1680 lines
100 KiB
Plaintext
1680 lines
100 KiB
Plaintext
input_blocks.0.0.bias [320]
|
|
input_blocks.0.0.weight [320,4,3,3]
|
|
input_blocks.1.0.emb_layers.1.bias [320]
|
|
input_blocks.1.0.emb_layers.1.weight [320,1280]
|
|
input_blocks.1.0.in_layers.0.bias [320]
|
|
input_blocks.1.0.in_layers.0.weight [320]
|
|
input_blocks.1.0.in_layers.2.bias [320]
|
|
input_blocks.1.0.in_layers.2.weight [320,320,3,3]
|
|
input_blocks.1.0.out_layers.0.bias [320]
|
|
input_blocks.1.0.out_layers.0.weight [320]
|
|
input_blocks.1.0.out_layers.3.bias [320]
|
|
input_blocks.1.0.out_layers.3.weight [320,320,3,3]
|
|
input_blocks.2.0.emb_layers.1.bias [320]
|
|
input_blocks.2.0.emb_layers.1.weight [320,1280]
|
|
input_blocks.2.0.in_layers.0.bias [320]
|
|
input_blocks.2.0.in_layers.0.weight [320]
|
|
input_blocks.2.0.in_layers.2.bias [320]
|
|
input_blocks.2.0.in_layers.2.weight [320,320,3,3]
|
|
input_blocks.2.0.out_layers.0.bias [320]
|
|
input_blocks.2.0.out_layers.0.weight [320]
|
|
input_blocks.2.0.out_layers.3.bias [320]
|
|
input_blocks.2.0.out_layers.3.weight [320,320,3,3]
|
|
input_blocks.3.0.op.bias [320]
|
|
input_blocks.3.0.op.weight [320,320,3,3]
|
|
input_blocks.4.0.emb_layers.1.bias [640]
|
|
input_blocks.4.0.emb_layers.1.weight [640,1280]
|
|
input_blocks.4.0.in_layers.0.bias [320]
|
|
input_blocks.4.0.in_layers.0.weight [320]
|
|
input_blocks.4.0.in_layers.2.bias [640]
|
|
input_blocks.4.0.in_layers.2.weight [640,320,3,3]
|
|
input_blocks.4.0.out_layers.0.bias [640]
|
|
input_blocks.4.0.out_layers.0.weight [640]
|
|
input_blocks.4.0.out_layers.3.bias [640]
|
|
input_blocks.4.0.out_layers.3.weight [640,640,3,3]
|
|
input_blocks.4.0.skip_connection.bias [640]
|
|
input_blocks.4.0.skip_connection.weight [640,320,1,1]
|
|
input_blocks.4.1.norm.bias [640]
|
|
input_blocks.4.1.norm.weight [640]
|
|
input_blocks.4.1.proj_in.bias [640]
|
|
input_blocks.4.1.proj_in.weight [640,640]
|
|
input_blocks.4.1.proj_out.bias [640]
|
|
input_blocks.4.1.proj_out.weight [640,640]
|
|
input_blocks.4.1.transformer_blocks.0.attn1.to_k.weight [640,640]
|
|
input_blocks.4.1.transformer_blocks.0.attn1.to_out.0.bias [640]
|
|
input_blocks.4.1.transformer_blocks.0.attn1.to_out.0.weight [640,640]
|
|
input_blocks.4.1.transformer_blocks.0.attn1.to_q.weight [640,640]
|
|
input_blocks.4.1.transformer_blocks.0.attn1.to_v.weight [640,640]
|
|
input_blocks.4.1.transformer_blocks.0.attn2.to_k.weight [640,2048]
|
|
input_blocks.4.1.transformer_blocks.0.attn2.to_out.0.bias [640]
|
|
input_blocks.4.1.transformer_blocks.0.attn2.to_out.0.weight [640,640]
|
|
input_blocks.4.1.transformer_blocks.0.attn2.to_q.weight [640,640]
|
|
input_blocks.4.1.transformer_blocks.0.attn2.to_v.weight [640,2048]
|
|
input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.bias [5120]
|
|
input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight [5120,640]
|
|
input_blocks.4.1.transformer_blocks.0.ff.net.2.bias [640]
|
|
input_blocks.4.1.transformer_blocks.0.ff.net.2.weight [640,2560]
|
|
input_blocks.4.1.transformer_blocks.0.norm1.bias [640]
|
|
input_blocks.4.1.transformer_blocks.0.norm1.weight [640]
|
|
input_blocks.4.1.transformer_blocks.0.norm2.bias [640]
|
|
input_blocks.4.1.transformer_blocks.0.norm2.weight [640]
|
|
input_blocks.4.1.transformer_blocks.0.norm3.bias [640]
|
|
input_blocks.4.1.transformer_blocks.0.norm3.weight [640]
|
|
input_blocks.4.1.transformer_blocks.1.attn1.to_k.weight [640,640]
|
|
input_blocks.4.1.transformer_blocks.1.attn1.to_out.0.bias [640]
|
|
input_blocks.4.1.transformer_blocks.1.attn1.to_out.0.weight [640,640]
|
|
input_blocks.4.1.transformer_blocks.1.attn1.to_q.weight [640,640]
|
|
input_blocks.4.1.transformer_blocks.1.attn1.to_v.weight [640,640]
|
|
input_blocks.4.1.transformer_blocks.1.attn2.to_k.weight [640,2048]
|
|
input_blocks.4.1.transformer_blocks.1.attn2.to_out.0.bias [640]
|
|
input_blocks.4.1.transformer_blocks.1.attn2.to_out.0.weight [640,640]
|
|
input_blocks.4.1.transformer_blocks.1.attn2.to_q.weight [640,640]
|
|
input_blocks.4.1.transformer_blocks.1.attn2.to_v.weight [640,2048]
|
|
input_blocks.4.1.transformer_blocks.1.ff.net.0.proj.bias [5120]
|
|
input_blocks.4.1.transformer_blocks.1.ff.net.0.proj.weight [5120,640]
|
|
input_blocks.4.1.transformer_blocks.1.ff.net.2.bias [640]
|
|
input_blocks.4.1.transformer_blocks.1.ff.net.2.weight [640,2560]
|
|
input_blocks.4.1.transformer_blocks.1.norm1.bias [640]
|
|
input_blocks.4.1.transformer_blocks.1.norm1.weight [640]
|
|
input_blocks.4.1.transformer_blocks.1.norm2.bias [640]
|
|
input_blocks.4.1.transformer_blocks.1.norm2.weight [640]
|
|
input_blocks.4.1.transformer_blocks.1.norm3.bias [640]
|
|
input_blocks.4.1.transformer_blocks.1.norm3.weight [640]
|
|
input_blocks.5.0.emb_layers.1.bias [640]
|
|
input_blocks.5.0.emb_layers.1.weight [640,1280]
|
|
input_blocks.5.0.in_layers.0.bias [640]
|
|
input_blocks.5.0.in_layers.0.weight [640]
|
|
input_blocks.5.0.in_layers.2.bias [640]
|
|
input_blocks.5.0.in_layers.2.weight [640,640,3,3]
|
|
input_blocks.5.0.out_layers.0.bias [640]
|
|
input_blocks.5.0.out_layers.0.weight [640]
|
|
input_blocks.5.0.out_layers.3.bias [640]
|
|
input_blocks.5.0.out_layers.3.weight [640,640,3,3]
|
|
input_blocks.5.1.norm.bias [640]
|
|
input_blocks.5.1.norm.weight [640]
|
|
input_blocks.5.1.proj_in.bias [640]
|
|
input_blocks.5.1.proj_in.weight [640,640]
|
|
input_blocks.5.1.proj_out.bias [640]
|
|
input_blocks.5.1.proj_out.weight [640,640]
|
|
input_blocks.5.1.transformer_blocks.0.attn1.to_k.weight [640,640]
|
|
input_blocks.5.1.transformer_blocks.0.attn1.to_out.0.bias [640]
|
|
input_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight [640,640]
|
|
input_blocks.5.1.transformer_blocks.0.attn1.to_q.weight [640,640]
|
|
input_blocks.5.1.transformer_blocks.0.attn1.to_v.weight [640,640]
|
|
input_blocks.5.1.transformer_blocks.0.attn2.to_k.weight [640,2048]
|
|
input_blocks.5.1.transformer_blocks.0.attn2.to_out.0.bias [640]
|
|
input_blocks.5.1.transformer_blocks.0.attn2.to_out.0.weight [640,640]
|
|
input_blocks.5.1.transformer_blocks.0.attn2.to_q.weight [640,640]
|
|
input_blocks.5.1.transformer_blocks.0.attn2.to_v.weight [640,2048]
|
|
input_blocks.5.1.transformer_blocks.0.ff.net.0.proj.bias [5120]
|
|
input_blocks.5.1.transformer_blocks.0.ff.net.0.proj.weight [5120,640]
|
|
input_blocks.5.1.transformer_blocks.0.ff.net.2.bias [640]
|
|
input_blocks.5.1.transformer_blocks.0.ff.net.2.weight [640,2560]
|
|
input_blocks.5.1.transformer_blocks.0.norm1.bias [640]
|
|
input_blocks.5.1.transformer_blocks.0.norm1.weight [640]
|
|
input_blocks.5.1.transformer_blocks.0.norm2.bias [640]
|
|
input_blocks.5.1.transformer_blocks.0.norm2.weight [640]
|
|
input_blocks.5.1.transformer_blocks.0.norm3.bias [640]
|
|
input_blocks.5.1.transformer_blocks.0.norm3.weight [640]
|
|
input_blocks.5.1.transformer_blocks.1.attn1.to_k.weight [640,640]
|
|
input_blocks.5.1.transformer_blocks.1.attn1.to_out.0.bias [640]
|
|
input_blocks.5.1.transformer_blocks.1.attn1.to_out.0.weight [640,640]
|
|
input_blocks.5.1.transformer_blocks.1.attn1.to_q.weight [640,640]
|
|
input_blocks.5.1.transformer_blocks.1.attn1.to_v.weight [640,640]
|
|
input_blocks.5.1.transformer_blocks.1.attn2.to_k.weight [640,2048]
|
|
input_blocks.5.1.transformer_blocks.1.attn2.to_out.0.bias [640]
|
|
input_blocks.5.1.transformer_blocks.1.attn2.to_out.0.weight [640,640]
|
|
input_blocks.5.1.transformer_blocks.1.attn2.to_q.weight [640,640]
|
|
input_blocks.5.1.transformer_blocks.1.attn2.to_v.weight [640,2048]
|
|
input_blocks.5.1.transformer_blocks.1.ff.net.0.proj.bias [5120]
|
|
input_blocks.5.1.transformer_blocks.1.ff.net.0.proj.weight [5120,640]
|
|
input_blocks.5.1.transformer_blocks.1.ff.net.2.bias [640]
|
|
input_blocks.5.1.transformer_blocks.1.ff.net.2.weight [640,2560]
|
|
input_blocks.5.1.transformer_blocks.1.norm1.bias [640]
|
|
input_blocks.5.1.transformer_blocks.1.norm1.weight [640]
|
|
input_blocks.5.1.transformer_blocks.1.norm2.bias [640]
|
|
input_blocks.5.1.transformer_blocks.1.norm2.weight [640]
|
|
input_blocks.5.1.transformer_blocks.1.norm3.bias [640]
|
|
input_blocks.5.1.transformer_blocks.1.norm3.weight [640]
|
|
input_blocks.6.0.op.bias [640]
|
|
input_blocks.6.0.op.weight [640,640,3,3]
|
|
input_blocks.7.0.emb_layers.1.bias [1280]
|
|
input_blocks.7.0.emb_layers.1.weight [1280,1280]
|
|
input_blocks.7.0.in_layers.0.bias [640]
|
|
input_blocks.7.0.in_layers.0.weight [640]
|
|
input_blocks.7.0.in_layers.2.bias [1280]
|
|
input_blocks.7.0.in_layers.2.weight [1280,640,3,3]
|
|
input_blocks.7.0.out_layers.0.bias [1280]
|
|
input_blocks.7.0.out_layers.0.weight [1280]
|
|
input_blocks.7.0.out_layers.3.bias [1280]
|
|
input_blocks.7.0.out_layers.3.weight [1280,1280,3,3]
|
|
input_blocks.7.0.skip_connection.bias [1280]
|
|
input_blocks.7.0.skip_connection.weight [1280,640,1,1]
|
|
input_blocks.7.1.norm.bias [1280]
|
|
input_blocks.7.1.norm.weight [1280]
|
|
input_blocks.7.1.proj_in.bias [1280]
|
|
input_blocks.7.1.proj_in.weight [1280,1280]
|
|
input_blocks.7.1.proj_out.bias [1280]
|
|
input_blocks.7.1.proj_out.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.0.attn1.to_k.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.0.attn1.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.0.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.0.attn1.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.0.attn1.to_v.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.0.attn2.to_k.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.0.attn2.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.0.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.0.attn2.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.0.attn2.to_v.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.0.ff.net.0.proj.bias [10240]
|
|
input_blocks.7.1.transformer_blocks.0.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.7.1.transformer_blocks.0.ff.net.2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.0.ff.net.2.weight [1280,5120]
|
|
input_blocks.7.1.transformer_blocks.0.norm1.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.0.norm1.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.0.norm2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.0.norm2.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.0.norm3.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.0.norm3.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.1.attn1.to_k.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.1.attn1.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.1.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.1.attn1.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.1.attn1.to_v.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.1.attn2.to_k.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.1.attn2.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.1.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.1.attn2.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.1.attn2.to_v.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.1.ff.net.0.proj.bias [10240]
|
|
input_blocks.7.1.transformer_blocks.1.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.7.1.transformer_blocks.1.ff.net.2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.1.ff.net.2.weight [1280,5120]
|
|
input_blocks.7.1.transformer_blocks.1.norm1.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.1.norm1.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.1.norm2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.1.norm2.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.1.norm3.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.1.norm3.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.2.attn1.to_k.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.2.attn1.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.2.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.2.attn1.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.2.attn1.to_v.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.2.attn2.to_k.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.2.attn2.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.2.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.2.attn2.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.2.attn2.to_v.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.2.ff.net.0.proj.bias [10240]
|
|
input_blocks.7.1.transformer_blocks.2.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.7.1.transformer_blocks.2.ff.net.2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.2.ff.net.2.weight [1280,5120]
|
|
