mirror of
https://github.com/huggingface/candle.git
synced 2025-06-16 10:38:54 +00:00

* onnx attention * setup an example, adding and fixing onnx ops bit by bit * model working, output is garbage data * trilu working * close but not quite, Issues still with scatterND * closer but the outputs are still slightly wrong * added tests for trilu and scatterND * lint * readme * clippy * removed unnessisary comments * changed device selection, took hyperparameters from model config
295 B
295 B
Using ONNX models in Candle
This example demonstrates how to run ONNX based LLM models in Candle.
This script only implements SmolLM-135M right now.
You can run the examples with following commands:
cargo run --example onnx-llm --features onnx