Image21-INT8 / transformer-quantization.json
ixim's picture
Release verified Image21-INT8 conversion
6f8c80a verified
Raw History Blame Contribute Delete
9.85 kB
{
"component": "transformer",
"method": "bitsandbytes LLM.int8",
"threshold": 6.0,
"skip_modules": [
"proj_out",
"img_in",
"txt_in",
"time_text_embed",
"modulation",
"norm_out"
],
"linear8bit_modules": [
"transformer_blocks.0.attn.to_q",
"transformer_blocks.0.attn.to_k",
"transformer_blocks.0.attn.to_v",
"transformer_blocks.0.attn.to_out.0",
"transformer_blocks.0.img_mlp.proj",
"transformer_blocks.0.img_mlp.out",
"transformer_blocks.0.img_mlp.gate_layer",
"transformer_blocks.1.attn.to_q",
"transformer_blocks.1.attn.to_k",
"transformer_blocks.1.attn.to_v",
"transformer_blocks.1.attn.to_out.0",
"transformer_blocks.1.img_mlp.proj",
"transformer_blocks.1.img_mlp.out",
"transformer_blocks.1.img_mlp.gate_layer",
"transformer_blocks.2.attn.to_q",
"transformer_blocks.2.attn.to_k",
"transformer_blocks.2.attn.to_v",
"transformer_blocks.2.attn.to_out.0",
"transformer_blocks.2.img_mlp.proj",
"transformer_blocks.2.img_mlp.out",
"transformer_blocks.2.img_mlp.gate_layer",
"transformer_blocks.3.attn.to_q",
"transformer_blocks.3.attn.to_k",
"transformer_blocks.3.attn.to_v",
"transformer_blocks.3.attn.to_out.0",
"transformer_blocks.3.img_mlp.proj",
"transformer_blocks.3.img_mlp.out",
"transformer_blocks.3.img_mlp.gate_layer",
"transformer_blocks.4.attn.to_q",
"transformer_blocks.4.attn.to_k",
"transformer_blocks.4.attn.to_v",
"transformer_blocks.4.attn.to_out.0",
"transformer_blocks.4.img_mlp.proj",
"transformer_blocks.4.img_mlp.out",
"transformer_blocks.4.img_mlp.gate_layer",
"transformer_blocks.5.attn.to_q",
"transformer_blocks.5.attn.to_k",
"transformer_blocks.5.attn.to_v",
"transformer_blocks.5.attn.to_out.0",
"transformer_blocks.5.img_mlp.proj",
"transformer_blocks.5.img_mlp.out",
"transformer_blocks.5.img_mlp.gate_layer",
"transformer_blocks.6.attn.to_q",
"transformer_blocks.6.attn.to_k",
"transformer_blocks.6.attn.to_v",
"transformer_blocks.6.attn.to_out.0",
"transformer_blocks.6.img_mlp.proj",
"transformer_blocks.6.img_mlp.out",
"transformer_blocks.6.img_mlp.gate_layer",
"transformer_blocks.7.attn.to_q",
"transformer_blocks.7.attn.to_k",
"transformer_blocks.7.attn.to_v",
"transformer_blocks.7.attn.to_out.0",
"transformer_blocks.7.img_mlp.proj",
"transformer_blocks.7.img_mlp.out",
"transformer_blocks.7.img_mlp.gate_layer",
"transformer_blocks.8.attn.to_q",
"transformer_blocks.8.attn.to_k",
"transformer_blocks.8.attn.to_v",
"transformer_blocks.8.attn.to_out.0",
"transformer_blocks.8.img_mlp.proj",
"transformer_blocks.8.img_mlp.out",
"transformer_blocks.8.img_mlp.gate_layer",
"transformer_blocks.9.attn.to_q",
"transformer_blocks.9.attn.to_k",
"transformer_blocks.9.attn.to_v",
"transformer_blocks.9.attn.to_out.0",
"transformer_blocks.9.img_mlp.proj",
"transformer_blocks.9.img_mlp.out",
"transformer_blocks.9.img_mlp.gate_layer",
