candle
candle copied to clipboard
huggingface
Minimalist ML framework for Rust
Hi, I have been trying to use MKL with SmolLMv2. I don't get any errors when building, but there are no speedups. The weird thing is that when I run...
Hi. I have been trying to run SmolLM and the lack of documentation slowed me down. I had to read examples and source codes to understand what is going on...
Hi, Gemma3 is now the best local model, if Gemma3 could be supported, candle will become even more popular!
I have noticed that this model has outclassed Whisper potentially having an RTF of 1000x https://huggingface.co/nvidia/canary-1b-flash https://huggingface.co/nvidia/canary-180m-flash If this could be portted this, that would be awesome @LaurentMazare
I encountered a need for a learning rate scheduler analogous to the PyTorch `ReduceLROnPlateau` so I rolled my own. I figured others may find it useful as well so made...
I'm a beginner in AI and I'm having some trouble trying to use the models from [firefox-translations-models](https://github.com/mozilla/firefox-translations-models) on candle. The examples at candle-examples/examples/marian-mt are great, but a lot of things...
This pull request introduces the `BertForSequenceClassification` model. It includes two examples to demonstrate its functionality: - A native implementation example. - A WebAssembly (WASM) example, which also supports `ModernBert`. Additionally,...
https://onnx.ai/onnx/operators/onnx__LayerNormalization.html