load_keys.json

{"all_checkpoint_keys": ["transformer.wte.weight", "transformer.wpe.weight", "transformer.h.0.ln_1.weight", "transformer.h.0.ln_1.bias", "transformer.h.0.attn.attention.k_proj.weight", "transformer.h.0.attn.attention.v_proj.weight", "transformer.h.0.attn.attention.q_proj.weight", "transformer.h.0.attn.attention.out_proj.weight", "transformer.h.0.attn.attention.out_proj.bias", "transformer.h.0.ln_2.weight", "transformer.h.0.ln_2.bias", "transformer.h.0.mlp.c_fc.weight", "transformer.h.0.mlp.c_fc.bias", "transformer.h.0.mlp.c_proj.weight", "transformer.h.0.mlp.c_proj.bias", "transformer.h.1.ln_1.weight", "transformer.h.1.ln_1.bias", "transformer.h.1.attn.attention.k_proj.weight", "transformer.h.1.attn.attention.v_proj.weight", "transformer.h.1.attn.attention.q_proj.weight", "transformer.h.1.attn.attention.out_proj.weight", "transformer.h.1.attn.attention.out_proj.bias", "transformer.h.1.ln_2.weight", "transformer.h.1.ln_2.bias", "transformer.h.1.mlp.c_fc.weight", "transformer.h.1.mlp.c_fc.bias", "transformer.h.1.mlp.c_proj.weight", "transformer.h.1.mlp.c_proj.bias", "transformer.h.2.ln_1.weight", "transformer.h.2.ln_1.bias", "transformer.h.2.attn.attention.k_proj.weight", "transformer.h.2.attn.attention.v_proj.weight", "transformer.h.2.attn.attention.q_proj.weight", "transformer.h.2.attn.attention.out_proj.weight", "transformer.h.2.attn.attention.out_proj.bias", "transformer.h.2.ln_2.weight", "transformer.h.2.ln_2.bias", "transformer.h.2.mlp.c_fc.weight", "transformer.h.2.mlp.c_fc.bias", "transformer.h.2.mlp.c_proj.weight", "transformer.h.2.mlp.c_proj.bias", "transformer.h.3.ln_1.weight", "transformer.h.3.ln_1.bias", "transformer.h.3.attn.attention.k_proj.weight", "transformer.h.3.attn.attention.v_proj.weight", "transformer.h.3.attn.attention.q_proj.weight", "transformer.h.3.attn.attention.out_proj.weight", "transformer.h.3.attn.attention.out_proj.bias", "transformer.h.3.ln_2.weight", "transformer.h.3.ln_2.bias", "transformer.h.3.mlp.c_fc.weight", "transformer.h.3.mlp.c_fc.bias", "transformer.h.3.mlp.c_proj.weight", "transformer.h.3.mlp.c_proj.bias", "transformer.h.4.ln_1.weight", "transformer.h.4.ln_1.bias", "transformer.h.4.attn.attention.k_proj.weight", "transformer.h.4.attn.attention.v_proj.weight", "transformer.h.4.attn.attention.q_proj.weight", "transformer.h.4.attn.attention.out_proj.weight", "transformer.h.4.attn.attention.out_proj.bias", "transformer.h.4.ln_2.weight", "transformer.h.4.ln_2.bias", "transformer.h.4.mlp.c_fc.weight", "transformer.h.4.mlp.c_fc.bias", "transformer.h.4.mlp.c_proj.weight", "transformer.h.4.mlp.c_proj.bias", "transformer.h.5.ln_1.weight", "transformer.h.5.ln_1.bias", "transformer.h.5.attn.attention.k_proj.weight", "transformer.h.5.attn.attention.v_proj.weight", "transformer.h.5.attn.attention.q_proj.weight", "transformer.h.5.attn.attention.out_proj.weight", "transformer.h.5.attn.attention.out_proj.bias", "transformer.h.5.ln_2.weight", "transformer.h.5.ln_2.bias", "transformer.h.5.mlp.c_fc.weight", "transformer.h.5.mlp.c_fc.bias", "transformer.h.5.mlp.c_proj.weight", "transformer.h.5.mlp.c_proj.