Mengwei Liu

Hello you don't need to process `tokenizer.model` you can just feed it into this step: https://github.com/pytorch/executorch/blob/main/examples/models/llama2/README.md#step-4-run-on-your-computer-to-validate

I can't repro the error. Though the documentation needs some update for sure. Let me update it and we can close this issue.

@Gasoonjia Do you mind taking this one?

Yeah pretty much we have to build quantized lib and link it into compiler. Similar to here https://github.com/pytorch/executorch/blob/main/examples/portable/custom_ops/test_custom_ops.sh#L101

This is awesome! It seems this PR includes all the changes in https://github.com/pytorch/executorch/pull/4574?

> @larryliu0820 could you help review this PR? I'd like to consolidate to one 🤗 `transformers` versions for ET. That will make future model enablement and benchmarking much easier Can...

Hi @jhetuts thanks for providing feedback! Can you give a specific example on what quantized llm you are referring to? For llama3.1 we have a few quantization options and you...

> The required work for OSS is probably creating a cmake target similar to this buck one: > > [executorch/backends/apple/coreml/TARGETS](https://github.com/pytorch/executorch/blob/bf272de13f936628c895d4723d07f3296ace0366/backends/apple/coreml/TARGETS#L61) > > Line 61 in [bf272de](/pytorch/executorch/commit/bf272de13f936628c895d4723d07f3296ace0366) > > runtime.cxx_python_extension( Thanks...

@msaroufim I wanted to raise this issue earlier but it slipped - what is the best way to install ao nightly on mac? It doesn't look like there's a nightly...

@Gasoonjia please help merge this