers.10.mlp.shared_expert.up_proj",
"model.language_model.layers.10.mlp.shared_expert.down_proj",
"model.language_model.layers.10.mlp.shared_expert_gate",
"model.language_model.layers.11.self_attn.q_proj",
"model.language_model.layers.11.self_attn.k_proj",
"model.language_model.layers.11.self_attn.v_proj",
"model.language_model.layers.11.self_attn.o_proj",
"model.language_model.layers.11.mlp.shared_expert.gate_proj",
"model.language_model.layers.11.mlp.shared_expert.up_proj",
"model.language_model.layers.11.mlp.shared_expert.down_proj",
"model.language_model.layers.11.mlp.shared_expert_gate",
"model.language_model.layers.12.linear_attn.out_proj",
"model.language_model.layers.12.linear_attn.in_proj_qkv",
"model.language_model.layers.12.linear_attn.in_proj_z",
"model.language_model.layers.12.linear_attn.in_proj_b",
"model.language_model.layers.12.linear_attn.in_proj_a",
"model.language_model.layers.12.mlp.shared_expert.gate_proj",
"model.language_model.layers.12.mlp.shared_expert.up_proj",
"model.language_model.layers.12.mlp.shared_expert.down_proj",
"model.language_model.layers.12.mlp.shared_expert_gate",
"model.language_model.layers.13.linear_attn.out_proj",
"model.language_model.layers.13.linear_attn.in_proj_qkv",
"model.language_model.layers.13.linear_attn.in_proj_z",
"model.language_model.layers.13.linear_attn.in_proj_b",
"model.language_model.layers.13.linear_attn.in_proj_a",
"model.language_model.layers.13.mlp.shared_expert.gate_proj",
"model.language_model.layers.13.mlp.shared_expert.up_proj",
"model.language_model.layers.13.mlp.shared_expert.down_proj",
"model.language_model.layers.13.mlp.shared_expert_gate",
"model.language_model.layers.14.linear_attn.out_proj",
"model.language_model.layers.14.linear_attn.in_proj_qkv",
"model.language_model.layers.14.linear_attn.in_proj_z",
"model.language_model.layers.14.linear_attn.in_proj_b",
"model.language_model.layers.14.linear_attn.in_proj_a",
"model.language_model.layers.14.mlp.shared_expert.gate_proj",
"model.language_model.layers.14.mlp.shared_expert.up_proj",
"model.language_model.layers.14.mlp.shared_expert.down_proj",
"model.language_model.layers.14.mlp.shared_expert_gate",
"model.language_model.layers.15.self_attn.q_proj",
"model.language_model.layers.15.self_attn.k_proj",
"model.language_model.layers.15.self_attn.v_proj",
"model.language_model.layers.15.self_attn.o_proj",
"model.language_model.layers.15.mlp.shared_expert.gate_proj",
"model.language_model.layers.15.mlp.shared_expert.up_proj",
"model.language_model.layers.15.mlp.shared_expert.down_proj",
"model.language_model.layers.15.mlp.shared_expert_gate",
"model.language_model.layers.16.linear_attn.out_proj",
"model.language_model.layers.16.linear_attn.in_proj_qkv",
"model.language_model.layers.16.linear_attn.in_proj_z",
"model.language_model.layers.16.linear_attn.in_proj_b",
"model.language_model.layers.16.linear_attn.in_proj_a",
"model.language_model.layers.16.mlp.shared_expert.gate_proj",
"model.language_model.layers.16.mlp.shared_expert.up_proj",
"model.language_model.layers.16.mlp.shared_expert.down_proj",
"model.language_model.layers.16.mlp.shared_expert_gate",
"model.language_model.layers.17.linear_attn.out_proj",
"model.language_model.layers.17.linear_attn.in_proj_qkv",
"model.language_model.layers.17.linear_attn.in_proj_z",
"model.language_model.layers.17.linear_attn.in_proj_b",
"model.language_model.layers.17.linear_attn.in_proj_a",
"model.language_model.layers.17.mlp.shared_expert.gate_proj",
"model.language_model.layers.17.mlp.shared_expert.up_proj",