"transformer_blocks.10.attn.to_q",
"transformer_blocks.10.attn.to_k",
"transformer_blocks.10.attn.to_v",
"transformer_blocks.10.attn.to_out.0",
"transformer_blocks.10.img_mlp.proj",
"transformer_blocks.10.img_mlp.out",
"transformer_blocks.10.img_mlp.gate_layer",
"transformer_blocks.11.attn.to_q",
"transformer_blocks.11.attn.to_k",
"transformer_blocks.11.attn.to_v",
"transformer_blocks.11.attn.to_out.0",
"transformer_blocks.11.img_mlp.proj",
"transformer_blocks.11.img_mlp.out",
"transformer_blocks.11.img_mlp.gate_layer",
"transformer_blocks.12.attn.to_q",
"transformer_blocks.12.attn.to_k",
"transformer_blocks.12.attn.to_v",
"transformer_blocks.12.attn.to_out.0",
"transformer_blocks.12.img_mlp.proj",
"transformer_blocks.12.img_mlp.out",
"transformer_blocks.12.img_mlp.gate_layer",
"transformer_blocks.13.attn.to_q",
"transformer_blocks.13.attn.to_k",
"transformer_blocks.13.attn.to_v",
"transformer_blocks.13.attn.to_out.0",
"transformer_blocks.13.img_mlp.proj",
"transformer_blocks.13.img_mlp.out",
"transformer_blocks.13.img_mlp.gate_layer",
"transformer_blocks.14.attn.to_q",
"transformer_blocks.14.attn.to_k",
"transformer_blocks.14.attn.to_v",
"transformer_blocks.14.attn.to_out.0",
"transformer_blocks.14.img_mlp.proj",
"transformer_blocks.14.img_mlp.out",
"transformer_blocks.14.img_mlp.gate_layer",
"transformer_blocks.15.attn.to_q",
"transformer_blocks.15.attn.to_k",
"transformer_blocks.15.attn.to_v",
"transformer_blocks.15.attn.to_out.0",
"transformer_blocks.15.img_mlp.proj",
"transformer_blocks.15.img_mlp.out",
"transformer_blocks.15.img_mlp.gate_layer",
"transformer_blocks.16.attn.to_q",
"transformer_blocks.16.attn.to_k",
"transformer_blocks.16.attn.to_v",
"transformer_blocks.16.attn.to_out.0",
"transformer_blocks.16.img_mlp.proj",
"transformer_blocks.16.img_mlp.out",
"transformer_blocks.16.img_mlp.gate_layer",
"transformer_blocks.17.attn.to_q",
"transformer_blocks.17.attn.to_k",
"transformer_blocks.17.attn.to_v",
"transformer_blocks.17.attn.to_out.0",
"transformer_blocks.17.img_mlp.proj",
"transformer_blocks.17.img_mlp.out",
"transformer_blocks.17.img_mlp.gate_layer",
"transformer_blocks.18.attn.to_q",
"transformer_blocks.18.attn.to_k",
"transformer_blocks.18.attn.to_v",
"transformer_blocks.18.attn.to_out.0",
"transformer_blocks.18.img_mlp.proj",
"transformer_blocks.18.img_mlp.out",
"transformer_blocks.18.img_mlp.gate_layer",
"transformer_blocks.19.attn.to_q",
"transformer_blocks.19.attn.to_k",
"transformer_blocks.19.attn.to_v",
"transformer_blocks.19.attn.to_out.0",
"transformer_blocks.19.img_mlp.proj",
"transformer_blocks.19.img_mlp.out",
"transformer_blocks.19.img_mlp.gate_layer",
"transformer_blocks.20.attn.to_q",
"transformer_blocks.20.attn.to_k",
"transformer_blocks.20.attn.to_v",
"transformer_blocks.20.attn.to_out.0",
"transformer_blocks.20.img_mlp.proj",
"transformer_blocks.20.img_mlp.out",
"transformer_blocks.20.img_mlp.gate_layer",
"transformer_blocks.21.attn.to_q",
"transformer_blocks.21.attn.to_k",