bias", "transformer.h.6.ln_1.weight", "transformer.h.6.ln_1.bias", "transformer.h.6.attn.attention.k_proj.weight", "transformer.h.6.attn.attention.v_proj.weight", "transformer.h.6.attn.attention.q_proj.weight", "transformer.h.6.attn.attention.out_proj.weight", "transformer.h.6.attn.attention.out_proj.bias", "transformer.h.6.ln_2.weight", "transformer.h.6.ln_2.bias", "transformer.h.6.mlp.c_fc.weight", "transformer.h.6.mlp.c_fc.bias", "transformer.h.6.mlp.c_proj.weight", "transformer.h.6.mlp.c_proj.bias", "transformer.h.7.ln_1.weight", "transformer.h.7.ln_1.bias", "transformer.h.7.attn.attention.k_proj.weight", "transformer.h.7.attn.attention.v_proj.weight", "transformer.h.7.attn.attention.q_proj.weight", "transformer.h.7.attn.attention.out_proj.weight", "transformer.h.7.attn.attention.out_proj.bias", "transformer.h.7.ln_2.weight", "transformer.h.7.ln_2.bias", "transformer.h.7.mlp.c_fc.weight", "transformer.h.7.mlp.c_fc.bias", "transformer.h.7.mlp.c_proj.weight", "transformer.h.7.mlp.c_proj.bias", "transformer.h.8.ln_1.weight", "transformer.h.8.ln_1.bias", "transformer.h.8.attn.attention.k_proj.weight", "transformer.h.8.attn.attention.v_proj.weight", "transformer.h.8.attn.attention.q_proj.weight", "transformer.h.8.attn.attention.out_proj.weight", "transformer.h.8.attn.attention.out_proj.bias", "transformer.h.8.ln_2.weight", "transformer.h.8.ln_2.bias", "transformer.h.8.mlp.c_fc.weight", "transformer.h.8.mlp.c_fc.bias", "transformer.h.8.mlp.c_proj.weight", "transformer.h.8.mlp.c_proj.bias", "transformer.h.9.ln_1.weight", "transformer.h.9.ln_1.bias", "transformer.h.9.attn.attention.k_proj.weight", "transformer.h.9.attn.attention.v_proj.weight", "transformer.h.9.attn.attention.q_proj.weight", "transformer.h.9.attn.attention.out_proj.weight", "transformer.h.9.attn.attention.out_proj.bias", "transformer.h.9.ln_2.weight", "transformer.h.9.ln_2.bias", "transformer.h.9.mlp.c_fc.weight", "transformer.h.9.mlp.c_fc.bias", "transformer.h.9.mlp.c_proj.weight", "transformer.h.9.mlp.c_proj.bias", "transformer.h.10.ln_1.weight", "transformer.h.10.ln_1.bias", "transformer.h.10.attn.attention.k_proj.weight", "transformer.h.10.attn.attention.v_proj.weight", "transformer.h.10.attn.attention.q_proj.weight", "transformer.h.10.attn.attention.out_proj.weight", "transformer.h.10.attn.attention.out_proj.bias", "transformer.h.10.ln_2.weight", "transformer.h.10.ln_2.bias", "transformer.h.10.mlp.c_fc.weight", "transformer.h.10.mlp.c_fc.bias", "transformer.h.10.mlp.c_proj.weight", "transformer.h.10.mlp.c_proj.bias", "transformer.h.11.ln_1.weight", "transformer.h.11.ln_1.bias", "transformer.h.11.attn.attention.k_proj.weight", "transformer.h.11.attn.attention.v_proj.weight", "transformer.h.11.attn.attention.q_proj.weight", "transformer.h.11.attn.attention.out_proj.weight", "transformer.h.11.attn.attention.out_proj.bias", "transformer.h.11.ln_2.weight", "transformer.h.11.ln_2.bias", "transformer.h.11.mlp.c_fc.weight", "transformer.h.11.mlp.c_fc.bias", "transformer.h.11.mlp.c_proj.weight", "transformer.h.11.mlp.c_proj.bias", "transformer.h.12.ln_1.weight", "transformer.h.12.ln_