"model.language_model.layers.17.mlp.shared_expert.down_proj",
"model.language_model.layers.17.mlp.shared_expert_gate",
"model.language_model.layers.18.linear_attn.out_proj",
"model.language_model.layers.18.linear_attn.in_proj_qkv",
"model.language_model.layers.18.linear_attn.in_proj_z",
"model.language_model.layers.18.linear_attn.in_proj_b",
"model.language_model.layers.18.linear_attn.in_proj_a",
"model.language_model.layers.18.mlp.shared_expert.gate_proj",
"model.language_model.layers.18.mlp.shared_expert.up_proj",
"model.language_model.layers.18.mlp.shared_expert.down_proj",
"model.language_model.layers.18.mlp.shared_expert_gate",
"model.language_model.layers.19.self_attn.q_proj",
"model.language_model.layers.19.self_attn.k_proj",
"model.language_model.layers.19.self_attn.v_proj",
"model.language_model.layers.19.self_attn.o_proj",
"model.language_model.layers.19.mlp.shared_expert.gate_proj",
"model.language_model.layers.19.mlp.shared_expert.up_proj",
"model.language_model.layers.19.mlp.shared_expert.down_proj",
"model.language_model.layers.19.mlp.shared_expert_gate",
"model.language_model.layers.20.linear_attn.out_proj",
"model.language_model.layers.20.linear_attn.in_proj_qkv",
"model.language_model.layers.20.linear_attn.in_proj_z",
"model.language_model.layers.20.linear_attn.in_proj_b",
"model.language_model.layers.20.linear_attn.in_proj_a",
"model.language_model.layers.20.mlp.shared_expert.gate_proj",
"model.language_model.layers.20.mlp.shared_expert.up_proj",
"model.language_model.layers.20.mlp.shared_expert.down_proj",
"model.language_model.layers.20.mlp.shared_expert_gate",
"model.language_model.layers.21.linear_attn.out_proj",
"model.language_model.layers.21.linear_attn.in_proj_qkv",
"model.language_model.layers.21.linear_attn.in_proj_z",
"model.language_model.layers.21.linear_attn.in_proj_b",
"model.language_model.layers.21.linear_attn.in_proj_a",
"model.language_model.layers.21.mlp.shared_expert.gate_proj",
"model.language_model.layers.21.mlp.shared_expert.up_proj",
"model.language_model.layers.21.mlp.shared_expert.down_proj",
"model.language_model.layers.21.mlp.shared_expert_gate",
"model.language_model.layers.22.linear_attn.out_proj",
"model.language_model.layers.22.linear_attn.in_proj_qkv",
"model.language_model.layers.22.linear_attn.in_proj_z",
"model.language_model.layers.22.linear_attn.in_proj_b",
"model.language_model.layers.22.linear_attn.in_proj_a",
"model.language_model.layers.22.mlp.shared_expert.gate_proj",
"model.language_model.layers.22.mlp.shared_expert.up_proj",
"model.language_model.layers.22.mlp.shared_expert.down_proj",
"model.language_model.layers.22.mlp.shared_expert_gate",
"model.language_model.layers.23.self_attn.q_proj",
"model.language_model.layers.23.self_attn.k_proj",
"model.language_model.layers.23.self_attn.v_proj",
"model.language_model.layers.23.self_attn.o_proj",
"model.language_model.layers.23.mlp.shared_expert.gate_proj",
"model.language_model.layers.23.mlp.shared_expert.up_proj",
"model.language_model.layers.23.mlp.shared_expert.down_proj",
"model.language_model.layers.23.mlp.shared_expert_gate",
"model.language_model.layers.24.linear_attn.out_proj",
"model.language_model.layers.24.linear_attn.in_proj_qkv",
"model.language_model.layers.24.linear_attn.in_proj_z",
"model.language_model.layers.24.linear_attn.in_proj_b",
"model.language_model.layers.24.linear_attn.in_proj_a",
"model.language_model.layers.24.mlp.shared_expert.gate_proj",
"model.language_model.layers.24.mlp.shared_expert.up_proj",
"model.language_model.layers.24.mlp.shared_expert.down_proj",
