390 lines
18 KiB
Plaintext
390 lines
18 KiB
Plaintext
ln_final.bias [1280]
|
|
ln_final.weight [1280]
|
|
logit_scale []
|
|
positional_embedding [77,1280]
|
|
text_projection [1280,1280]
|
|
token_embedding.weight [49408,1280]
|
|
transformer.resblocks.0.attn.in_proj_bias [3840]
|
|
transformer.resblocks.0.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.0.attn.out_proj.bias [1280]
|
|
transformer.resblocks.0.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.0.ln_1.bias [1280]
|
|
transformer.resblocks.0.ln_1.weight [1280]
|
|
transformer.resblocks.0.ln_2.bias [1280]
|
|
transformer.resblocks.0.ln_2.weight [1280]
|
|
transformer.resblocks.0.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.0.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.0.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.0.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.1.attn.in_proj_bias [3840]
|
|
transformer.resblocks.1.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.1.attn.out_proj.bias [1280]
|
|
transformer.resblocks.1.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.1.ln_1.bias [1280]
|
|
transformer.resblocks.1.ln_1.weight [1280]
|
|
transformer.resblocks.1.ln_2.bias [1280]
|
|
transformer.resblocks.1.ln_2.weight [1280]
|
|
transformer.resblocks.1.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.1.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.1.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.1.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.10.attn.in_proj_bias [3840]
|
|
transformer.resblocks.10.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.10.attn.out_proj.bias [1280]
|
|
transformer.resblocks.10.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.10.ln_1.bias [1280]
|
|
transformer.resblocks.10.ln_1.weight [1280]
|
|
transformer.resblocks.10.ln_2.bias [1280]
|
|
transformer.resblocks.10.ln_2.weight [1280]
|
|
transformer.resblocks.10.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.10.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.10.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.10.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.11.attn.in_proj_bias [3840]
|
|
transformer.resblocks.11.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.11.attn.out_proj.bias [1280]
|
|
transformer.resblocks.11.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.11.ln_1.bias [1280]
|
|
transformer.resblocks.11.ln_1.weight [1280]
|
|
transformer.resblocks.11.ln_2.bias [1280]
|
|
transformer.resblocks.11.ln_2.weight [1280]
|
|
transformer.resblocks.11.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.11.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.11.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.11.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.12.attn.in_proj_bias [3840]
|
|
transformer.resblocks.12.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.12.attn.out_proj.bias [1280]
|
|
transformer.resblocks.12.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.12.ln_1.bias [1280]
|
|
transformer.resblocks.12.ln_1.weight [1280]
|
|
transformer.resblocks.12.ln_2.bias [1280]
|
|
transformer.resblocks.12.ln_2.weight [1280]
|
|
transformer.resblocks.12.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.12.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.12.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.12.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.13.attn.in_proj_bias [3840]
|
|
transformer.resblocks.13.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.13.attn.out_proj.bias [1280]
|
|
transformer.resblocks.13.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.13.ln_1.bias [1280]
|
|
transformer.resblocks.13.ln_1.weight [1280]
|
|
transformer.resblocks.13.ln_2.bias [1280]
|
|
transformer.resblocks.13.ln_2.weight [1280]
|
|
transformer.resblocks.13.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.13.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.13.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.13.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.14.attn.in_proj_bias [3840]
|
|
transformer.resblocks.14.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.14.attn.out_proj.bias [1280]
|
|
transformer.resblocks.14.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.14.ln_1.bias [1280]
|
|
transformer.resblocks.14.ln_1.weight [1280]
|
|
transformer.resblocks.14.ln_2.bias [1280]
|
|
transformer.resblocks.14.ln_2.weight [1280]
|
|
transformer.resblocks.14.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.14.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.14.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.14.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.15.attn.in_proj_bias [3840]
|
|
transformer.resblocks.15.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.15.attn.out_proj.bias [1280]
|
|
transformer.resblocks.15.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.15.ln_1.bias [1280]
|
|
transformer.resblocks.15.ln_1.weight [1280]
|
|
transformer.resblocks.15.ln_2.bias [1280]
|
|
transformer.resblocks.15.ln_2.weight [1280]
|
|