input_blocks.7.1.transformer_blocks.2.norm1.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.2.norm1.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.2.norm2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.2.norm2.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.2.norm3.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.2.norm3.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.3.attn1.to_k.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.3.attn1.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.3.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.3.attn1.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.3.attn1.to_v.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.3.attn2.to_k.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.3.attn2.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.3.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.3.attn2.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.3.attn2.to_v.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.3.ff.net.0.proj.bias [10240]
|
|
input_blocks.7.1.transformer_blocks.3.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.7.1.transformer_blocks.3.ff.net.2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.3.ff.net.2.weight [1280,5120]
|
|
input_blocks.7.1.transformer_blocks.3.norm1.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.3.norm1.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.3.norm2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.3.norm2.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.3.norm3.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.3.norm3.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.4.attn1.to_k.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.4.attn1.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.4.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.4.attn1.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.4.attn1.to_v.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.4.attn2.to_k.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.4.attn2.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.4.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.4.attn2.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.4.attn2.to_v.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.4.ff.net.0.proj.bias [10240]
|
|
input_blocks.7.1.transformer_blocks.4.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.7.1.transformer_blocks.4.ff.net.2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.4.ff.net.2.weight [1280,5120]
|
|
input_blocks.7.1.transformer_blocks.4.norm1.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.4.norm1.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.4.norm2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.4.norm2.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.4.norm3.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.4.norm3.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.5.attn1.to_k.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.5.attn1.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.5.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.5.attn1.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.5.attn1.to_v.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.5.attn2.to_k.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.5.attn2.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.5.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.5.attn2.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.5.attn2.to_v.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.5.ff.net.0.proj.bias [10240]
|
|
input_blocks.7.1.transformer_blocks.5.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.7.1.transformer_blocks.5.ff.net.2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.5.ff.net.2.weight [1280,5120]
|
|
input_blocks.7.1.transformer_blocks.5.norm1.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.5.norm1.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.5.norm2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.5.norm2.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.5.norm3.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.5.norm3.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.6.attn1.to_k.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.6.attn1.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.6.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.6.attn1.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.6.attn1.to_v.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.6.attn2.to_k.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.6.attn2.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.6.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.6.attn2.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.6.attn2.to_v.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.6.ff.net.0.proj.bias [10240]
|
|
input_blocks.7.1.transformer_blocks.6.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.7.1.transformer_blocks.6.ff.net.2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.6.ff.net.2.weight [1280,5120]
|
|
input_blocks.7.1.transformer_blocks.6.norm1.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.6.norm1.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.6.norm2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.6.norm2.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.6.norm3.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.6.norm3.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.7.attn1.to_k.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.7.attn1.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.7.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.7.attn1.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.7.attn1.to_v.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.7.attn2.to_k.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.7.attn2.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.7.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.7.attn2.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.7.attn2.to_v.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.7.ff.net.0.proj.bias [10240]
|
|
input_blocks.7.1.transformer_blocks.7.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.7.1.transformer_blocks.7.ff.net.2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.7.ff.net.2.weight [1280,5120]
|
|
input_blocks.7.1.transformer_blocks.7.norm1.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.7.norm1.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.7.norm2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.7.norm2.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.7.norm3.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.7.norm3.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.8.attn1.to_k.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.8.attn1.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.8.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.8.attn1.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.8.attn1.to_v.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.8.attn2.to_k.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.8.attn2.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.8.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.8.attn2.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.8.attn2.to_v.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.8.ff.net.0.proj.bias [10240]
|
|
input_blocks.7.1.transformer_blocks.8.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.7.1.transformer_blocks.8.ff.net.2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.8.ff.net.2.weight [1280,5120]
|
|
input_blocks.7.1.transformer_blocks.8.norm1.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.8.norm1.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.8.norm2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.8.norm2.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.8.norm3.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.8.norm3.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.9.attn1.to_k.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.9.attn1.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.9.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.9.attn1.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.9.attn1.to_v.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.9.attn2.to_k.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.9.attn2.to_out.0.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.9.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.9.attn2.to_q.weight [1280,1280]
|
|
input_blocks.7.1.transformer_blocks.9.attn2.to_v.weight [1280,2048]
|
|
input_blocks.7.1.transformer_blocks.9.ff.net.0.proj.bias [10240]
|
|
input_blocks.7.1.transformer_blocks.9.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.7.1.transformer_blocks.9.ff.net.2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.9.ff.net.2.weight [1280,5120]
|
|
input_blocks.7.1.transformer_blocks.9.norm1.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.9.norm1.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.9.norm2.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.9.norm2.weight [1280]
|
|
input_blocks.7.1.transformer_blocks.9.norm3.bias [1280]
|
|
input_blocks.7.1.transformer_blocks.9.norm3.weight [1280]
|
|
input_blocks.8.0.emb_layers.1.bias [1280]
|
|
input_blocks.8.0.emb_layers.1.weight [1280,1280]
|
|
input_blocks.8.0.in_layers.0.bias [1280]
|
|
input_blocks.8.0.in_layers.0.weight [1280]
|
|
input_blocks.8.0.in_layers.2.bias [1280]
|
|
input_blocks.8.0.in_layers.2.weight [1280,1280,3,3]
|
|
input_blocks.8.0.out_layers.0.bias [1280]
|
|
input_blocks.8.0.out_layers.0.weight [1280]
|
|
input_blocks.8.0.out_layers.3.bias [1280]
|
|
input_blocks.8.0.out_layers.3.weight [1280,1280,3,3]
|
|
input_blocks.8.1.norm.bias [1280]
|
|
input_blocks.8.1.norm.weight [1280]
|
|
input_blocks.8.1.proj_in.bias [1280]
|
|
input_blocks.8.1.proj_in.weight [1280,1280]
|
|
input_blocks.8.1.proj_out.bias [1280]
|
|
input_blocks.8.1.proj_out.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.0.attn1.to_k.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.0.attn1.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.0.attn1.to_v.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.0.attn2.to_k.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.0.attn2.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.0.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.0.attn2.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.0.attn2.to_v.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.0.ff.net.0.proj.bias [10240]
|
|
input_blocks.8.1.transformer_blocks.0.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.8.1.transformer_blocks.0.ff.net.2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.0.ff.net.2.weight [1280,5120]
|
|
input_blocks.8.1.transformer_blocks.0.norm1.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.0.norm1.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.0.norm2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.0.norm2.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.0.norm3.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.0.norm3.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.1.attn1.to_k.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.1.attn1.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.1.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.1.attn1.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.1.attn1.to_v.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.1.attn2.to_k.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.1.attn2.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.1.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.1.attn2.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.1.attn2.to_v.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.1.ff.net.0.proj.bias [10240]
|
|
input_blocks.8.1.transformer_blocks.1.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.8.1.transformer_blocks.1.ff.net.2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.1.ff.net.2.weight [1280,5120]
|
|
input_blocks.8.1.transformer_blocks.1.norm1.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.1.norm1.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.1.norm2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.1.norm2.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.1.norm3.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.1.norm3.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.2.attn1.to_k.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.2.attn1.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.2.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.2.attn1.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.2.attn1.to_v.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.2.attn2.to_k.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.2.attn2.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.2.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.2.attn2.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.2.attn2.to_v.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.2.ff.net.0.proj.bias [10240]
|
|
input_blocks.8.1.transformer_blocks.2.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.8.1.transformer_blocks.2.ff.net.2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.2.ff.net.2.weight [1280,5120]
