MedPLIB-BRISC / adapter_meta.json
Sssunset's picture
Upload MedPLIB-BRISC weights and model card
d1acd9e verified
Raw History Blame Contribute Delete
21.5 kB
{
"n_tensors": 872,
"n_params": 286811620,
"lora": {
"peft_type": "LORA",
"auto_mapping": null,
"base_model_name_or_path": "/mnt/data/peilin/HF_MODEL/MedPLIB-7b-2e",
"revision": null,
"task_type": "CAUSAL_LM",
"inference_mode": false,
"r": 16,
"target_modules": [
"model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.0.self_attn.k_proj",
"model.layers.0.self_attn.o_proj",
"model.layers.0.self_attn.q_proj",
"model.layers.0.self_attn.v_proj",
"model.layers.1.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.1.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.1.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.1.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.1.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.1.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.1.self_attn.k_proj",
"model.layers.1.self_attn.o_proj",
"model.layers.1.self_attn.q_proj",
"model.layers.1.self_attn.v_proj",
"model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.10.self_attn.k_proj",
"model.layers.10.self_attn.o_proj",
"model.layers.10.self_attn.q_proj",
"model.layers.10.self_attn.v_proj",
"model.layers.11.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.11.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.11.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.11.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.11.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.11.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.11.self_attn.k_proj",
"model.layers.11.self_attn.o_proj",
"model.layers.11.self_attn.q_proj",
"model.layers.11.self_attn.v_proj",
"model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.12.self_attn.k_proj",
"model.layers.12.self_attn.o_proj",
"model.layers.12.self_attn.q_proj",
"model.layers.12.self_attn.v_proj",
"model.layers.13.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.13.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.13.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.13.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.13.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.13.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.13.self_attn.k_proj",
"model.layers.13.self_attn.o_proj",
"model.layers.13.self_attn.q_proj",
"model.layers.13.self_attn.v_proj",
"model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.14.self_attn.k_proj",
"model.layers.14.self_attn.o_proj",
"model.layers.14.self_attn.q_proj",
"model.layers.14.self_attn.v_proj",
"model.layers.15.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.15.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.15.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.15.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.15.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.15.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.15.self_attn.k_proj",
"model.layers.15.self_attn.o_proj",
"model.layers.15.self_attn.q_proj",
"model.layers.15.self_attn.v_proj",
"model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.16.self_attn.k_proj",
"model.layers.16.self_attn.o_proj",
"model.layers.16.self_attn.q_proj",
"model.layers.16.self_attn.v_proj",
"model.layers.17.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.17.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.17.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.17.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.17.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.17.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.17.self_attn.k_proj",
"model.layers.17.self_attn.o_proj",
"model.layers.17.self_attn.q_proj",
"model.layers.17.self_attn.v_proj",
"model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.18.self_attn.k_proj",
"model.layers.18.self_attn.o_proj",
"model.layers.18.self_attn.q_proj",
"model.layers.18.self_attn.v_proj",
"model.layers.19.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.19.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.19.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.19.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.19.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.19.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.19.self_attn.k_proj",
"model.layers.19.self_attn.o_proj",
"model.layers.19.self_attn.q_proj",
"model.layers.19.self_attn.v_proj",
"model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.2.self_attn.k_proj",
"model.layers.2.self_attn.o_proj",
"model.layers.2.self_attn.q_proj",
"model.layers.2.self_attn.v_proj",
"model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.20.self_attn.k_proj",
"model.layers.20.self_attn.o_proj",
"model.layers.20.self_attn.q_proj",
"model.layers.20.self_attn.v_proj",
"model.layers.21.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.21.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.21.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.21.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.21.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.21.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.21.self_attn.k_proj",
"model.layers.21.self_attn.o_proj",
"model.layers.21.self_attn.q_proj",
"model.layers.21.self_attn.v_proj",
"model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.22.self_attn.k_proj",
"model.layers.22.self_attn.o_proj",
"model.layers.22.self_attn.q_proj",
"model.layers.22.self_attn.v_proj",
"model.layers.23.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.23.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.23.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.23.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.23.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.23.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.23.self_attn.k_proj",
"model.layers.23.self_attn.o_proj",
"model.layers.23.self_attn.q_proj",
"model.layers.23.self_attn.v_proj",
"model.layers.24.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.24.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.24.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.24.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.24.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.24.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.24.self_attn.k_proj",
"model.layers.24.self_attn.o_proj",
"model.layers.24.self_attn.q_proj",