transformer.resblocks.15.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.15.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.15.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.15.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.16.attn.in_proj_bias [3840]
|
|
transformer.resblocks.16.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.16.attn.out_proj.bias [1280]
|
|
transformer.resblocks.16.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.16.ln_1.bias [1280]
|
|
transformer.resblocks.16.ln_1.weight [1280]
|
|
transformer.resblocks.16.ln_2.bias [1280]
|
|
transformer.resblocks.16.ln_2.weight [1280]
|
|
transformer.resblocks.16.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.16.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.16.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.16.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.17.attn.in_proj_bias [3840]
|
|
transformer.resblocks.17.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.17.attn.out_proj.bias [1280]
|
|
transformer.resblocks.17.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.17.ln_1.bias [1280]
|
|
transformer.resblocks.17.ln_1.weight [1280]
|
|
transformer.resblocks.17.ln_2.bias [1280]
|
|
transformer.resblocks.17.ln_2.weight [1280]
|
|
transformer.resblocks.17.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.17.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.17.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.17.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.18.attn.in_proj_bias [3840]
|
|
transformer.resblocks.18.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.18.attn.out_proj.bias [1280]
|
|
transformer.resblocks.18.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.18.ln_1.bias [1280]
|
|
transformer.resblocks.18.ln_1.weight [1280]
|
|
transformer.resblocks.18.ln_2.bias [1280]
|
|
transformer.resblocks.18.ln_2.weight [1280]
|
|
transformer.resblocks.18.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.18.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.18.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.18.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.19.attn.in_proj_bias [3840]
|
|
transformer.resblocks.19.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.19.attn.out_proj.bias [1280]
|
|
transformer.resblocks.19.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.19.ln_1.bias [1280]
|
|
transformer.resblocks.19.ln_1.weight [1280]
|
|
transformer.resblocks.19.ln_2.bias [1280]
|
|
transformer.resblocks.19.ln_2.weight [1280]
|
|
transformer.resblocks.19.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.19.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.19.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.19.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.2.attn.in_proj_bias [3840]
|
|
transformer.resblocks.2.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.2.attn.out_proj.bias [1280]
|
|
transformer.resblocks.2.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.2.ln_1.bias [1280]
|
|
transformer.resblocks.2.ln_1.weight [1280]
|
|
transformer.resblocks.2.ln_2.bias [1280]
|
|
transformer.resblocks.2.ln_2.weight [1280]
|
|
transformer.resblocks.2.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.2.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.2.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.2.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.20.attn.in_proj_bias [3840]
|
|
transformer.resblocks.20.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.20.attn.out_proj.bias [1280]
|
|
transformer.resblocks.20.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.20.ln_1.bias [1280]
|
|
transformer.resblocks.20.ln_1.weight [1280]
|
|
transformer.resblocks.20.ln_2.bias [1280]
|
|
transformer.resblocks.20.ln_2.weight [1280]
|
|
transformer.resblocks.20.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.20.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.20.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.20.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.21.attn.in_proj_bias [3840]
|
|
transformer.resblocks.21.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.21.attn.out_proj.bias [1280]
|
|
transformer.resblocks.21.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.21.ln_1.bias [1280]
|
|
transformer.resblocks.21.ln_1.weight [1280]
|
|
transformer.resblocks.21.ln_2.bias [1280]
|
|
transformer.resblocks.21.ln_2.weight [1280]
|
|
transformer.resblocks.21.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.21.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.21.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.21.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.22.attn.in_proj_bias [3840]
|
|
transformer.resblocks.22.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.22.attn.out_proj.bias [1280]
|
|
transformer.resblocks.22.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.22.ln_1.bias [1280]
|
|
transformer.resblocks.22.ln_1.weight [1280]
|
|
transformer.resblocks.22.ln_2.bias [1280]
|
|
transformer.resblocks.22.ln_2.weight [1280]
|
|