"model.language_model.layers.24.mlp.shared_expert_gate",
"model.language_model.layers.25.linear_attn.out_proj",
"model.language_model.layers.25.linear_attn.in_proj_qkv",
"model.language_model.layers.25.linear_attn.in_proj_z",
"model.language_model.layers.25.linear_attn.in_proj_b",
"model.language_model.layers.25.linear_attn.in_proj_a",
"model.language_model.layers.25.mlp.shared_expert.gate_proj",
"model.language_model.layers.25.mlp.shared_expert.up_proj",
"model.language_model.layers.25.mlp.shared_expert.down_proj",
"model.language_model.layers.25.mlp.shared_expert_gate",
"model.language_model.layers.26.linear_attn.out_proj",
"model.language_model.layers.26.linear_attn.in_proj_qkv",
"model.language_model.layers.26.linear_attn.in_proj_z",
"model.language_model.layers.26.linear_attn.in_proj_b",
"model.language_model.layers.26.linear_attn.in_proj_a",
"model.language_model.layers.26.mlp.shared_expert.gate_proj",
"model.language_model.layers.26.mlp.shared_expert.up_proj",
"model.language_model.layers.26.mlp.shared_expert.down_proj",
"model.language_model.layers.26.mlp.shared_expert_gate",
"model.language_model.layers.27.self_attn.q_proj",
"model.language_model.layers.27.self_attn.k_proj",
"model.language_model.layers.27.self_attn.v_proj",
"model.language_model.layers.27.self_attn.o_proj",
"model.language_model.layers.27.mlp.shared_expert.gate_proj",
"model.language_model.layers.27.mlp.shared_expert.up_proj",
"model.language_model.layers.27.mlp.shared_expert.down_proj",
"model.language_model.layers.27.mlp.shared_expert_gate",
"model.language_model.layers.28.linear_attn.out_proj",
"model.language_model.layers.28.linear_attn.in_proj_qkv",
"model.language_model.layers.28.linear_attn.in_proj_z",
"model.language_model.layers.28.linear_attn.in_proj_b",
"model.language_model.layers.28.linear_attn.in_proj_a",
"model.language_model.layers.28.mlp.shared_expert.gate_proj",
"model.language_model.layers.28.mlp.shared_expert.up_proj",
"model.language_model.layers.28.mlp.shared_expert.down_proj",
"model.language_model.layers.28.mlp.shared_expert_gate",
"model.language_model.layers.29.linear_attn.out_proj",
"model.language_model.layers.29.linear_attn.in_proj_qkv",
"model.language_model.layers.29.linear_attn.in_proj_z",
"model.language_model.layers.29.linear_attn.in_proj_b",
"model.language_model.layers.29.linear_attn.in_proj_a",
"model.language_model.layers.29.mlp.shared_expert.gate_proj",
"model.language_model.layers.29.mlp.shared_expert.up_proj",
"model.language_model.layers.29.mlp.shared_expert.down_proj",
"model.language_model.layers.29.mlp.shared_expert_gate",
"model.language_model.layers.30.linear_attn.out_proj",
"model.language_model.layers.30.linear_attn.in_proj_qkv",
"model.language_model.layers.30.linear_attn.in_proj_z",
"model.language_model.layers.30.linear_attn.in_proj_b",
"model.language_model.layers.30.linear_attn.in_proj_a",
"model.language_model.layers.30.mlp.shared_expert.gate_proj",
"model.language_model.layers.30.mlp.shared_expert.up_proj",
"model.language_model.layers.30.mlp.shared_expert.down_proj",
"model.language_model.layers.30.mlp.shared_expert_gate",
"model.language_model.layers.31.self_attn.q_proj",
"model.language_model.layers.31.self_attn.k_proj",
"model.language_model.layers.31.self_attn.v_proj",
"model.language_model.layers.31.self_attn.o_proj",
"model.language_model.layers.31.mlp.shared_expert.gate_proj",
"model.language_model.layers.31.mlp.shared_expert.up_proj",
"model.language_model.layers.31.mlp.shared_expert.down_proj",
"model.language_model.layers.31.mlp.shared_expert_gate",
