TomekPro

CoreML to ONNX: ValueError: Unsupported shape calculation for operator multiplyBroadcastable

1

Hi, I'm trying to convert EfficientNet model from CoreML back to ONNX (in order to validate correctness of onnx -> CoreML conversion) ``` # Load a Core ML model coreml_model...

Model inference - performace drop when using unsloth

4

Hi, I fine-tuned a model (yam-peleg/Experiment26-7B) using unsloth. Then during inference, model correctness drops when using unsloath FastLanguageModel. I see some modules are replaced. It looks a little bit weird...

Hi, are the any plans to add a support for GGUF export for CPU inference? Or is there any other way to inference AWQ quantized model on CPU? Thanks Tomek