transformer.resblocks.22.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.22.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.22.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.22.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.23.attn.in_proj_bias [3840]
|
|
transformer.resblocks.23.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.23.attn.out_proj.bias [1280]
|
|
transformer.resblocks.23.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.23.ln_1.bias [1280]
|
|
transformer.resblocks.23.ln_1.weight [1280]
|
|
transformer.resblocks.23.ln_2.bias [1280]
|
|
transformer.resblocks.23.ln_2.weight [1280]
|
|
transformer.resblocks.23.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.23.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.23.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.23.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.24.attn.in_proj_bias [3840]
|
|
transformer.resblocks.24.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.24.attn.out_proj.bias [1280]
|
|
transformer.resblocks.24.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.24.ln_1.bias [1280]
|
|
transformer.resblocks.24.ln_1.weight [1280]
|
|
transformer.resblocks.24.ln_2.bias [1280]
|
|
transformer.resblocks.24.ln_2.weight [1280]
|
|
transformer.resblocks.24.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.24.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.24.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.24.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.25.attn.in_proj_bias [3840]
|
|
transformer.resblocks.25.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.25.attn.out_proj.bias [1280]
|
|
transformer.resblocks.25.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.25.ln_1.bias [1280]
|
|
transformer.resblocks.25.ln_1.weight [1280]
|
|
transformer.resblocks.25.ln_2.bias [1280]
|
|
transformer.resblocks.25.ln_2.weight [1280]
|
|
transformer.resblocks.25.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.25.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.25.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.25.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.26.attn.in_proj_bias [3840]
|
|
transformer.resblocks.26.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.26.attn.out_proj.bias [1280]
|
|
transformer.resblocks.26.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.26.ln_1.bias [1280]
|
|
transformer.resblocks.26.ln_1.weight [1280]
|
|
transformer.resblocks.26.ln_2.bias [1280]
|
|
transformer.resblocks.26.ln_2.weight [1280]
|
|
transformer.resblocks.26.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.26.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.26.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.26.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.27.attn.in_proj_bias [3840]
|
|
transformer.resblocks.27.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.27.attn.out_proj.bias [1280]
|
|
transformer.resblocks.27.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.27.ln_1.bias [1280]
|
|
transformer.resblocks.27.ln_1.weight [1280]
|
|
transformer.resblocks.27.ln_2.bias [1280]
|
|
transformer.resblocks.27.ln_2.weight [1280]
|
|
transformer.resblocks.27.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.27.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.27.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.27.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.28.attn.in_proj_bias [3840]
|
|
transformer.resblocks.28.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.28.attn.out_proj.bias [1280]
|
|
transformer.resblocks.28.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.28.ln_1.bias [1280]
|
|
transformer.resblocks.28.ln_1.weight [1280]
|
|
transformer.resblocks.28.ln_2.bias [1280]
|
|
transformer.resblocks.28.ln_2.weight [1280]
|
|
transformer.resblocks.28.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.28.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.28.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.28.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.29.attn.in_proj_bias [3840]
|
|
transformer.resblocks.29.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.29.attn.out_proj.bias [1280]
|
|
transformer.resblocks.29.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.29.ln_1.bias [1280]
|
|
transformer.resblocks.29.ln_1.weight [1280]
|
|
transformer.resblocks.29.ln_2.bias [1280]
|
|
transformer.resblocks.29.ln_2.weight [1280]
|
|
transformer.resblocks.29.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.29.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.29.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.29.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.3.attn.in_proj_bias [3840]
|
|
transformer.resblocks.3.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.3.attn.out_proj.bias [1280]
|
|
transformer.resblocks.3.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.3.ln_1.bias [1280]
|
|
transformer.resblocks.3.ln_1.weight [1280]
|
|
transformer.resblocks.3.ln_2.bias [1280]
|
|
transformer.resblocks.3.ln_2.weight [1280]
|
|