"model.language_model.layers.32.linear_attn.out_proj",
"model.language_model.layers.32.linear_attn.in_proj_qkv",
"model.language_model.layers.32.linear_attn.in_proj_z",
"model.language_model.layers.32.linear_attn.in_proj_b",
"model.language_model.layers.32.linear_attn.in_proj_a",
"model.language_model.layers.32.mlp.shared_expert.gate_proj",
"model.language_model.layers.32.mlp.shared_expert.up_proj",
"model.language_model.layers.32.mlp.shared_expert.down_proj",
"model.language_model.layers.32.mlp.shared_expert_gate",
"model.language_model.layers.33.linear_attn.out_proj",
"model.language_model.layers.33.linear_attn.in_proj_qkv",
"model.language_model.layers.33.linear_attn.in_proj_z",
"model.language_model.layers.33.linear_attn.in_proj_b",
"model.language_model.layers.33.linear_attn.in_proj_a",
"model.language_model.layers.33.mlp.shared_expert.gate_proj",
"model.language_model.layers.33.mlp.shared_expert.up_proj",
"model.language_model.layers.33.mlp.shared_expert.down_proj",
"model.language_model.layers.33.mlp.shared_expert_gate",
"model.language_model.layers.34.linear_attn.out_proj",
"model.language_model.layers.34.linear_attn.in_proj_qkv",
"model.language_model.layers.34.linear_attn.in_proj_z",
"model.language_model.layers.34.linear_attn.in_proj_b",
"model.language_model.layers.34.linear_attn.in_proj_a",
"model.language_model.layers.34.mlp.shared_expert.gate_proj",
"model.language_model.layers.34.mlp.shared_expert.up_proj",
"model.language_model.layers.34.mlp.shared_expert.down_proj",
"model.language_model.layers.34.mlp.shared_expert_gate",
"model.language_model.layers.35.self_attn.q_proj",
"model.language_model.layers.35.self_attn.k_proj",
"model.language_model.layers.35.self_attn.v_proj",
"model.language_model.layers.35.self_attn.o_proj",
"model.language_model.layers.35.mlp.shared_expert.gate_proj",
"model.language_model.layers.35.mlp.shared_expert.up_proj",
"model.language_model.layers.35.mlp.shared_expert.down_proj",
"model.language_model.layers.35.mlp.shared_expert_gate",
"model.language_model.layers.36.linear_attn.out_proj",
"model.language_model.layers.36.linear_attn.in_proj_qkv",
"model.language_model.layers.36.linear_attn.in_proj_z",
"model.language_model.layers.36.linear_attn.in_proj_b",
"model.language_model.layers.36.linear_attn.in_proj_a",
"model.language_model.layers.36.mlp.shared_expert.gate_proj",
"model.language_model.layers.36.mlp.shared_expert.up_proj",
"model.language_model.layers.36.mlp.shared_expert.down_proj",
"model.language_model.layers.36.mlp.shared_expert_gate",
"model.language_model.layers.37.linear_attn.out_proj",
"model.language_model.layers.37.linear_attn.in_proj_qkv",
"model.language_model.layers.37.linear_attn.in_proj_z",
"model.language_model.layers.37.linear_attn.in_proj_b",
"model.language_model.layers.37.linear_attn.in_proj_a",
"model.language_model.layers.37.mlp.shared_expert.gate_proj",
"model.language_model.layers.37.mlp.shared_expert.up_proj",
"model.language_model.layers.37.mlp.shared_expert.down_proj",
"model.language_model.layers.37.mlp.shared_expert_gate",
"model.language_model.layers.38.linear_attn.out_proj",
"model.language_model.layers.38.linear_attn.in_proj_qkv",
"model.language_model.layers.38.linear_attn.in_proj_z",
"model.language_model.layers.38.linear_attn.in_proj_b",
"model.language_model.layers.38.linear_attn.in_proj_a",
"model.language_model.layers.38.mlp.shared_expert.gate_proj",
"model.language_model.layers.38.mlp.shared_expert.up_proj",
"model.language_model.layers.38.mlp.shared_expert.down_proj",