"model.layers.24.self_attn.v_proj",
"model.layers.25.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.25.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.25.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.25.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.25.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.25.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.25.self_attn.k_proj",
"model.layers.25.self_attn.o_proj",
"model.layers.25.self_attn.q_proj",
"model.layers.25.self_attn.v_proj",
"model.layers.26.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.26.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.26.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.26.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.26.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.26.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.26.self_attn.k_proj",
"model.layers.26.self_attn.o_proj",
"model.layers.26.self_attn.q_proj",
"model.layers.26.self_attn.v_proj",
"model.layers.27.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.27.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.27.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.27.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.27.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.27.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.27.self_attn.k_proj",
"model.layers.27.self_attn.o_proj",
"model.layers.27.self_attn.q_proj",
"model.layers.27.self_attn.v_proj",
"model.layers.28.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.28.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.28.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.28.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.28.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.28.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.28.self_attn.k_proj",
"model.layers.28.self_attn.o_proj",
"model.layers.28.self_attn.q_proj",
"model.layers.28.self_attn.v_proj",
"model.layers.29.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.29.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.29.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.29.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.29.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.29.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.29.self_attn.k_proj",
"model.layers.29.self_attn.o_proj",
"model.layers.29.self_attn.q_proj",
"model.layers.29.self_attn.v_proj",
"model.layers.3.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.3.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.3.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.3.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.3.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.3.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.3.self_attn.k_proj",
"model.layers.3.self_attn.o_proj",
"model.layers.3.self_attn.q_proj",
"model.layers.3.self_attn.v_proj",
"model.layers.30.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.30.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.30.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.30.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.30.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.30.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.30.self_attn.k_proj",
"model.layers.30.self_attn.o_proj",
"model.layers.30.self_attn.q_proj",
"model.layers.30.self_attn.v_proj",
"model.layers.31.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.31.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.31.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.31.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.31.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.31.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.31.self_attn.k_proj",
"model.layers.31.self_attn.o_proj",
"model.layers.31.self_attn.q_proj",
"model.layers.31.self_attn.v_proj",
"model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.4.self_attn.k_proj",
"model.layers.4.self_attn.o_proj",
"model.layers.4.self_attn.q_proj",
"model.layers.4.self_attn.v_proj",
"model.layers.5.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.5.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.5.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.5.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.5.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.5.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.5.self_attn.k_proj",
"model.layers.5.self_attn.o_proj",
"model.layers.5.self_attn.q_proj",
"model.layers.5.self_attn.v_proj",
"model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.6.self_attn.k_proj",
"model.layers.6.self_attn.o_proj",
"model.layers.6.self_attn.q_proj",
"model.layers.6.self_attn.v_proj",
"model.layers.7.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.7.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.7.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.7.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.7.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.7.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.7.self_attn.k_proj",
"model.layers.7.self_attn.o_proj",
"model.layers.7.self_attn.q_proj",
"model.layers.7.self_attn.v_proj",
"model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.8.self_attn.k_proj",
"model.layers.8.self_attn.o_proj",
"model.layers.8.self_attn.q_proj",
"model.layers.8.self_attn.v_proj",
"model.layers.9.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj",
"model.layers.9.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj",
"model.layers.9.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj",
"model.layers.9.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj",
"model.layers.9.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj",
"model.layers.9.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj",
"model.layers.9.self_attn.k_proj",
"model.layers.9.self_attn.o_proj",
"model.layers.9.self_attn.q_proj",
"model.layers.9.self_attn.v_proj"
],
"lora_alpha": 32,
"lora_dropout": 0.05,
"fan_in_fan_out": false,
"bias": "none",
"use_rslora": false,
"modules_to_save": null,
"init_lora_weights": true,
"layers_to_transform": null,
"layers_pattern": null,
"rank_pattern": {},
"alpha_pattern": {},
"megatron_config": null,
"megatron_core": "megatron.core",
"loftq_config": {},
"use_dora": false,
"layer_replication": null
},
"epoch": 11,
"stage": "B",
"seed": 42,
"opt_steps": 937
}