transformer.resblocks.3.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.3.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.3.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.3.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.30.attn.in_proj_bias [3840]
|
|
transformer.resblocks.30.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.30.attn.out_proj.bias [1280]
|
|
transformer.resblocks.30.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.30.ln_1.bias [1280]
|
|
transformer.resblocks.30.ln_1.weight [1280]
|
|
transformer.resblocks.30.ln_2.bias [1280]
|
|
transformer.resblocks.30.ln_2.weight [1280]
|
|
transformer.resblocks.30.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.30.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.30.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.30.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.31.attn.in_proj_bias [3840]
|
|
transformer.resblocks.31.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.31.attn.out_proj.bias [1280]
|
|
transformer.resblocks.31.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.31.ln_1.bias [1280]
|
|
transformer.resblocks.31.ln_1.weight [1280]
|
|
transformer.resblocks.31.ln_2.bias [1280]
|
|
transformer.resblocks.31.ln_2.weight [1280]
|
|
transformer.resblocks.31.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.31.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.31.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.31.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.4.attn.in_proj_bias [3840]
|
|
transformer.resblocks.4.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.4.attn.out_proj.bias [1280]
|
|
transformer.resblocks.4.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.4.ln_1.bias [1280]
|
|
transformer.resblocks.4.ln_1.weight [1280]
|
|
transformer.resblocks.4.ln_2.bias [1280]
|
|
transformer.resblocks.4.ln_2.weight [1280]
|
|
transformer.resblocks.4.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.4.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.4.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.4.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.5.attn.in_proj_bias [3840]
|
|
transformer.resblocks.5.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.5.attn.out_proj.bias [1280]
|
|
transformer.resblocks.5.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.5.ln_1.bias [1280]
|
|
transformer.resblocks.5.ln_1.weight [1280]
|
|
transformer.resblocks.5.ln_2.bias [1280]
|
|
transformer.resblocks.5.ln_2.weight [1280]
|
|
transformer.resblocks.5.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.5.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.5.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.5.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.6.attn.in_proj_bias [3840]
|
|
transformer.resblocks.6.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.6.attn.out_proj.bias [1280]
|
|
transformer.resblocks.6.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.6.ln_1.bias [1280]
|
|
transformer.resblocks.6.ln_1.weight [1280]
|
|
transformer.resblocks.6.ln_2.bias [1280]
|
|
transformer.resblocks.6.ln_2.weight [1280]
|
|
transformer.resblocks.6.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.6.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.6.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.6.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.7.attn.in_proj_bias [3840]
|
|
transformer.resblocks.7.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.7.attn.out_proj.bias [1280]
|
|
transformer.resblocks.7.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.7.ln_1.bias [1280]
|
|
transformer.resblocks.7.ln_1.weight [1280]
|
|
transformer.resblocks.7.ln_2.bias [1280]
|
|
transformer.resblocks.7.ln_2.weight [1280]
|
|
transformer.resblocks.7.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.7.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.7.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.7.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.8.attn.in_proj_bias [3840]
|
|
transformer.resblocks.8.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.8.attn.out_proj.bias [1280]
|
|
transformer.resblocks.8.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.8.ln_1.bias [1280]
|
|
transformer.resblocks.8.ln_1.weight [1280]
|
|
transformer.resblocks.8.ln_2.bias [1280]
|
|
transformer.resblocks.8.ln_2.weight [1280]
|
|
transformer.resblocks.8.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.8.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.8.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.8.mlp.c_proj.weight [1280,5120]
|
|
transformer.resblocks.9.attn.in_proj_bias [3840]
|
|
transformer.resblocks.9.attn.in_proj_weight [3840,1280]
|
|
transformer.resblocks.9.attn.out_proj.bias [1280]
|
|
transformer.resblocks.9.attn.out_proj.weight [1280,1280]
|
|
transformer.resblocks.9.ln_1.bias [1280]
|
|
transformer.resblocks.9.ln_1.weight [1280]
|
|
transformer.resblocks.9.ln_2.bias [1280]
|
|
transformer.resblocks.9.ln_2.weight [1280]
|
|
transformer.resblocks.9.mlp.c_fc.bias [5120]
|
|
transformer.resblocks.9.mlp.c_fc.weight [5120,1280]
|
|
transformer.resblocks.9.mlp.c_proj.bias [1280]
|
|
transformer.resblocks.9.mlp.c_proj.weight [1280,5120] |