|
|
input_blocks.8.1.transformer_blocks.2.norm1.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.2.norm1.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.2.norm2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.2.norm2.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.2.norm3.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.2.norm3.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.3.attn1.to_k.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.3.attn1.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.3.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.3.attn1.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.3.attn1.to_v.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.3.attn2.to_k.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.3.attn2.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.3.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.3.attn2.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.3.attn2.to_v.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.3.ff.net.0.proj.bias [10240]
|
|
input_blocks.8.1.transformer_blocks.3.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.8.1.transformer_blocks.3.ff.net.2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.3.ff.net.2.weight [1280,5120]
|
|
input_blocks.8.1.transformer_blocks.3.norm1.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.3.norm1.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.3.norm2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.3.norm2.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.3.norm3.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.3.norm3.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.4.attn1.to_k.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.4.attn1.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.4.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.4.attn1.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.4.attn1.to_v.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.4.attn2.to_k.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.4.attn2.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.4.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.4.attn2.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.4.attn2.to_v.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.4.ff.net.0.proj.bias [10240]
|
|
input_blocks.8.1.transformer_blocks.4.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.8.1.transformer_blocks.4.ff.net.2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.4.ff.net.2.weight [1280,5120]
|
|
input_blocks.8.1.transformer_blocks.4.norm1.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.4.norm1.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.4.norm2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.4.norm2.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.4.norm3.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.4.norm3.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.5.attn1.to_k.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.5.attn1.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.5.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.5.attn1.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.5.attn1.to_v.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.5.attn2.to_k.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.5.attn2.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.5.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.5.attn2.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.5.attn2.to_v.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.5.ff.net.0.proj.bias [10240]
|
|
input_blocks.8.1.transformer_blocks.5.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.8.1.transformer_blocks.5.ff.net.2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.5.ff.net.2.weight [1280,5120]
|
|
input_blocks.8.1.transformer_blocks.5.norm1.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.5.norm1.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.5.norm2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.5.norm2.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.5.norm3.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.5.norm3.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.6.attn1.to_k.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.6.attn1.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.6.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.6.attn1.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.6.attn1.to_v.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.6.attn2.to_k.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.6.attn2.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.6.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.6.attn2.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.6.attn2.to_v.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.6.ff.net.0.proj.bias [10240]
|
|
input_blocks.8.1.transformer_blocks.6.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.8.1.transformer_blocks.6.ff.net.2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.6.ff.net.2.weight [1280,5120]
|
|
input_blocks.8.1.transformer_blocks.6.norm1.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.6.norm1.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.6.norm2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.6.norm2.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.6.norm3.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.6.norm3.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.7.attn1.to_k.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.7.attn1.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.7.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.7.attn1.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.7.attn1.to_v.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.7.attn2.to_k.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.7.attn2.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.7.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.7.attn2.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.7.attn2.to_v.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.7.ff.net.0.proj.bias [10240]
|
|
input_blocks.8.1.transformer_blocks.7.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.8.1.transformer_blocks.7.ff.net.2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.7.ff.net.2.weight [1280,5120]
|
|
input_blocks.8.1.transformer_blocks.7.norm1.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.7.norm1.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.7.norm2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.7.norm2.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.7.norm3.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.7.norm3.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.8.attn1.to_k.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.8.attn1.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.8.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.8.attn1.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.8.attn1.to_v.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.8.attn2.to_k.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.8.attn2.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.8.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.8.attn2.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.8.attn2.to_v.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.8.ff.net.0.proj.bias [10240]
|
|
input_blocks.8.1.transformer_blocks.8.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.8.1.transformer_blocks.8.ff.net.2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.8.ff.net.2.weight [1280,5120]
|
|
input_blocks.8.1.transformer_blocks.8.norm1.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.8.norm1.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.8.norm2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.8.norm2.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.8.norm3.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.8.norm3.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.9.attn1.to_k.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.9.attn1.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.9.attn1.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.9.attn1.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.9.attn1.to_v.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.9.attn2.to_k.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.9.attn2.to_out.0.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.9.attn2.to_out.0.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.9.attn2.to_q.weight [1280,1280]
|
|
input_blocks.8.1.transformer_blocks.9.attn2.to_v.weight [1280,2048]
|
|
input_blocks.8.1.transformer_blocks.9.ff.net.0.proj.bias [10240]
|
|
input_blocks.8.1.transformer_blocks.9.ff.net.0.proj.weight [10240,1280]
|
|
input_blocks.8.1.transformer_blocks.9.ff.net.2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.9.ff.net.2.weight [1280,5120]
|
|
input_blocks.8.1.transformer_blocks.9.norm1.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.9.norm1.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.9.norm2.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.9.norm2.weight [1280]
|
|
input_blocks.8.1.transformer_blocks.9.norm3.bias [1280]
|
|
input_blocks.8.1.transformer_blocks.9.norm3.weight [1280]
|
|
label_emb.0.0.bias [1280]
|
|
label_emb.0.0.weight [1280,2816]
|
|
label_emb.0.2.bias [1280]
|
|
label_emb.0.2.weight [1280,1280]
|
|
middle_block.0.emb_layers.1.bias [1280]
|
|
middle_block.0.emb_layers.1.weight [1280,1280]
|
|
middle_block.0.in_layers.0.bias [1280]
|
|
middle_block.0.in_layers.0.weight [1280]
|
|
middle_block.0.in_layers.2.bias [1280]
|
|
middle_block.0.in_layers.2.weight [1280,1280,3,3]
|
|
middle_block.0.out_layers.0.bias [1280]
|
|
middle_block.0.out_layers.0.weight [1280]
|
|
middle_block.0.out_layers.3.bias [1280]
|
|
middle_block.0.out_layers.3.weight [1280,1280,3,3]
|
|
middle_block.1.norm.bias [1280]
|
|
middle_block.1.norm.weight [1280]
|
|
middle_block.1.proj_in.bias [1280]
|
|
middle_block.1.proj_in.weight [1280,1280]
|
|
middle_block.1.proj_out.bias [1280]
|
|
middle_block.1.proj_out.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.0.attn1.to_k.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.0.attn1.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.0.attn1.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.0.attn1.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.0.attn1.to_v.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.0.attn2.to_k.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.0.attn2.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.0.attn2.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.0.attn2.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.0.attn2.to_v.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.0.ff.net.0.proj.bias [10240]
|
|
middle_block.1.transformer_blocks.0.ff.net.0.proj.weight [10240,1280]
|
|
middle_block.1.transformer_blocks.0.ff.net.2.bias [1280]
|
|
middle_block.1.transformer_blocks.0.ff.net.2.weight [1280,5120]
|
|
middle_block.1.transformer_blocks.0.norm1.bias [1280]
|
|
middle_block.1.transformer_blocks.0.norm1.weight [1280]
|
|
middle_block.1.transformer_blocks.0.norm2.bias [1280]
|
|
middle_block.1.transformer_blocks.0.norm2.weight [1280]
|
|
middle_block.1.transformer_blocks.0.norm3.bias [1280]
|
|
middle_block.1.transformer_blocks.0.norm3.weight [1280]
|
|
middle_block.1.transformer_blocks.1.attn1.to_k.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.1.attn1.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.1.attn1.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.1.attn1.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.1.attn1.to_v.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.1.attn2.to_k.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.1.attn2.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.1.attn2.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.1.attn2.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.1.attn2.to_v.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.1.ff.net.0.proj.bias [10240]
|
|
middle_block.1.transformer_blocks.1.ff.net.0.proj.weight [10240,1280]
|
|
middle_block.1.transformer_blocks.1.ff.net.2.bias [1280]
|
|
middle_block.1.transformer_blocks.1.ff.net.2.weight [1280,5120]
|
|
middle_block.1.transformer_blocks.1.norm1.bias [1280]
|
|
middle_block.1.transformer_blocks.1.norm1.weight [1280]
|
|
middle_block.1.transformer_blocks.1.norm2.bias [1280]
|
|
middle_block.1.transformer_blocks.1.norm2.weight [1280]
|
|
middle_block.1.transformer_blocks.1.norm3.bias [1280]
|
|
middle_block.1.transformer_blocks.1.norm3.weight [1280]
|
|