1.bias", "transformer.h.12.attn.attention.k_proj.weight", "transformer.h.12.attn.attention.v_proj.weight", "transformer.h.12.attn.attention.q_proj.weight", "transformer.h.12.attn.attention.out_proj.weight", "transformer.h.12.attn.attention.out_proj.bias", "transformer.h.12.ln_2.weight", "transformer.h.12.ln_2.bias", "transformer.h.12.mlp.c_fc.weight", "transformer.h.12.mlp.c_fc.bias", "transformer.h.12.mlp.c_proj.weight", "transformer.h.12.mlp.c_proj.bias", "transformer.h.13.ln_1.weight", "transformer.h.13.ln_1.bias", "transformer.h.13.attn.attention.k_proj.weight", "transformer.h.13.attn.attention.v_proj.weight", "transformer.h.13.attn.attention.q_proj.weight", "transformer.h.13.attn.attention.out_proj.weight", "transformer.h.13.attn.attention.out_proj.bias", "transformer.h.13.ln_2.weight", "transformer.h.13.ln_2.bias", "transformer.h.13.mlp.c_fc.weight", "transformer.h.13.mlp.c_fc.bias", "transformer.h.13.mlp.c_proj.weight", "transformer.h.13.mlp.c_proj.bias", "transformer.h.14.ln_1.weight", "transformer.h.14.ln_1.bias", "transformer.h.14.attn.attention.k_proj.weight", "transformer.h.14.attn.attention.v_proj.weight", "transformer.h.14.attn.attention.q_proj.weight", "transformer.h.14.attn.attention.out_proj.weight", "transformer.h.14.attn.attention.out_proj.bias", "transformer.h.14.ln_2.weight", "transformer.h.14.ln_2.bias", "transformer.h.14.mlp.c_fc.weight", "transformer.h.14.mlp.c_fc.bias", "transformer.h.14.mlp.c_proj.weight", "transformer.h.14.mlp.c_proj.bias", "transformer.h.15.ln_1.weight", "transformer.h.15.ln_1.bias", "transformer.h.15.attn.attention.k_proj.weight", "transformer.h.15.attn.attention.v_proj.weight", "transformer.h.15.attn.attention.q_proj.weight", "transformer.h.15.attn.attention.out_proj.weight", "transformer.h.15.attn.attention.out_proj.bias", "transformer.h.15.ln_2.weight", "transformer.h.15.ln_2.bias", "transformer.h.15.mlp.c_fc.weight", "transformer.h.15.mlp.c_fc.bias", "transformer.h.15.mlp.c_proj.weight", "transformer.h.15.mlp.c_proj.bias", "transformer.h.16.ln_1.weight", "transformer.h.16.ln_1.bias", "transformer.h.16.attn.attention.k_proj.weight", "transformer.h.16.attn.attention.v_proj.weight", "transformer.h.16.attn.attention.q_proj.weight", "transformer.h.16.attn.attention.out_proj.weight", "transformer.h.16.attn.attention.out_proj.bias", "transformer.h.16.ln_2.weight", "transformer.h.16.ln_2.bias", "transformer.h.16.mlp.c_fc.weight", "transformer.h.16.mlp.c_fc.bias", "transformer.h.16.mlp.c_proj.weight", "transformer.h.16.mlp.c_proj.bias", "transformer.h.17.ln_1.weight", "transformer.h.17.ln_1.bias", "transformer.h.17.attn.attention.k_proj.weight", "transformer.h.17.attn.attention.v_proj.weight", "transformer.h.17.attn.attention.q_proj.weight", "transformer.h.17.attn.attention.out_proj.weight", "transformer.h.17.attn.attention.out_proj.bias", "transformer.h.17.ln_2.weight", "transformer.h.17.ln_2.bias", "transformer.h.17.mlp.c_fc.weight", "transformer.h.17.mlp.c_fc.bias", "transformer.h.17.mlp.c_proj.weight", "transformer.h.17.mlp.c_proj.bias", "transformer.h.18.ln_1.weight", "transformer.h.18.ln_1.bias", "transformer.h.18.attn.attention.k_proj.weight", "transformer.h.18.attn.attention.v_proj.weight", "transformer.h.18.attn.attention.q_proj.weight", "transformer.h.18.attn.attention.out_proj.weight", "transformer.h.18.attn.attention.out_proj.bias", "transformer.h.18.ln_2.weight", "transformer.h.18.ln_2.bias", "transformer.h.18.mlp.c_fc.weight", "transformer.h.18.mlp.c_fc.bias", "transformer.h.18.mlp.c_proj.weight", "transformer.h.18.mlp.c_proj.bias", "transformer.h.19.ln_1.weight", "transformer.h.19.ln_1.bias", "transformer.h.19.attn.attention.k_proj.weight", "transformer.h.19.attn.attention.v_proj.weight", "transformer.h.19.attn.attention.q_proj.weight", "transformer.h.19.attn.attention.out_proj.weight", "transformer.h.19.attn.attention.out_proj.bias", "transformer.h.19.ln_2.weight", "transformer.h.19.ln_2.bias", "transformer.h.19.mlp.c_fc.weight", "transformer.h.19.mlp.c_fc.bias", "transformer.h.19.mlp.c_proj.weight", "transformer.h.19.mlp.c_proj.bias", "transformer.h.20.ln_1.weight", "transformer.h.20.ln_1.bias", "transformer.h.20.attn.attention.k_proj.weight", "transformer.h.20.attn.attention.v_proj.weight", "transformer.h.20.attn.attention.q_proj.weight", "transformer.h.20.attn.attention.out_proj.weight", "transformer.h.20.attn.attention.out_proj.bias", "transformer.h.20.ln_2.weight", "transformer.h.20.ln_2.bias", "transformer.h.20.mlp.c_fc.weight", "transformer.h.20.mlp.c_fc.bias", "transformer.h.20.mlp.c_proj.weight", "transformer.h.20.mlp.c_proj.bias", "transformer.h.21.ln_1.weight", "transformer.h.21.ln_1.bias", "transformer.h.21.attn.attention.k_proj.weight", "transformer.h.21.attn.attention.v_proj.weight", "transformer.h.21.attn.attention.q_proj.weight", "transformer.h.21.attn.attention.out_proj.weight", "transformer.h.21.attn.attention.out_proj.bias", "transformer.h.21.ln_2.weight", "transformer.h.21.ln_2.bias", "transformer.h.21.mlp.c_fc.weight", "transformer.h.21.mlp.c_fc.bias", "transformer.h.21.mlp.c_proj.weight", "transformer.h.21.mlp.c_proj.bias", "transformer.h.22.ln_1.weight", "transformer.h.22.ln_1.bias", "transformer.h.22.attn.attention.k_proj.weight", "transformer.h.22.attn.attention.v_proj.weight", "transformer.h.22.attn.attention.q_proj.weight", "transformer.h.22.attn.attention.out_proj.weight", "transformer.h.22.attn.attention.out_proj.bias", "transformer.h.22.ln_2.weight", "transformer.h.22.ln_2.bias", "transformer.h.22.mlp.c_fc.weight", "transformer.h.22.mlp.c_fc.bias", "transformer.h.22.mlp.c_proj.weight", "transformer.h.22.mlp.c_proj.bias", "transformer.h.23.ln_1.weight", "transformer.h.23.ln_1.bias", "transformer.h.23.attn.attention.k_proj.weight", "transformer.h.23.attn.attention.v_proj.weight", "transformer.h.23.attn.attention.q_proj.weight", "transformer.h.23.attn.attention.out_proj.weight", "transformer.h.23.attn.attention.out_proj.bias", "transformer.h.23.ln_2.weight", "transformer.h.23.ln_2.bias", "transformer.h.23.mlp.c_fc.weight", "transformer.h.23.mlp.c_fc.bias", "transformer.h.23.mlp.c_proj.weight", "transformer.h.23.mlp.c_proj.bias", "transformer.ln_f.weight", "transformer.ln_f.bias", "lm_head.weight"]}