rasgaard commited on
Commit
dfd8e2b
·
verified ·
1 Parent(s): d913929

Model card: link the GitHub repo and demo

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -8,7 +8,7 @@ tags: [embla, webgpu, onnxruntime-web, onnx]
8
 
9
  # Embla1-4bit, WebGPU step graph
10
 
11
- The ONNX graph that runs prefill for Embla 1 on WebGPU, a browser engine for
12
  [`sevren-ai/Embla1-4bit`](https://huggingface.co/sevren-ai/Embla1-4bit). One step of the model (a prefill chunk of up to 64
13
  tokens, or one decode token) with the KV / engram-conv cache as explicit inputs and outputs, exported from the PyTorch reference
14
  and rewritten for onnxruntime-web's WebGPU execution provider.
@@ -18,6 +18,6 @@ and rewritten for onnxruntime-web's WebGPU execution provider.
18
  - The routed experts (3.9 GB) are **graph inputs**, not part of this repo. The engine streams them from
19
  `sevren-ai/Embla1-4bit/model.safetensors`. The engram rows are an input too (looked up in that repo's `engram_table.safetensors`).
20
 
21
- Build: `sh tools/build_graph.sh` in the GitHub repo (export + four graph rewrites, documented there).
22
 
23
  Model by [sevren.ai](https://huggingface.co/sevren-ai), MIT licensed. This is a derived format of their weights, under the same license.
 
8
 
9
  # Embla1-4bit, WebGPU step graph
10
 
11
+ The ONNX graph that runs prefill for [Embla 1 on WebGPU](https://github.com/rasgaard/embla-webgpu) ([live demo](https://rasgaard.com/embla-webgpu/)), a browser engine for
12
  [`sevren-ai/Embla1-4bit`](https://huggingface.co/sevren-ai/Embla1-4bit). One step of the model (a prefill chunk of up to 64
13
  tokens, or one decode token) with the KV / engram-conv cache as explicit inputs and outputs, exported from the PyTorch reference
14
  and rewritten for onnxruntime-web's WebGPU execution provider.
 
18
  - The routed experts (3.9 GB) are **graph inputs**, not part of this repo. The engine streams them from
19
  `sevren-ai/Embla1-4bit/model.safetensors`. The engram rows are an input too (looked up in that repo's `engram_table.safetensors`).
20
 
21
+ Build: `sh tools/build_graph.sh` in the [GitHub repo](https://github.com/rasgaard/embla-webgpu) (export + four graph rewrites, documented there).
22
 
23
  Model by [sevren.ai](https://huggingface.co/sevren-ai), MIT licensed. This is a derived format of their weights, under the same license.