middle_block.1.transformer_blocks.2.attn1.to_k.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.2.attn1.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.2.attn1.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.2.attn1.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.2.attn1.to_v.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.2.attn2.to_k.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.2.attn2.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.2.attn2.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.2.attn2.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.2.attn2.to_v.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.2.ff.net.0.proj.bias [10240]
|
|
middle_block.1.transformer_blocks.2.ff.net.0.proj.weight [10240,1280]
|
|
middle_block.1.transformer_blocks.2.ff.net.2.bias [1280]
|
|
middle_block.1.transformer_blocks.2.ff.net.2.weight [1280,5120]
|
|
middle_block.1.transformer_blocks.2.norm1.bias [1280]
|
|
middle_block.1.transformer_blocks.2.norm1.weight [1280]
|
|
middle_block.1.transformer_blocks.2.norm2.bias [1280]
|
|
middle_block.1.transformer_blocks.2.norm2.weight [1280]
|
|
middle_block.1.transformer_blocks.2.norm3.bias [1280]
|
|
middle_block.1.transformer_blocks.2.norm3.weight [1280]
|
|
middle_block.1.transformer_blocks.3.attn1.to_k.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.3.attn1.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.3.attn1.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.3.attn1.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.3.attn1.to_v.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.3.attn2.to_k.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.3.attn2.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.3.attn2.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.3.attn2.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.3.attn2.to_v.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.3.ff.net.0.proj.bias [10240]
|
|
middle_block.1.transformer_blocks.3.ff.net.0.proj.weight [10240,1280]
|
|
middle_block.1.transformer_blocks.3.ff.net.2.bias [1280]
|
|
middle_block.1.transformer_blocks.3.ff.net.2.weight [1280,5120]
|
|
middle_block.1.transformer_blocks.3.norm1.bias [1280]
|
|
middle_block.1.transformer_blocks.3.norm1.weight [1280]
|
|
middle_block.1.transformer_blocks.3.norm2.bias [1280]
|
|
middle_block.1.transformer_blocks.3.norm2.weight [1280]
|
|
middle_block.1.transformer_blocks.3.norm3.bias [1280]
|
|
middle_block.1.transformer_blocks.3.norm3.weight [1280]
|
|
middle_block.1.transformer_blocks.4.attn1.to_k.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.4.attn1.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.4.attn1.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.4.attn1.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.4.attn1.to_v.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.4.attn2.to_k.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.4.attn2.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.4.attn2.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.4.attn2.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.4.attn2.to_v.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.4.ff.net.0.proj.bias [10240]
|
|
middle_block.1.transformer_blocks.4.ff.net.0.proj.weight [10240,1280]
|
|
middle_block.1.transformer_blocks.4.ff.net.2.bias [1280]
|
|
middle_block.1.transformer_blocks.4.ff.net.2.weight [1280,5120]
|
|
middle_block.1.transformer_blocks.4.norm1.bias [1280]
|
|
middle_block.1.transformer_blocks.4.norm1.weight [1280]
|
|
middle_block.1.transformer_blocks.4.norm2.bias [1280]
|
|
middle_block.1.transformer_blocks.4.norm2.weight [1280]
|
|
middle_block.1.transformer_blocks.4.norm3.bias [1280]
|
|
middle_block.1.transformer_blocks.4.norm3.weight [1280]
|
|
middle_block.1.transformer_blocks.5.attn1.to_k.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.5.attn1.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.5.attn1.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.5.attn1.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.5.attn1.to_v.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.5.attn2.to_k.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.5.attn2.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.5.attn2.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.5.attn2.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.5.attn2.to_v.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.5.ff.net.0.proj.bias [10240]
|
|
middle_block.1.transformer_blocks.5.ff.net.0.proj.weight [10240,1280]
|
|
middle_block.1.transformer_blocks.5.ff.net.2.bias [1280]
|
|
middle_block.1.transformer_blocks.5.ff.net.2.weight [1280,5120]
|
|
middle_block.1.transformer_blocks.5.norm1.bias [1280]
|
|
middle_block.1.transformer_blocks.5.norm1.weight [1280]
|
|
middle_block.1.transformer_blocks.5.norm2.bias [1280]
|
|
middle_block.1.transformer_blocks.5.norm2.weight [1280]
|
|
middle_block.1.transformer_blocks.5.norm3.bias [1280]
|
|
middle_block.1.transformer_blocks.5.norm3.weight [1280]
|
|
middle_block.1.transformer_blocks.6.attn1.to_k.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.6.attn1.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.6.attn1.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.6.attn1.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.6.attn1.to_v.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.6.attn2.to_k.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.6.attn2.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.6.attn2.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.6.attn2.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.6.attn2.to_v.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.6.ff.net.0.proj.bias [10240]
|
|
middle_block.1.transformer_blocks.6.ff.net.0.proj.weight [10240,1280]
|
|
middle_block.1.transformer_blocks.6.ff.net.2.bias [1280]
|
|
middle_block.1.transformer_blocks.6.ff.net.2.weight [1280,5120]
|
|
middle_block.1.transformer_blocks.6.norm1.bias [1280]
|
|
middle_block.1.transformer_blocks.6.norm1.weight [1280]
|
|
middle_block.1.transformer_blocks.6.norm2.bias [1280]
|
|
middle_block.1.transformer_blocks.6.norm2.weight [1280]
|
|
middle_block.1.transformer_blocks.6.norm3.bias [1280]
|
|
middle_block.1.transformer_blocks.6.norm3.weight [1280]
|
|
middle_block.1.transformer_blocks.7.attn1.to_k.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.7.attn1.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.7.attn1.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.7.attn1.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.7.attn1.to_v.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.7.attn2.to_k.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.7.attn2.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.7.attn2.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.7.attn2.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.7.attn2.to_v.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.7.ff.net.0.proj.bias [10240]
|
|
middle_block.1.transformer_blocks.7.ff.net.0.proj.weight [10240,1280]
|
|
middle_block.1.transformer_blocks.7.ff.net.2.bias [1280]
|
|
middle_block.1.transformer_blocks.7.ff.net.2.weight [1280,5120]
|
|
middle_block.1.transformer_blocks.7.norm1.bias [1280]
|
|
middle_block.1.transformer_blocks.7.norm1.weight [1280]
|
|
middle_block.1.transformer_blocks.7.norm2.bias [1280]
|
|
middle_block.1.transformer_blocks.7.norm2.weight [1280]
|
|
middle_block.1.transformer_blocks.7.norm3.bias [1280]
|
|
middle_block.1.transformer_blocks.7.norm3.weight [1280]
|
|
middle_block.1.transformer_blocks.8.attn1.to_k.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.8.attn1.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.8.attn1.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.8.attn1.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.8.attn1.to_v.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.8.attn2.to_k.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.8.attn2.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.8.attn2.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.8.attn2.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.8.attn2.to_v.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.8.ff.net.0.proj.bias [10240]
|
|
middle_block.1.transformer_blocks.8.ff.net.0.proj.weight [10240,1280]
|
|
middle_block.1.transformer_blocks.8.ff.net.2.bias [1280]
|
|
middle_block.1.transformer_blocks.8.ff.net.2.weight [1280,5120]
|
|
middle_block.1.transformer_blocks.8.norm1.bias [1280]
|
|
middle_block.1.transformer_blocks.8.norm1.weight [1280]
|
|
middle_block.1.transformer_blocks.8.norm2.bias [1280]
|
|
middle_block.1.transformer_blocks.8.norm2.weight [1280]
|
|
middle_block.1.transformer_blocks.8.norm3.bias [1280]
|
|
middle_block.1.transformer_blocks.8.norm3.weight [1280]
|
|
middle_block.1.transformer_blocks.9.attn1.to_k.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.9.attn1.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.9.attn1.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.9.attn1.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.9.attn1.to_v.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.9.attn2.to_k.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.9.attn2.to_out.0.bias [1280]
|
|
middle_block.1.transformer_blocks.9.attn2.to_out.0.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.9.attn2.to_q.weight [1280,1280]
|
|
middle_block.1.transformer_blocks.9.attn2.to_v.weight [1280,2048]
|
|
middle_block.1.transformer_blocks.9.ff.net.0.proj.bias [10240]
|
|
middle_block.1.transformer_blocks.9.ff.net.0.proj.weight [10240,1280]
|
|
middle_block.1.transformer_blocks.9.ff.net.2.bias [1280]
|
|
middle_block.1.transformer_blocks.9.ff.net.2.weight [1280,5120]
|
|
middle_block.1.transformer_blocks.9.norm1.bias [1280]
|
|
middle_block.1.transformer_blocks.9.norm1.weight [1280]
|
|
middle_block.1.transformer_blocks.9.norm2.bias [1280]
|
|
middle_block.1.transformer_blocks.9.norm2.weight [1280]
|
|
middle_block.1.transformer_blocks.9.norm3.bias [1280]
|
|
middle_block.1.transformer_blocks.9.norm3.weight [1280]
|
|
middle_block.2.emb_layers.1.bias [1280]
|
|
middle_block.2.emb_layers.1.weight [1280,1280]
|
|
middle_block.2.in_layers.0.bias [1280]
|
|
middle_block.2.in_layers.0.weight [1280]
|
|
middle_block.2.in_layers.2.bias [1280]
|
|
middle_block.2.in_layers.2.weight [1280,1280,3,3]
|
|
middle_block.2.out_layers.0.bias [1280]
|
|
middle_block.2.out_layers.0.weight [1280]
|
|
middle_block.2.out_layers.3.bias [1280]
|
|
middle_block.2.out_layers.3.weight [1280,1280,3,3]
|
|
out.0.bias [320]
|
|
out.0.weight [320]
|
|
out.2.bias [4]
|
|
out.2.weight [4,320,3,3]
|
|
output_blocks.0.0.emb_layers.1.bias [1280]
|
|
output_blocks.0.0.emb_layers.1.weight [1280,1280]
|
|
output_blocks.0.0.in_layers.0.bias [2560]
|
|
output_blocks.0.0.in_layers.0.weight [2560]
|
|
output_blocks.0.0.in_layers.2.bias [1280]
|
|
output_blocks.0.0.in_layers.2.weight [1280,2560,3,3]
|
|
output_blocks.0.0.out_layers.0.bias [1280]
|
|
output_blocks.0.0.out_layers.0.weight [1280]
|
|
output_blocks.0.0.out_layers.3.bias [1280]
|
|
output_blocks.0.0.out_layers.3.weight [1280,1280,3,3]
|
|
output_blocks.0.0.skip_connection.bias [1280]
|
|
output_blocks.0.0.skip_connection.weight [1280,2560,1,1]
|
|
output_blocks.0.1.norm.bias [1280]
|
|
output_blocks.0.1.norm.weight [1280]
|
|
output_blocks.0.1.proj_in.bias [1280]
|
|
output_blocks.0.1.proj_in.weight [1280,1280]
|
|
output_blocks.0.1.proj_out.bias [1280]
|
|
output_blocks.0.1.proj_out.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.0.attn1.to_k.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.0.attn1.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.0.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.0.attn1.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.0.attn1.to_v.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.0.attn2.to_k.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.0.attn2.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.0.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.0.attn2.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.0.attn2.to_v.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.0.ff.net.0.proj.bias [10240]
|
|
output_blocks.0.1.transformer_blocks.0.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.0.1.transformer_blocks.0.ff.net.2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.0.ff.net.2.weight [1280,5120]
|
|
