Hugging Face's logo

archevel
/
laya-web

ONNX
Laya
onnxruntime-web
webgpu
Model card Files
xet
 Community
laya-web / README.md
archevel's picture
archevel
Upload folder using huggingface_hub
da1f557 verified
preview code
|
Raw History Blame Contribute Delete
1.13 kB
metadata 
license: apache-2.0
base_model: convaiinnovations/laya
library_name: onnx
tags:
  - onnx
  - onnxruntime-web
  - webgpu
  - laya

Laya for WebGPU in the browser (int8 ONNX, fp32 embeddings)

Unofficial copy of convaiinnovations/laya (Apache-2.0, Copyright ConvAI Innovations) for onnxruntime-web. Used by https://archevel.github.io/laya/.

Made from harshpreet931/cut-laya-onnx (revision 192138dfb32a0b2f73425ba70345946d415bfde1: 8-bit weight-only MatMulNBits, split encoder/head for laya-ts) with one change: the token-embedding table in encoder.onnx is widened from fp16 to fp32 (lossless). With the fp16 table, onnxruntime-web's WebGPU Gather requires the shader-f16 feature, which Chrome does not expose on e.g. Linux with NVIDIA GPUs. Script: tools/embeddings_to_fp32.py in https://github.com/archevel/laya.

Outputs differ slightly from the PyTorch checkpoint because of the 8-bit weights.

Licensed under the Apache License, Version 2.0, like the original.