solume

Is there a temporary solution to this? running into the same issue with openELM, but that doesnt seem to be supported for

It does support the unquantized model, but it breaks when using the quantized model with the same error as above ("Failed: unhandledKeys(base: "Embedding", keys: ["biases", "scales"]), and downgrading doesn't seem...

tested it with mlx-swift fork [mlx-swift fork](https://github.com/ml-explore/mlx-swift/pull/73), this breaks for me with Libraries/LLM/Load.swift:62:13 Cannot find 'quantize' in scope and Libraries/LLM/Qwen2.swift:198:37 Value of type 'Embedding' has no member 'asLinear'

was able to fix dependencies but getting runtime error: `libc++abi: terminating due to uncaught exception of type std::invalid_argument: [matmul] Last dimension of first input with shape (1,42,1280) must match second...