"model.language_model.layers.38.mlp.shared_expert_gate",
"model.language_model.layers.39.self_attn.q_proj",
"model.language_model.layers.39.self_attn.k_proj",
"model.language_model.layers.39.self_attn.v_proj",
"model.language_model.layers.39.self_attn.o_proj",
"model.language_model.layers.39.mlp.shared_expert.gate_proj",
"model.language_model.layers.39.mlp.shared_expert.up_proj",
"model.language_model.layers.39.mlp.shared_expert.down_proj",
"model.language_model.layers.39.mlp.shared_expert_gate",
"lm_head",
"model.time_series.encoder.adapt_in",
"model.time_series.encoder.adapt_out",
"model.time_series.encoder.layers.0.fc1",
"model.time_series.encoder.layers.0.fc2",
"model.time_series.encoder.layers.0.self_attn.k_proj",
"model.time_series.encoder.layers.0.self_attn.out_proj",
"model.time_series.encoder.layers.0.self_attn.q_proj",
"model.time_series.encoder.layers.0.self_attn.v_proj",
"model.time_series.encoder.layers.1.fc1",
"model.time_series.encoder.layers.1.fc2",
"model.time_series.encoder.layers.1.self_attn.k_proj",
"model.time_series.encoder.layers.1.self_attn.out_proj",
"model.time_series.encoder.layers.1.self_attn.q_proj",
"model.time_series.encoder.layers.1.self_attn.v_proj",
"model.time_series.encoder.layers.10.fc1",
"model.time_series.encoder.layers.10.fc2",
"model.time_series.encoder.layers.10.self_attn.k_proj",
"model.time_series.encoder.layers.10.self_attn.out_proj",
"model.time_series.encoder.layers.10.self_attn.q_proj",
"model.time_series.encoder.layers.10.self_attn.v_proj",
"model.time_series.encoder.layers.11.fc1",
"model.time_series.encoder.layers.11.fc2",
"model.time_series.encoder.layers.11.self_attn.k_proj",
"model.time_series.encoder.layers.11.self_attn.out_proj",
"model.time_series.encoder.layers.11.self_attn.q_proj",
"model.time_series.encoder.layers.11.self_attn.v_proj",
"model.time_series.encoder.layers.12.fc1",
"model.time_series.encoder.layers.12.fc2",
"model.time_series.encoder.layers.12.self_attn.k_proj",
"model.time_series.encoder.layers.12.self_attn.out_proj",
"model.time_series.encoder.layers.12.self_attn.q_proj",
"model.time_series.encoder.layers.12.self_attn.v_proj",
"model.time_series.encoder.layers.13.fc1",
"model.time_series.encoder.layers.13.fc2",
"model.time_series.encoder.layers.13.self_attn.k_proj",
"model.time_series.encoder.layers.13.self_attn.out_proj",
"model.time_series.encoder.layers.13.self_attn.q_proj",
"model.time_series.encoder.layers.13.self_attn.v_proj",
"model.time_series.encoder.layers.14.fc1",
"model.time_series.encoder.layers.14.fc2",
"model.time_series.encoder.layers.14.self_attn.k_proj",
"model.time_series.encoder.layers.14.self_attn.out_proj",
"model.time_series.encoder.layers.14.self_attn.q_proj",
"model.time_series.encoder.layers.14.self_attn.v_proj",
"model.time_series.encoder.layers.15.fc1",
"model.time_series.encoder.layers.15.fc2",
"model.time_series.encoder.layers.15.self_attn.k_proj",
"model.time_series.encoder.layers.15.self_attn.out_proj",
"model.time_series.encoder.layers.15.self_attn.q_proj",
"model.time_series.encoder.layers.15.self_attn.v_proj",
"model.time_series.encoder.layers.16.fc1",
"model.time_series.encoder.layers.16.fc2",
"model.time_series.encoder.layers.16.self_attn.k_proj",
"model.time_series.encoder.layers.16.self_attn.out_proj",
"model.time_series.encoder.layers.16.self_attn.q_proj",
"model.time_series.encoder.layers.16.self_attn.v_proj",
"model.time_series.encoder.layers.2.fc1",
"model.time_series.encoder.layers.2.fc2",
"model.time_series.encoder.layers.2.self_attn.k_proj",