output_blocks.0.1.transformer_blocks.0.norm1.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.0.norm1.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.0.norm2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.0.norm2.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.0.norm3.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.0.norm3.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.1.attn1.to_k.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.1.attn1.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.1.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.1.attn1.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.1.attn1.to_v.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.1.attn2.to_k.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.1.attn2.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.1.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.1.attn2.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.1.attn2.to_v.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.1.ff.net.0.proj.bias [10240]
|
|
output_blocks.0.1.transformer_blocks.1.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.0.1.transformer_blocks.1.ff.net.2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.1.ff.net.2.weight [1280,5120]
|
|
output_blocks.0.1.transformer_blocks.1.norm1.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.1.norm1.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.1.norm2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.1.norm2.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.1.norm3.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.1.norm3.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.2.attn1.to_k.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.2.attn1.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.2.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.2.attn1.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.2.attn1.to_v.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.2.attn2.to_k.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.2.attn2.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.2.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.2.attn2.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.2.attn2.to_v.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.2.ff.net.0.proj.bias [10240]
|
|
output_blocks.0.1.transformer_blocks.2.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.0.1.transformer_blocks.2.ff.net.2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.2.ff.net.2.weight [1280,5120]
|
|
output_blocks.0.1.transformer_blocks.2.norm1.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.2.norm1.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.2.norm2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.2.norm2.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.2.norm3.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.2.norm3.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.3.attn1.to_k.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.3.attn1.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.3.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.3.attn1.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.3.attn1.to_v.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.3.attn2.to_k.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.3.attn2.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.3.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.3.attn2.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.3.attn2.to_v.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.3.ff.net.0.proj.bias [10240]
|
|
output_blocks.0.1.transformer_blocks.3.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.0.1.transformer_blocks.3.ff.net.2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.3.ff.net.2.weight [1280,5120]
|
|
output_blocks.0.1.transformer_blocks.3.norm1.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.3.norm1.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.3.norm2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.3.norm2.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.3.norm3.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.3.norm3.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.4.attn1.to_k.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.4.attn1.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.4.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.4.attn1.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.4.attn1.to_v.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.4.attn2.to_k.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.4.attn2.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.4.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.4.attn2.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.4.attn2.to_v.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.4.ff.net.0.proj.bias [10240]
|
|
output_blocks.0.1.transformer_blocks.4.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.0.1.transformer_blocks.4.ff.net.2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.4.ff.net.2.weight [1280,5120]
|
|
output_blocks.0.1.transformer_blocks.4.norm1.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.4.norm1.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.4.norm2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.4.norm2.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.4.norm3.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.4.norm3.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.5.attn1.to_k.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.5.attn1.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.5.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.5.attn1.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.5.attn1.to_v.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.5.attn2.to_k.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.5.attn2.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.5.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.5.attn2.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.5.attn2.to_v.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.5.ff.net.0.proj.bias [10240]
|
|
output_blocks.0.1.transformer_blocks.5.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.0.1.transformer_blocks.5.ff.net.2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.5.ff.net.2.weight [1280,5120]
|
|
output_blocks.0.1.transformer_blocks.5.norm1.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.5.norm1.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.5.norm2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.5.norm2.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.5.norm3.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.5.norm3.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.6.attn1.to_k.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.6.attn1.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.6.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.6.attn1.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.6.attn1.to_v.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.6.attn2.to_k.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.6.attn2.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.6.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.6.attn2.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.6.attn2.to_v.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.6.ff.net.0.proj.bias [10240]
|
|
output_blocks.0.1.transformer_blocks.6.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.0.1.transformer_blocks.6.ff.net.2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.6.ff.net.2.weight [1280,5120]
|
|
output_blocks.0.1.transformer_blocks.6.norm1.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.6.norm1.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.6.norm2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.6.norm2.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.6.norm3.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.6.norm3.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.7.attn1.to_k.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.7.attn1.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.7.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.7.attn1.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.7.attn1.to_v.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.7.attn2.to_k.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.7.attn2.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.7.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.7.attn2.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.7.attn2.to_v.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.7.ff.net.0.proj.bias [10240]
|
|
output_blocks.0.1.transformer_blocks.7.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.0.1.transformer_blocks.7.ff.net.2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.7.ff.net.2.weight [1280,5120]
|
|
output_blocks.0.1.transformer_blocks.7.norm1.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.7.norm1.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.7.norm2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.7.norm2.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.7.norm3.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.7.norm3.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.8.attn1.to_k.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.8.attn1.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.8.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.8.attn1.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.8.attn1.to_v.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.8.attn2.to_k.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.8.attn2.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.8.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.8.attn2.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.8.attn2.to_v.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.8.ff.net.0.proj.bias [10240]
|
|
output_blocks.0.1.transformer_blocks.8.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.0.1.transformer_blocks.8.ff.net.2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.8.ff.net.2.weight [1280,5120]
|
|
output_blocks.0.1.transformer_blocks.8.norm1.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.8.norm1.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.8.norm2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.8.norm2.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.8.norm3.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.8.norm3.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.9.attn1.to_k.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.9.attn1.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.9.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.9.attn1.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.9.attn1.to_v.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.9.attn2.to_k.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.9.attn2.to_out.0.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.9.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.9.attn2.to_q.weight [1280,1280]
|
|
output_blocks.0.1.transformer_blocks.9.attn2.to_v.weight [1280,2048]
|
|
output_blocks.0.1.transformer_blocks.9.ff.net.0.proj.bias [10240]
|
|
output_blocks.0.1.transformer_blocks.9.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.0.1.transformer_blocks.9.ff.net.2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.9.ff.net.2.weight [1280,5120]
|
|
output_blocks.0.1.transformer_blocks.9.norm1.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.9.norm1.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.9.norm2.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.9.norm2.weight [1280]
|
|
output_blocks.0.1.transformer_blocks.9.norm3.bias [1280]
|
|
output_blocks.0.1.transformer_blocks.9.norm3.weight [1280]
|
|
output_blocks.1.0.emb_layers.1.bias [1280]
|
|
output_blocks.1.0.emb_layers.1.weight [1280,1280]
|
|
output_blocks.1.0.in_layers.0.bias [2560]
|
|
output_blocks.1.0.in_layers.0.weight [2560]
|
|
output_blocks.1.0.in_layers.2.bias [1280]
|
|
output_blocks.1.0.in_layers.2.weight [1280,2560,3,3]
|
|
output_blocks.1.0.out_layers.0.bias [1280]
|
|
output_blocks.1.0.out_layers.0.weight [1280]
|
|
output_blocks.1.0.out_layers.3.bias [1280]
|
|
output_blocks.1.0.out_layers.3.weight [1280,1280,3,3]
|
|
output_blocks.1.0.skip_connection.bias [1280]
|
|
output_blocks.1.0.skip_connection.weight [1280,2560,1,1]
|
|
output_blocks.1.1.norm.bias [1280]
|
|
output_blocks.1.1.norm.weight [1280]
|
|
output_blocks.1.1.proj_in.bias [1280]
|
|
output_blocks.1.1.proj_in.weight [1280,1280]
|
|
output_blocks.1.1.proj_out.bias [1280]
|
|
output_blocks.1.1.proj_out.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.0.attn1.to_k.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.0.attn1.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.0.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.0.attn1.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.0.attn1.to_v.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.0.attn2.to_k.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.0.attn2.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.0.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.0.attn2.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.0.attn2.to_v.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.0.ff.net.0.proj.bias [10240]
