model_png.json

{"cfg": {"dim": 512, "depth": 16, "heads": 8, "mlp_hidden": 1408, "t5_len": 32}, "params": [{"name": "x_embed.weight", "shape": [512, 16], "numel": 8192}, {"name": "x_embed.bias", "shape": [512], "numel": 512}, {"name": "t_mlp.0.weight", "shape": [512, 512], "numel": 262144}, {"name": "t_mlp.0.bias", "shape": [512], "numel": 512}, {"name": "t_mlp.2.weight", "shape": [512, 512], "numel": 262144}, {"name": "t_mlp.2.bias", "shape": [512], "numel": 512}, {"name": "clip_proj.weight", "shape": [512, 512], "numel": 262144}, {"name": "clip_proj.bias", "shape": [512], "numel": 512}, {"name": "t5_proj.weight", "shape": [512, 768], "numel": 393216}, {"name": "t5_proj.bias", "shape": [512], "numel": 512}, {"name": "blocks.0.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.0.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.0.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.0.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.0.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.0.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.0.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.0.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.0.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.0.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.0.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.0.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.0.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.0.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.0.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.0.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.0.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.0.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.0.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.0.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.0.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.0.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.0.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.0.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.0.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.0.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.0.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.0.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.1.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.1.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.1.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.1.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.1.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.1.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.1.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.1.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.1.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.1.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.1.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.1.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.1.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.1.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.1.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.1.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.1.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.1.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.1.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.1.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.1.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.1.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.1.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.1.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.1.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.1.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.1.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.1.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.2.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.2.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.2.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.2.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.2.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.2.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.2.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.2.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.2.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.2.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.2.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.2.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.2.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.2.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.2.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.2.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.2.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.2.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.2.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.2.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.2.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.2.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.2.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.2.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.2.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.2.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.2.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.2.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.3.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.3.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.3.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.3.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.3.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.3.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.3.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.3.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.3.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.3.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.3.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.3.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.3.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.3.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.3.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.3.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.3.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.3.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.3.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.3.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.3.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.3.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.3.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.3.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.3.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.3.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.3.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.3.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.4.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.4.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.4.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.4.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.4.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.4.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.4.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.4.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.4.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.4.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.4.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.4.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.4.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.4.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.4.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.4.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.4.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.4.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.4.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.4.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.4.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.4.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.4.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.4.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.4.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.4.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.4.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.4.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.5.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.5.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.5.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.5.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.5.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.5.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.5.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.5.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.5.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.5.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.5.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.5.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.5.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.5.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.5.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.5.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.5.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.5.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.5.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.5.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.5.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.5.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.5.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.5.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.5.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.5.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.5.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.5.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.6.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.6.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.6.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.6.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.6.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.6.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.6.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.6.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.6.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.6.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.6.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.6.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.6.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.6.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.6.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.6.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.6.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.6.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.6.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.6.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.6.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.6.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.6.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.6.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.6.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.6.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.6.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.6.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.7.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.7.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.7.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.7.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.7.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.7.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.7.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.7.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.7.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.7.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.7.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.7.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.7.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.7.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.7.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.7.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.7.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.7.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.7.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.7.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.7.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.7.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.7.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.7.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.7.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.7.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.7.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.7.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.8.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.8.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.8.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.8.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.8.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.8.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.8.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.8.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.8.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.8.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.8.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.8.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.8.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.8.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.8.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.8.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.8.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.8.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.8.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.8.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.8.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.8.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.8.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.8.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.8.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.8.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.8.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.8.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.9.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.9.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.9.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.9.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.9.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.9.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.9.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.9.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.9.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.9.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.9.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.9.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.9.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.9.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.9.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.9.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.9.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.9.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.9.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.9.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.9.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.9.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.9.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.9.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.9.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.9.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.9.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.9.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.10.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.10.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.10.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.10.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.10.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.10.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.10.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.10.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.10.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.10.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.10.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.10.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.10.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.10.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.10.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.10.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.10.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.10.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.10.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.10.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.10.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.10.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.10.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.10.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.10.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.10.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.10.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.10.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.11.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.11.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.11.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.11.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.11.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.11.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.11.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.11.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.11.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.11.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.11.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.11.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.11.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.11.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.11.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.11.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.11.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.11.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.11.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.11.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.11.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.11.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.11.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.11.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.11.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.11.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.11.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.11.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.12.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.12.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.12.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.12.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.12.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.12.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.12.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.12.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.12.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.12.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.12.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.12.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.12.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.12.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.12.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.12.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.12.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.12.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.12.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.12.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.12.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.12.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.12.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.12.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.12.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.12.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.12.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.12.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.13.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.13.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.13.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.13.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.13.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.13.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.13.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.13.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.13.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.13.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.13.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.13.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.13.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.13.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.13.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.13.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.13.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.13.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.13.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.13.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.13.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.13.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.13.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.13.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.13.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.13.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.13.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.13.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.14.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.14.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.14.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.14.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.14.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.14.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.14.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.14.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.14.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.14.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.14.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.14.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.14.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.14.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.14.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.14.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.14.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.14.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.14.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.14.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.14.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.14.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.14.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.14.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.14.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.14.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.14.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.14.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.15.qkv_img.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.15.qkv_img.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.15.qkv_txt.weight", "shape": [1536, 512], "numel": 786432}, {"name": "blocks.15.qkv_txt.bias", "shape": [1536], "numel": 1536}, {"name": "blocks.15.qn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.15.kn_img.weight", "shape": [64], "numel": 64}, {"name": "blocks.15.qn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.15.kn_txt.weight", "shape": [64], "numel": 64}, {"name": "blocks.15.proj_img.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.15.proj_img.bias", "shape": [512], "numel": 512}, {"name": "blocks.15.proj_txt.weight", "shape": [512, 512], "numel": 262144}, {"name": "blocks.15.proj_txt.bias", "shape": [512], "numel": 512}, {"name": "blocks.15.mlp_img.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.15.mlp_img.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.15.mlp_img.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.15.mlp_img.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.15.mlp_img.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.15.mlp_img.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.15.mlp_txt.gate.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.15.mlp_txt.gate.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.15.mlp_txt.up.weight", "shape": [1408, 512], "numel": 720896}, {"name": "blocks.15.mlp_txt.up.bias", "shape": [1408], "numel": 1408}, {"name": "blocks.15.mlp_txt.down.weight", "shape": [512, 1408], "numel": 720896}, {"name": "blocks.15.mlp_txt.down.bias", "shape": [512], "numel": 512}, {"name": "blocks.15.ada_img.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.15.ada_img.1.bias", "shape": [3072], "numel": 3072}, {"name": "blocks.15.ada_txt.1.weight", "shape": [3072, 512], "numel": 1572864}, {"name": "blocks.15.ada_txt.1.bias", "shape": [3072], "numel": 3072}, {"name": "ada_out.1.weight", "shape": [1024, 512], "numel": 524288}, {"name": "ada_out.1.bias", "shape": [1024], "numel": 1024}, {"name": "head.weight", "shape": [16, 512], "numel": 8192}, {"name": "head.bias", "shape": [16], "numel": 16}], "total_parameters": 155090448, "side": 12454, "dtype": "float16", "channels": "R=hi,G=lo,B=unused"}