"model.time_series.encoder.layers.2.self_attn.out_proj",
"model.time_series.encoder.layers.2.self_attn.q_proj",
"model.time_series.encoder.layers.2.self_attn.v_proj",
"model.time_series.encoder.layers.3.fc1",
"model.time_series.encoder.layers.3.fc2",
"model.time_series.encoder.layers.3.self_attn.k_proj",
"model.time_series.encoder.layers.3.self_attn.out_proj",
"model.time_series.encoder.layers.3.self_attn.q_proj",
"model.time_series.encoder.layers.3.self_attn.v_proj",
"model.time_series.encoder.layers.4.fc1",
"model.time_series.encoder.layers.4.fc2",
"model.time_series.encoder.layers.4.self_attn.k_proj",
"model.time_series.encoder.layers.4.self_attn.out_proj",
"model.time_series.encoder.layers.4.self_attn.q_proj",
"model.time_series.encoder.layers.4.self_attn.v_proj",
"model.time_series.encoder.layers.5.fc1",
"model.time_series.encoder.layers.5.fc2",
"model.time_series.encoder.layers.5.self_attn.k_proj",
"model.time_series.encoder.layers.5.self_attn.out_proj",
"model.time_series.encoder.layers.5.self_attn.q_proj",
"model.time_series.encoder.layers.5.self_attn.v_proj",
"model.time_series.encoder.layers.6.fc1",
"model.time_series.encoder.layers.6.fc2",
"model.time_series.encoder.layers.6.self_attn.k_proj",
"model.time_series.encoder.layers.6.self_attn.out_proj",
"model.time_series.encoder.layers.6.self_attn.q_proj",
"model.time_series.encoder.layers.6.self_attn.v_proj",
"model.time_series.encoder.layers.7.fc1",
"model.time_series.encoder.layers.7.fc2",
"model.time_series.encoder.layers.7.self_attn.k_proj",
"model.time_series.encoder.layers.7.self_attn.out_proj",
"model.time_series.encoder.layers.7.self_attn.q_proj",
"model.time_series.encoder.layers.7.self_attn.v_proj",
"model.time_series.encoder.layers.8.fc1",
"model.time_series.encoder.layers.8.fc2",
"model.time_series.encoder.layers.8.self_attn.k_proj",
"model.time_series.encoder.layers.8.self_attn.out_proj",
"model.time_series.encoder.layers.8.self_attn.q_proj",
"model.time_series.encoder.layers.8.self_attn.v_proj",
"model.time_series.encoder.layers.9.fc1",
"model.time_series.encoder.layers.9.fc2",
"model.time_series.encoder.layers.9.self_attn.k_proj",
"model.time_series.encoder.layers.9.self_attn.out_proj",
"model.time_series.encoder.layers.9.self_attn.q_proj",
"model.time_series.encoder.layers.9.self_attn.v_proj",
"model.time_series.encoder_embed.transformer_encoder.layers.0.linear1",
"model.time_series.encoder_embed.transformer_encoder.layers.0.linear2",
"model.time_series.encoder_embed.transformer_encoder.layers.0.self_attn.out_proj",
"model.time_series.projector.linear_1",
"model.time_series.projector.linear_2",
"model.visual.blocks.0.attn.proj",
"model.visual.blocks.0.attn.qkv",
"model.visual.blocks.0.mlp.linear_fc1",
"model.visual.blocks.0.mlp.linear_fc2",
"model.visual.blocks.1.attn.proj",
"model.visual.blocks.1.attn.qkv",
"model.visual.blocks.1.mlp.linear_fc1",
"model.visual.blocks.1.mlp.linear_fc2",
"model.visual.blocks.10.attn.proj",
"model.visual.blocks.10.attn.qkv",
"model.visual.blocks.10.mlp.linear_fc1",
"model.visual.blocks.10.mlp.linear_fc2",
"model.visual.blocks.11.attn.proj",
"model.visual.blocks.11.attn.qkv",
"model.visual.blocks.11.mlp.linear_fc1",
"model.visual.blocks.11.mlp.linear_fc2",
"model.visual.blocks.12.attn.proj",
"model.visual.blocks.12.attn.qkv",
"model.visual.blocks.12.mlp.linear_fc1",
"model.visual.blocks.12.mlp.linear_fc2",
"model.visual.blocks.13.attn.proj",
"model.visual.blocks.13.attn.qkv",
"model.visual.blocks.13.mlp.linear_fc1",
"model.visual.blocks.13.mlp.linear_fc2",
"model.visual.blocks.14.attn.proj",