|
|
output_blocks.1.1.transformer_blocks.0.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.1.1.transformer_blocks.0.ff.net.2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.0.ff.net.2.weight [1280,5120]
|
|
output_blocks.1.1.transformer_blocks.0.norm1.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.0.norm1.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.0.norm2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.0.norm2.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.0.norm3.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.0.norm3.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.1.attn1.to_k.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.1.attn1.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.1.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.1.attn1.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.1.attn1.to_v.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.1.attn2.to_k.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.1.attn2.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.1.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.1.attn2.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.1.attn2.to_v.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.1.ff.net.0.proj.bias [10240]
|
|
output_blocks.1.1.transformer_blocks.1.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.1.1.transformer_blocks.1.ff.net.2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.1.ff.net.2.weight [1280,5120]
|
|
output_blocks.1.1.transformer_blocks.1.norm1.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.1.norm1.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.1.norm2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.1.norm2.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.1.norm3.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.1.norm3.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.2.attn1.to_k.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.2.attn1.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.2.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.2.attn1.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.2.attn1.to_v.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.2.attn2.to_k.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.2.attn2.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.2.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.2.attn2.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.2.attn2.to_v.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.2.ff.net.0.proj.bias [10240]
|
|
output_blocks.1.1.transformer_blocks.2.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.1.1.transformer_blocks.2.ff.net.2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.2.ff.net.2.weight [1280,5120]
|
|
output_blocks.1.1.transformer_blocks.2.norm1.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.2.norm1.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.2.norm2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.2.norm2.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.2.norm3.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.2.norm3.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.3.attn1.to_k.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.3.attn1.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.3.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.3.attn1.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.3.attn1.to_v.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.3.attn2.to_k.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.3.attn2.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.3.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.3.attn2.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.3.attn2.to_v.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.3.ff.net.0.proj.bias [10240]
|
|
output_blocks.1.1.transformer_blocks.3.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.1.1.transformer_blocks.3.ff.net.2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.3.ff.net.2.weight [1280,5120]
|
|
output_blocks.1.1.transformer_blocks.3.norm1.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.3.norm1.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.3.norm2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.3.norm2.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.3.norm3.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.3.norm3.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.4.attn1.to_k.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.4.attn1.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.4.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.4.attn1.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.4.attn1.to_v.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.4.attn2.to_k.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.4.attn2.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.4.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.4.attn2.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.4.attn2.to_v.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.4.ff.net.0.proj.bias [10240]
|
|
output_blocks.1.1.transformer_blocks.4.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.1.1.transformer_blocks.4.ff.net.2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.4.ff.net.2.weight [1280,5120]
|
|
output_blocks.1.1.transformer_blocks.4.norm1.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.4.norm1.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.4.norm2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.4.norm2.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.4.norm3.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.4.norm3.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.5.attn1.to_k.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.5.attn1.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.5.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.5.attn1.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.5.attn1.to_v.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.5.attn2.to_k.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.5.attn2.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.5.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.5.attn2.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.5.attn2.to_v.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.5.ff.net.0.proj.bias [10240]
|
|
output_blocks.1.1.transformer_blocks.5.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.1.1.transformer_blocks.5.ff.net.2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.5.ff.net.2.weight [1280,5120]
|
|
output_blocks.1.1.transformer_blocks.5.norm1.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.5.norm1.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.5.norm2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.5.norm2.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.5.norm3.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.5.norm3.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.6.attn1.to_k.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.6.attn1.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.6.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.6.attn1.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.6.attn1.to_v.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.6.attn2.to_k.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.6.attn2.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.6.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.6.attn2.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.6.attn2.to_v.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.6.ff.net.0.proj.bias [10240]
|
|
output_blocks.1.1.transformer_blocks.6.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.1.1.transformer_blocks.6.ff.net.2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.6.ff.net.2.weight [1280,5120]
|
|
output_blocks.1.1.transformer_blocks.6.norm1.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.6.norm1.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.6.norm2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.6.norm2.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.6.norm3.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.6.norm3.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.7.attn1.to_k.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.7.attn1.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.7.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.7.attn1.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.7.attn1.to_v.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.7.attn2.to_k.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.7.attn2.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.7.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.7.attn2.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.7.attn2.to_v.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.7.ff.net.0.proj.bias [10240]
|
|
output_blocks.1.1.transformer_blocks.7.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.1.1.transformer_blocks.7.ff.net.2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.7.ff.net.2.weight [1280,5120]
|
|
output_blocks.1.1.transformer_blocks.7.norm1.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.7.norm1.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.7.norm2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.7.norm2.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.7.norm3.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.7.norm3.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.8.attn1.to_k.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.8.attn1.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.8.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.8.attn1.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.8.attn1.to_v.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.8.attn2.to_k.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.8.attn2.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.8.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.8.attn2.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.8.attn2.to_v.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.8.ff.net.0.proj.bias [10240]
|
|
output_blocks.1.1.transformer_blocks.8.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.1.1.transformer_blocks.8.ff.net.2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.8.ff.net.2.weight [1280,5120]
|
|
output_blocks.1.1.transformer_blocks.8.norm1.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.8.norm1.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.8.norm2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.8.norm2.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.8.norm3.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.8.norm3.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.9.attn1.to_k.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.9.attn1.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.9.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.9.attn1.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.9.attn1.to_v.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.9.attn2.to_k.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.9.attn2.to_out.0.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.9.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.9.attn2.to_q.weight [1280,1280]
|
|
output_blocks.1.1.transformer_blocks.9.attn2.to_v.weight [1280,2048]
|
|
output_blocks.1.1.transformer_blocks.9.ff.net.0.proj.bias [10240]
|
|
output_blocks.1.1.transformer_blocks.9.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.1.1.transformer_blocks.9.ff.net.2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.9.ff.net.2.weight [1280,5120]
|
|
output_blocks.1.1.transformer_blocks.9.norm1.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.9.norm1.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.9.norm2.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.9.norm2.weight [1280]
|
|
output_blocks.1.1.transformer_blocks.9.norm3.bias [1280]
|
|
output_blocks.1.1.transformer_blocks.9.norm3.weight [1280]
|
|
output_blocks.2.0.emb_layers.1.bias [1280]
|
|
output_blocks.2.0.emb_layers.1.weight [1280,1280]
|
|
output_blocks.2.0.in_layers.0.bias [1920]
|
|
output_blocks.2.0.in_layers.0.weight [1920]
|
|
output_blocks.2.0.in_layers.2.bias [1280]
|
|
output_blocks.2.0.in_layers.2.weight [1280,1920,3,3]
|
|
output_blocks.2.0.out_layers.0.bias [1280]
|
|
output_blocks.2.0.out_layers.0.weight [1280]
|
|
output_blocks.2.0.out_layers.3.bias [1280]
|
|
output_blocks.2.0.out_layers.3.weight [1280,1280,3,3]
|
|
output_blocks.2.0.skip_connection.bias [1280]
|
|
output_blocks.2.0.skip_connection.weight [1280,1920,1,1]
|
|
output_blocks.2.1.norm.bias [1280]
|
|
output_blocks.2.1.norm.weight [1280]
|
|