"transformer_blocks.21.attn.to_v",
"transformer_blocks.21.attn.to_out.0",
"transformer_blocks.21.img_mlp.proj",
"transformer_blocks.21.img_mlp.out",
"transformer_blocks.21.img_mlp.gate_layer",
"transformer_blocks.22.attn.to_q",
"transformer_blocks.22.attn.to_k",
"transformer_blocks.22.attn.to_v",
"transformer_blocks.22.attn.to_out.0",
"transformer_blocks.22.img_mlp.proj",
"transformer_blocks.22.img_mlp.out",
"transformer_blocks.22.img_mlp.gate_layer",
"transformer_blocks.23.attn.to_q",
"transformer_blocks.23.attn.to_k",
"transformer_blocks.23.attn.to_v",
"transformer_blocks.23.attn.to_out.0",
"transformer_blocks.23.img_mlp.proj",
"transformer_blocks.23.img_mlp.out",
"transformer_blocks.23.img_mlp.gate_layer",
"transformer_blocks.24.attn.to_q",
"transformer_blocks.24.attn.to_k",
"transformer_blocks.24.attn.to_v",
"transformer_blocks.24.attn.to_out.0",
"transformer_blocks.24.img_mlp.proj",
"transformer_blocks.24.img_mlp.out",
"transformer_blocks.24.img_mlp.gate_layer",
"transformer_blocks.25.attn.to_q",
"transformer_blocks.25.attn.to_k",
"transformer_blocks.25.attn.to_v",
"transformer_blocks.25.attn.to_out.0",
"transformer_blocks.25.img_mlp.proj",
"transformer_blocks.25.img_mlp.out",
"transformer_blocks.25.img_mlp.gate_layer",
"transformer_blocks.26.attn.to_q",
"transformer_blocks.26.attn.to_k",
"transformer_blocks.26.attn.to_v",
"transformer_blocks.26.attn.to_out.0",
"transformer_blocks.26.img_mlp.proj",
"transformer_blocks.26.img_mlp.out",
"transformer_blocks.26.img_mlp.gate_layer",
"transformer_blocks.27.attn.to_q",
"transformer_blocks.27.attn.to_k",
"transformer_blocks.27.attn.to_v",
"transformer_blocks.27.attn.to_out.0",
"transformer_blocks.27.img_mlp.proj",
"transformer_blocks.27.img_mlp.out",
"transformer_blocks.27.img_mlp.gate_layer",
"transformer_blocks.28.attn.to_q",
"transformer_blocks.28.attn.to_k",
"transformer_blocks.28.attn.to_v",
"transformer_blocks.28.attn.to_out.0",
"transformer_blocks.28.img_mlp.proj",
"transformer_blocks.28.img_mlp.out",
"transformer_blocks.28.img_mlp.gate_layer",
"transformer_blocks.29.attn.to_q",
"transformer_blocks.29.attn.to_k",
"transformer_blocks.29.attn.to_v",
"transformer_blocks.29.attn.to_out.0",
"transformer_blocks.29.img_mlp.proj",
"transformer_blocks.29.img_mlp.out",
"transformer_blocks.29.img_mlp.gate_layer",
"transformer_blocks.30.attn.to_q",
"transformer_blocks.30.attn.to_k",
"transformer_blocks.30.attn.to_v",
"transformer_blocks.30.attn.to_out.0",
"transformer_blocks.30.img_mlp.proj",
"transformer_blocks.30.img_mlp.out",
"transformer_blocks.30.img_mlp.gate_layer",
"transformer_blocks.31.attn.to_q",
"transformer_blocks.31.attn.to_k",
"transformer_blocks.31.attn.to_v",
"transformer_blocks.31.attn.to_out.0",
"transformer_blocks.31.img_mlp.proj",
"transformer_blocks.31.img_mlp.out",
"transformer_blocks.31.img_mlp.gate_layer"
],
"parameter_dtypes": {
"torch.bfloat16": 135802880,
"torch.int8": 6979321856
},
"int8_parameters": 6979321856
}