"model.visual.blocks.14.attn.qkv",
"model.visual.blocks.14.mlp.linear_fc1",
"model.visual.blocks.14.mlp.linear_fc2",
"model.visual.blocks.15.attn.proj",
"model.visual.blocks.15.attn.qkv",
"model.visual.blocks.15.mlp.linear_fc1",
"model.visual.blocks.15.mlp.linear_fc2",
"model.visual.blocks.16.attn.proj",
"model.visual.blocks.16.attn.qkv",
"model.visual.blocks.16.mlp.linear_fc1",
"model.visual.blocks.16.mlp.linear_fc2",
"model.visual.blocks.17.attn.proj",
"model.visual.blocks.17.attn.qkv",
"model.visual.blocks.17.mlp.linear_fc1",
"model.visual.blocks.17.mlp.linear_fc2",
"model.visual.blocks.18.attn.proj",
"model.visual.blocks.18.attn.qkv",
"model.visual.blocks.18.mlp.linear_fc1",
"model.visual.blocks.18.mlp.linear_fc2",
"model.visual.blocks.19.attn.proj",
"model.visual.blocks.19.attn.qkv",
"model.visual.blocks.19.mlp.linear_fc1",
"model.visual.blocks.19.mlp.linear_fc2",
"model.visual.blocks.2.attn.proj",
"model.visual.blocks.2.attn.qkv",
"model.visual.blocks.2.mlp.linear_fc1",
"model.visual.blocks.2.mlp.linear_fc2",
"model.visual.blocks.20.attn.proj",
"model.visual.blocks.20.attn.qkv",
"model.visual.blocks.20.mlp.linear_fc1",
"model.visual.blocks.20.mlp.linear_fc2",
"model.visual.blocks.21.attn.proj",
"model.visual.blocks.21.attn.qkv",
"model.visual.blocks.21.mlp.linear_fc1",
"model.visual.blocks.21.mlp.linear_fc2",
"model.visual.blocks.22.attn.proj",
"model.visual.blocks.22.attn.qkv",
"model.visual.blocks.22.mlp.linear_fc1",
"model.visual.blocks.22.mlp.linear_fc2",
"model.visual.blocks.23.attn.proj",
"model.visual.blocks.23.attn.qkv",
"model.visual.blocks.23.mlp.linear_fc1",
"model.visual.blocks.23.mlp.linear_fc2",
"model.visual.blocks.24.attn.proj",
"model.visual.blocks.24.attn.qkv",
"model.visual.blocks.24.mlp.linear_fc1",
"model.visual.blocks.24.mlp.linear_fc2",
"model.visual.blocks.25.attn.proj",
"model.visual.blocks.25.attn.qkv",
"model.visual.blocks.25.mlp.linear_fc1",
"model.visual.blocks.25.mlp.linear_fc2",
"model.visual.blocks.26.attn.proj",
"model.visual.blocks.26.attn.qkv",
"model.visual.blocks.26.mlp.linear_fc1",
"model.visual.blocks.26.mlp.linear_fc2",
"model.visual.blocks.3.attn.proj",
"model.visual.blocks.3.attn.qkv",
"model.visual.blocks.3.mlp.linear_fc1",
"model.visual.blocks.3.mlp.linear_fc2",
"model.visual.blocks.4.attn.proj",
"model.visual.blocks.4.attn.qkv",
"model.visual.blocks.4.mlp.linear_fc1",
"model.visual.blocks.4.mlp.linear_fc2",
"model.visual.blocks.5.attn.proj",
"model.visual.blocks.5.attn.qkv",
"model.visual.blocks.5.mlp.linear_fc1",
"model.visual.blocks.5.mlp.linear_fc2",
"model.visual.blocks.6.attn.proj",
"model.visual.blocks.6.attn.qkv",
"model.visual.blocks.6.mlp.linear_fc1",
"model.visual.blocks.6.mlp.linear_fc2",
"model.visual.blocks.7.attn.proj",
"model.visual.blocks.7.attn.qkv",
"model.visual.blocks.7.mlp.linear_fc1",
"model.visual.blocks.7.mlp.linear_fc2",
"model.visual.blocks.8.attn.proj",
"model.visual.blocks.8.attn.qkv",
"model.visual.blocks.8.mlp.linear_fc1",
"model.visual.blocks.8.mlp.linear_fc2",
"model.visual.blocks.9.attn.proj",
"model.visual.blocks.9.attn.qkv",
"model.visual.blocks.9.mlp.linear_fc1",
"model.visual.blocks.9.mlp.linear_fc2",
"model.visual.merger.linear_fc1",
"model.visual.merger.linear_fc2",
"mtp.fc",
"mtp.layers.0.mlp.gate",
"mtp.layers.0.mlp.shared_expert.down_proj",
"mtp.layers.0.mlp.shared_expert.gate_proj",
"mtp.layers.0.mlp.shared_expert.up_proj",
"mtp.layers.0.mlp.shared_expert_gate",
"mtp.layers.0.self_attn.k_proj",
"mtp.layers.0.self_attn.o_proj",
"mtp.layers.0.self_attn.q_proj",
"mtp.layers.0.self_attn.v_proj"
]
}