output_blocks.2.1.proj_in.bias [1280]
|
|
output_blocks.2.1.proj_in.weight [1280,1280]
|
|
output_blocks.2.1.proj_out.bias [1280]
|
|
output_blocks.2.1.proj_out.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.0.attn1.to_k.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.0.attn1.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.0.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.0.attn1.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.0.attn1.to_v.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.0.attn2.to_k.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.0.attn2.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.0.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.0.attn2.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.0.attn2.to_v.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.0.ff.net.0.proj.bias [10240]
|
|
output_blocks.2.1.transformer_blocks.0.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.2.1.transformer_blocks.0.ff.net.2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.0.ff.net.2.weight [1280,5120]
|
|
output_blocks.2.1.transformer_blocks.0.norm1.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.0.norm1.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.0.norm2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.0.norm2.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.0.norm3.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.0.norm3.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.1.attn1.to_k.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.1.attn1.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.1.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.1.attn1.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.1.attn1.to_v.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.1.attn2.to_k.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.1.attn2.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.1.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.1.attn2.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.1.attn2.to_v.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.1.ff.net.0.proj.bias [10240]
|
|
output_blocks.2.1.transformer_blocks.1.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.2.1.transformer_blocks.1.ff.net.2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.1.ff.net.2.weight [1280,5120]
|
|
output_blocks.2.1.transformer_blocks.1.norm1.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.1.norm1.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.1.norm2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.1.norm2.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.1.norm3.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.1.norm3.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.2.attn1.to_k.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.2.attn1.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.2.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.2.attn1.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.2.attn1.to_v.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.2.attn2.to_k.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.2.attn2.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.2.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.2.attn2.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.2.attn2.to_v.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.2.ff.net.0.proj.bias [10240]
|
|
output_blocks.2.1.transformer_blocks.2.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.2.1.transformer_blocks.2.ff.net.2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.2.ff.net.2.weight [1280,5120]
|
|
output_blocks.2.1.transformer_blocks.2.norm1.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.2.norm1.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.2.norm2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.2.norm2.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.2.norm3.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.2.norm3.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.3.attn1.to_k.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.3.attn1.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.3.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.3.attn1.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.3.attn1.to_v.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.3.attn2.to_k.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.3.attn2.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.3.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.3.attn2.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.3.attn2.to_v.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.3.ff.net.0.proj.bias [10240]
|
|
output_blocks.2.1.transformer_blocks.3.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.2.1.transformer_blocks.3.ff.net.2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.3.ff.net.2.weight [1280,5120]
|
|
output_blocks.2.1.transformer_blocks.3.norm1.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.3.norm1.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.3.norm2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.3.norm2.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.3.norm3.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.3.norm3.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.4.attn1.to_k.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.4.attn1.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.4.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.4.attn1.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.4.attn1.to_v.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.4.attn2.to_k.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.4.attn2.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.4.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.4.attn2.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.4.attn2.to_v.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.4.ff.net.0.proj.bias [10240]
|
|
output_blocks.2.1.transformer_blocks.4.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.2.1.transformer_blocks.4.ff.net.2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.4.ff.net.2.weight [1280,5120]
|
|
output_blocks.2.1.transformer_blocks.4.norm1.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.4.norm1.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.4.norm2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.4.norm2.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.4.norm3.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.4.norm3.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.5.attn1.to_k.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.5.attn1.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.5.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.5.attn1.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.5.attn1.to_v.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.5.attn2.to_k.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.5.attn2.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.5.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.5.attn2.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.5.attn2.to_v.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.5.ff.net.0.proj.bias [10240]
|
|
output_blocks.2.1.transformer_blocks.5.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.2.1.transformer_blocks.5.ff.net.2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.5.ff.net.2.weight [1280,5120]
|
|
output_blocks.2.1.transformer_blocks.5.norm1.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.5.norm1.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.5.norm2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.5.norm2.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.5.norm3.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.5.norm3.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.6.attn1.to_k.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.6.attn1.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.6.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.6.attn1.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.6.attn1.to_v.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.6.attn2.to_k.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.6.attn2.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.6.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.6.attn2.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.6.attn2.to_v.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.6.ff.net.0.proj.bias [10240]
|
|
output_blocks.2.1.transformer_blocks.6.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.2.1.transformer_blocks.6.ff.net.2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.6.ff.net.2.weight [1280,5120]
|
|
output_blocks.2.1.transformer_blocks.6.norm1.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.6.norm1.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.6.norm2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.6.norm2.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.6.norm3.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.6.norm3.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.7.attn1.to_k.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.7.attn1.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.7.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.7.attn1.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.7.attn1.to_v.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.7.attn2.to_k.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.7.attn2.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.7.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.7.attn2.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.7.attn2.to_v.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.7.ff.net.0.proj.bias [10240]
|
|
output_blocks.2.1.transformer_blocks.7.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.2.1.transformer_blocks.7.ff.net.2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.7.ff.net.2.weight [1280,5120]
|
|
output_blocks.2.1.transformer_blocks.7.norm1.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.7.norm1.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.7.norm2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.7.norm2.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.7.norm3.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.7.norm3.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.8.attn1.to_k.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.8.attn1.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.8.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.8.attn1.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.8.attn1.to_v.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.8.attn2.to_k.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.8.attn2.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.8.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.8.attn2.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.8.attn2.to_v.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.8.ff.net.0.proj.bias [10240]
|
|
output_blocks.2.1.transformer_blocks.8.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.2.1.transformer_blocks.8.ff.net.2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.8.ff.net.2.weight [1280,5120]
|
|
output_blocks.2.1.transformer_blocks.8.norm1.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.8.norm1.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.8.norm2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.8.norm2.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.8.norm3.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.8.norm3.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.9.attn1.to_k.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.9.attn1.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.9.attn1.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.9.attn1.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.9.attn1.to_v.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.9.attn2.to_k.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.9.attn2.to_out.0.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.9.attn2.to_out.0.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.9.attn2.to_q.weight [1280,1280]
|
|
output_blocks.2.1.transformer_blocks.9.attn2.to_v.weight [1280,2048]
|
|
output_blocks.2.1.transformer_blocks.9.ff.net.0.proj.bias [10240]
|
|
output_blocks.2.1.transformer_blocks.9.ff.net.0.proj.weight [10240,1280]
|
|
output_blocks.2.1.transformer_blocks.9.ff.net.2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.9.ff.net.2.weight [1280,5120]
|
|
output_blocks.2.1.transformer_blocks.9.norm1.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.9.norm1.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.9.norm2.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.9.norm2.weight [1280]
|
|
