|
Download README.md from rasgaard/Embla1-4bit-webgpu: direct link, hf CLI and curl.
- Browser
- Download file 1.36 kB
-
https://huggingface.co/rasgaard/Embla1-4bit-webgpu/resolve/main/README.md
- Command line
-
hf download hf://rasgaard/Embla1-4bit-webgpu/README.md
-
curl -L -o README.md https://huggingface.co/rasgaard/Embla1-4bit-webgpu/resolve/main/README.md
1.36 kB
| license: mit | |
| base_model: sevren-ai/Embla1-4bit | |
| library_name: onnx | |
| pipeline_tag: text-generation | |
| tags: [embla, webgpu, onnxruntime-web, onnx] | |
| # Embla1-4bit, WebGPU step graph | |
| 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 | |
| [`sevren-ai/Embla1-4bit`](https://huggingface.co/sevren-ai/Embla1-4bit). One step of the model (a prefill chunk of up to 64 | |
| tokens, or one decode token) with the KV / engram-conv cache as explicit inputs and outputs, exported from the PyTorch reference | |
| and rewritten for onnxruntime-web's WebGPU execution provider. | |
| - `embla_step.onnx` + `embla_step.onnx.data` (0.48 GB): the non-expert weights in MLX's 4-bit format, as `MatMulNBits` with an | |
| exact offset term for the affine bias. | |
| - The routed experts (3.9 GB) are **graph inputs**, not part of this repo. The engine streams them from | |
| `sevren-ai/Embla1-4bit/model.safetensors`. The engram rows are an input too (looked up in that repo's `engram_table.safetensors`). | |
| Build: `sh tools/build_graph.sh` in the [GitHub repo](https://github.com/rasgaard/embla-webgpu) (export + four graph rewrites, documented there). | |
| Model by [sevren.ai](https://huggingface.co/sevren-ai), MIT licensed. This is a derived format of their weights, under the same license. | |