From 2736eaaa189a8b0c84f123af01939b35ab106f4f Mon Sep 17 00:00:00 2001 From: Mengwei Liu Date: Thu, 30 May 2024 17:16:36 -0700 Subject: [PATCH] Update README.md to ask user to double check python env (#3782) Summary: As titled. Reviewed By: tarun292, mcr229 Differential Revision: D57983213 Pulled By: larryliu0820 --- examples/models/llama2/README.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/examples/models/llama2/README.md b/examples/models/llama2/README.md index 21ef5f00fa1..247575817dc 100644 --- a/examples/models/llama2/README.md +++ b/examples/models/llama2/README.md @@ -55,9 +55,12 @@ Llama 2 7B performance was measured on the Samsung Galaxy S22, S24, and OnePlus - For Llama 2 7B, your device may require at least 32GB RAM. If this is a constraint for you, please try the smaller stories model. ## Step 1: Setup +> :warning: **double check your python environment**: make sure `conda activate ` is run before all the bash and python scripts. + 1. Follow the [tutorial](https://pytorch.org/executorch/main/getting-started-setup) to set up ExecuTorch. For installation run `./install_requirements.sh --pybind xnnpack` 2. Run `examples/models/llama2/install_requirements.sh` to install a few dependencies. + ## Step 2: Prepare model ### Option A: Download and export Llama 2 7B model