output_blocks.2.1.transformer_blocks.9.norm3.bias [1280]
|
|
output_blocks.2.1.transformer_blocks.9.norm3.weight [1280]
|
|
output_blocks.2.2.conv.bias [1280]
|
|
output_blocks.2.2.conv.weight [1280,1280,3,3]
|
|
output_blocks.3.0.emb_layers.1.bias [640]
|
|
output_blocks.3.0.emb_layers.1.weight [640,1280]
|
|
output_blocks.3.0.in_layers.0.bias [1920]
|
|
output_blocks.3.0.in_layers.0.weight [1920]
|
|
output_blocks.3.0.in_layers.2.bias [640]
|
|
output_blocks.3.0.in_layers.2.weight [640,1920,3,3]
|
|
output_blocks.3.0.out_layers.0.bias [640]
|
|
output_blocks.3.0.out_layers.0.weight [640]
|
|
output_blocks.3.0.out_layers.3.bias [640]
|
|
output_blocks.3.0.out_layers.3.weight [640,640,3,3]
|
|
output_blocks.3.0.skip_connection.bias [640]
|
|
output_blocks.3.0.skip_connection.weight [640,1920,1,1]
|
|
output_blocks.3.1.norm.bias [640]
|
|
output_blocks.3.1.norm.weight [640]
|
|
output_blocks.3.1.proj_in.bias [640]
|
|
output_blocks.3.1.proj_in.weight [640,640]
|
|
output_blocks.3.1.proj_out.bias [640]
|
|
output_blocks.3.1.proj_out.weight [640,640]
|
|
output_blocks.3.1.transformer_blocks.0.attn1.to_k.weight [640,640]
|
|
output_blocks.3.1.transformer_blocks.0.attn1.to_out.0.bias [640]
|
|
output_blocks.3.1.transformer_blocks.0.attn1.to_out.0.weight [640,640]
|
|
output_blocks.3.1.transformer_blocks.0.attn1.to_q.weight [640,640]
|
|
output_blocks.3.1.transformer_blocks.0.attn1.to_v.weight [640,640]
|
|
output_blocks.3.1.transformer_blocks.0.attn2.to_k.weight [640,2048]
|
|
output_blocks.3.1.transformer_blocks.0.attn2.to_out.0.bias [640]
|
|
output_blocks.3.1.transformer_blocks.0.attn2.to_out.0.weight [640,640]
|
|
output_blocks.3.1.transformer_blocks.0.attn2.to_q.weight [640,640]
|
|
output_blocks.3.1.transformer_blocks.0.attn2.to_v.weight [640,2048]
|
|
output_blocks.3.1.transformer_blocks.0.ff.net.0.proj.bias [5120]
|
|
output_blocks.3.1.transformer_blocks.0.ff.net.0.proj.weight [5120,640]
|
|
output_blocks.3.1.transformer_blocks.0.ff.net.2.bias [640]
|
|
output_blocks.3.1.transformer_blocks.0.ff.net.2.weight [640,2560]
|
|
output_blocks.3.1.transformer_blocks.0.norm1.bias [640]
|
|
output_blocks.3.1.transformer_blocks.0.norm1.weight [640]
|
|
output_blocks.3.1.transformer_blocks.0.norm2.bias [640]
|
|
output_blocks.3.1.transformer_blocks.0.norm2.weight [640]
|
|
output_blocks.3.1.transformer_blocks.0.norm3.bias [640]
|
|
output_blocks.3.1.transformer_blocks.0.norm3.weight [640]
|
|
output_blocks.3.1.transformer_blocks.1.attn1.to_k.weight [640,640]
|
|
output_blocks.3.1.transformer_blocks.1.attn1.to_out.0.bias [640]
|
|
output_blocks.3.1.transformer_blocks.1.attn1.to_out.0.weight [640,640]
|
|
output_blocks.3.1.transformer_blocks.1.attn1.to_q.weight [640,640]
|
|
output_blocks.3.1.transformer_blocks.1.attn1.to_v.weight [640,640]
|
|
output_blocks.3.1.transformer_blocks.1.attn2.to_k.weight [640,2048]
|
|
output_blocks.3.1.transformer_blocks.1.attn2.to_out.0.bias [640]
|
|
output_blocks.3.1.transformer_blocks.1.attn2.to_out.0.weight [640,640]
|
|
output_blocks.3.1.transformer_blocks.1.attn2.to_q.weight [640,640]
|
|
output_blocks.3.1.transformer_blocks.1.attn2.to_v.weight [640,2048]
|
|
output_blocks.3.1.transformer_blocks.1.ff.net.0.proj.bias [5120]
|
|
output_blocks.3.1.transformer_blocks.1.ff.net.0.proj.weight [5120,640]
|
|
output_blocks.3.1.transformer_blocks.1.ff.net.2.bias [640]
|
|
output_blocks.3.1.transformer_blocks.1.ff.net.2.weight [640,2560]
|
|
output_blocks.3.1.transformer_blocks.1.norm1.bias [640]
|
|
output_blocks.3.1.transformer_blocks.1.norm1.weight [640]
|
|
output_blocks.3.1.transformer_blocks.1.norm2.bias [640]
|
|
output_blocks.3.1.transformer_blocks.1.norm2.weight [640]
|
|
output_blocks.3.1.transformer_blocks.1.norm3.bias [640]
|
|
output_blocks.3.1.transformer_blocks.1.norm3.weight [640]
|
|
output_blocks.4.0.emb_layers.1.bias [640]
|
|
output_blocks.4.0.emb_layers.1.weight [640,1280]
|
|
output_blocks.4.0.in_layers.0.bias [1280]
|
|
output_blocks.4.0.in_layers.0.weight [1280]
|
|
output_blocks.4.0.in_layers.2.bias [640]
|
|
output_blocks.4.0.in_layers.2.weight [640,1280,3,3]
|
|
output_blocks.4.0.out_layers.0.bias [640]
|
|
output_blocks.4.0.out_layers.0.weight [640]
|
|
output_blocks.4.0.out_layers.3.bias [640]
|
|
output_blocks.4.0.out_layers.3.weight [640,640,3,3]
|
|
output_blocks.4.0.skip_connection.bias [640]
|
|
output_blocks.4.0.skip_connection.weight [640,1280,1,1]
|
|
output_blocks.4.1.norm.bias [640]
|
|
output_blocks.4.1.norm.weight [640]
|
|
output_blocks.4.1.proj_in.bias [640]
|
|
output_blocks.4.1.proj_in.weight [640,640]
|
|
output_blocks.4.1.proj_out.bias [640]
|
|
output_blocks.4.1.proj_out.weight [640,640]
|
|
output_blocks.4.1.transformer_blocks.0.attn1.to_k.weight [640,640]
|
|
output_blocks.4.1.transformer_blocks.0.attn1.to_out.0.bias [640]
|
|
output_blocks.4.1.transformer_blocks.0.attn1.to_out.0.weight [640,640]
|
|
output_blocks.4.1.transformer_blocks.0.attn1.to_q.weight [640,640]
|
|
output_blocks.4.1.transformer_blocks.0.attn1.to_v.weight [640,640]
|
|
output_blocks.4.1.transformer_blocks.0.attn2.to_k.weight [640,2048]
|
|
output_blocks.4.1.transformer_blocks.0.attn2.to_out.0.bias [640]
|
|
output_blocks.4.1.transformer_blocks.0.attn2.to_out.0.weight [640,640]
|
|
output_blocks.4.1.transformer_blocks.0.attn2.to_q.weight [640,640]
|
|
output_blocks.4.1.transformer_blocks.0.attn2.to_v.weight [640,2048]
|
|
output_blocks.4.1.transformer_blocks.0.ff.net.0.proj.bias [5120]
|
|
output_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight [5120,640]
|
|
output_blocks.4.1.transformer_blocks.0.ff.net.2.bias [640]
|
|
output_blocks.4.1.transformer_blocks.0.ff.net.2.weight [640,2560]
|
|
output_blocks.4.1.transformer_blocks.0.norm1.bias [640]
|
|
output_blocks.4.1.transformer_blocks.0.norm1.weight [640]
|
|
output_blocks.4.1.transformer_blocks.0.norm2.bias [640]
|
|
output_blocks.4.1.transformer_blocks.0.norm2.weight [640]
|
|
output_blocks.4.1.transformer_blocks.0.norm3.bias [640]
|
|
output_blocks.4.1.transformer_blocks.0.norm3.weight [640]
|
|
output_blocks.4.1.transformer_blocks.1.attn1.to_k.weight [640,640]
|
|
output_blocks.4.1.transformer_blocks.1.attn1.to_out.0.bias [640]
|
|
output_blocks.4.1.transformer_blocks.1.attn1.to_out.0.weight [640,640]
|
|
output_blocks.4.1.transformer_blocks.1.attn1.to_q.weight [640,640]
|
|
output_blocks.4.1.transformer_blocks.1.attn1.to_v.weight [640,640]
|
|
output_blocks.4.1.transformer_blocks.1.attn2.to_k.weight [640,2048]
|
|
output_blocks.4.1.transformer_blocks.1.attn2.to_out.0.bias [640]
|
|
output_blocks.4.1.transformer_blocks.1.attn2.to_out.0.weight [640,640]
|
|
output_blocks.4.1.transformer_blocks.1.attn2.to_q.weight [640,640]
|
|
output_blocks.4.1.transformer_blocks.1.attn2.to_v.weight [640,2048]
|
|
output_blocks.4.1.transformer_blocks.1.ff.net.0.proj.bias [5120]
|
|
output_blocks.4.1.transformer_blocks.1.ff.net.0.proj.weight [5120,640]
|
|
output_blocks.4.1.transformer_blocks.1.ff.net.2.bias [640]
|
|
output_blocks.4.1.transformer_blocks.1.ff.net.2.weight [640,2560]
|
|
output_blocks.4.1.transformer_blocks.1.norm1.bias [640]
|
|
output_blocks.4.1.transformer_blocks.1.norm1.weight [640]
|
|
output_blocks.4.1.transformer_blocks.1.norm2.bias [640]
|
|
output_blocks.4.1.transformer_blocks.1.norm2.weight [640]
|
|
output_blocks.4.1.transformer_blocks.1.norm3.bias [640]
|
|
output_blocks.4.1.transformer_blocks.1.norm3.weight [640]
|
|
output_blocks.5.0.emb_layers.1.bias [640]
|
|
output_blocks.5.0.emb_layers.1.weight [640,1280]
|
|
output_blocks.5.0.in_layers.0.bias [960]
|
|
output_blocks.5.0.in_layers.0.weight [960]
|
|
output_blocks.5.0.in_layers.2.bias [640]
|
|
output_blocks.5.0.in_layers.2.weight [640,960,3,3]
|
|
output_blocks.5.0.out_layers.0.bias [640]
|
|
output_blocks.5.0.out_layers.0.weight [640]
|
|
output_blocks.5.0.out_layers.3.bias [640]
|
|
output_blocks.5.0.out_layers.3.weight [640,640,3,3]
|
|
output_blocks.5.0.skip_connection.bias [640]
|
|
output_blocks.5.0.skip_connection.weight [640,960,1,1]
|
|
output_blocks.5.1.norm.bias [640]
|
|
output_blocks.5.1.norm.weight [640]
|
|
output_blocks.5.1.proj_in.bias [640]
|
|
output_blocks.5.1.proj_in.weight [640,640]
|
|
output_blocks.5.1.proj_out.bias [640]
|
|
output_blocks.5.1.proj_out.weight [640,640]
|
|
output_blocks.5.1.transformer_blocks.0.attn1.to_k.weight [640,640]
|
|
output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.bias [640]
|
|
output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight [640,640]
|
|
output_blocks.5.1.transformer_blocks.0.attn1.to_q.weight [640,640]
|
|
output_blocks.5.1.transformer_blocks.0.attn1.to_v.weight [640,640]
|
|
output_blocks.5.1.transformer_blocks.0.attn2.to_k.weight [640,2048]
|
|
output_blocks.5.1.transformer_blocks.0.attn2.to_out.0.bias [640]
|
|
output_blocks.5.1.transformer_blocks.0.attn2.to_out.0.weight [640,640]
|
|
output_blocks.5.1.transformer_blocks.0.attn2.to_q.weight [640,640]
|
|
output_blocks.5.1.transformer_blocks.0.attn2.to_v.weight [640,2048]
|
|
output_blocks.5.1.transformer_blocks.0.ff.net.0.proj.bias [5120]
|
|
output_blocks.5.1.transformer_blocks.0.ff.net.0.proj.weight [5120,640]
|
|
output_blocks.5.1.transformer_blocks.0.ff.net.2.bias [640]
|
|
output_blocks.5.1.transformer_blocks.0.ff.net.2.weight [640,2560]
|
|
output_blocks.5.1.transformer_blocks.0.norm1.bias [640]
|
|
output_blocks.5.1.transformer_blocks.0.norm1.weight [640]
|
|
output_blocks.5.1.transformer_blocks.0.norm2.bias [640]
|
|
output_blocks.5.1.transformer_blocks.0.norm2.weight [640]
|
|
output_blocks.5.1.transformer_blocks.0.norm3.bias [640]
|
|
output_blocks.5.1.transformer_blocks.0.norm3.weight [640]
|
|
output_blocks.5.1.transformer_blocks.1.attn1.to_k.weight [640,640]
|
|
output_blocks.5.1.transformer_blocks.1.attn1.to_out.0.bias [640]
|
|
output_blocks.5.1.transformer_blocks.1.attn1.to_out.0.weight [640,640]
|
|
output_blocks.5.1.transformer_blocks.1.attn1.to_q.weight [640,640]
|
|
output_blocks.5.1.transformer_blocks.1.attn1.to_v.weight [640,640]
|
|
output_blocks.5.1.transformer_blocks.1.attn2.to_k.weight [640,2048]
|
|
output_blocks.5.1.transformer_blocks.1.attn2.to_out.0.bias [640]
|
|
output_blocks.5.1.transformer_blocks.1.attn2.to_out.0.weight [640,640]
|
|
output_blocks.5.1.transformer_blocks.1.attn2.to_q.weight [640,640]
|
|
output_blocks.5.1.transformer_blocks.1.attn2.to_v.weight [640,2048]
|
|
output_blocks.5.1.transformer_blocks.1.ff.net.0.proj.bias [5120]
|
|
output_blocks.5.1.transformer_blocks.1.ff.net.0.proj.weight [5120,640]
|
|
output_blocks.5.1.transformer_blocks.1.ff.net.2.bias [640]
|
|
output_blocks.5.1.transformer_blocks.1.ff.net.2.weight [640,2560]
|
|
output_blocks.5.1.transformer_blocks.1.norm1.bias [640]
|
|
output_blocks.5.1.transformer_blocks.1.norm1.weight [640]
|
|
output_blocks.5.1.transformer_blocks.1.norm2.bias [640]
|
|
output_blocks.5.1.transformer_blocks.1.norm2.weight [640]
|
|
output_blocks.5.1.transformer_blocks.1.norm3.bias [640]
|
|
output_blocks.5.1.transformer_blocks.1.norm3.weight [640]
|
|
output_blocks.5.2.conv.bias [640]
|
|
output_blocks.5.2.conv.weight [640,640,3,3]
|
|
output_blocks.6.0.emb_layers.1.bias [320]
|
|
output_blocks.6.0.emb_layers.1.weight [320,1280]
|
|
output_blocks.6.0.in_layers.0.bias [960]
|
|
output_blocks.6.0.in_layers.0.weight [960]
|
|
output_blocks.6.0.in_layers.2.bias [320]
|
|
output_blocks.6.0.in_layers.2.weight [320,960,3,3]
|
|
output_blocks.6.0.out_layers.0.bias [320]
|
|
output_blocks.6.0.out_layers.0.weight [320]
|
|
output_blocks.6.0.out_layers.3.bias [320]
|
|
output_blocks.6.0.out_layers.3.weight [320,320,3,3]
|
|
output_blocks.6.0.skip_connection.bias [320]
|
|
output_blocks.6.0.skip_connection.weight [320,960,1,1]
|
|
output_blocks.7.0.emb_layers.1.bias [320]
|
|
output_blocks.7.0.emb_layers.1.weight [320,1280]
|
|
output_blocks.7.0.in_layers.0.bias [640]
|
|
output_blocks.7.0.in_layers.0.weight [640]
|
|
output_blocks.7.0.in_layers.2.bias [320]
|
|
output_blocks.7.0.in_layers.2.weight [320,640,3,3]
|
|
output_blocks.7.0.out_layers.0.bias [320]
|
|
output_blocks.7.0.out_layers.0.weight [320]
|
|
output_blocks.7.0.out_layers.3.bias [320]
|
|
output_blocks.7.0.out_layers.3.weight [320,320,3,3]
|
|
output_blocks.7.0.skip_connection.bias [320]
|
|
output_blocks.7.0.skip_connection.weight [320,640,1,1]
|
|
output_blocks.8.0.emb_layers.1.bias [320]
|
|
output_blocks.8.0.emb_layers.1.weight [320,1280]
|
|
output_blocks.8.0.in_layers.0.bias [640]
|
|
output_blocks.8.0.in_layers.0.weight [640]
|
|
output_blocks.8.0.in_layers.2.bias [320]
|
|
output_blocks.8.0.in_layers.2.weight [320,640,3,3]
|
|
output_blocks.8.0.out_layers.0.bias [320]
|
|
output_blocks.8.0.out_layers.0.weight [320]
|
|
output_blocks.8.0.out_layers.3.bias [320]
|
|
output_blocks.8.0.out_layers.3.weight [320,320,3,3]
|
|
output_blocks.8.0.skip_connection.bias [320]
|
|
output_blocks.8.0.skip_connection.weight [320,640,1,1]
|
|
time_embed.0.bias [1280]
|
|
time_embed.0.weight [1280,320]
|
|
time_embed.2.bias [1280]
|
|
time_embed.2.weight [1280,1280] |