Update llama readme, use main branch for llama3

Summary:
Use main branch for llama3. Looks like the warning was removed in D56358723 ?

See: #3850

Differential Revision: D58212855

Author: lucylq

examples/models/llama2/README.md

@@ -1,5 +1,5 @@
 # Summary
-This example demonstrates how to run a [Llama 2] (https://llama.meta.com/llama2/) 7B or [Llama 3](https://ai.meta.com/llama/) 8B model on mobile via ExecuTorch. We use XNNPACK to accelerate the performance and 4-bit groupwise PTQ quantization to fit the model on a phone.
+This example demonstrates how to run a [Llama 2](https://llama.meta.com/llama2/) 7B or [Llama 3](https://ai.meta.com/llama/) 8B model on mobile via ExecuTorch. We use XNNPACK to accelerate the performance and 4-bit groupwise PTQ quantization to fit the model on a phone.
 
 For more details, see [Llama 2 repo](https://github.com/facebookresearch/llama) or [Llama 3 repo](https://github.com/facebookresearch/llama3).
 
@@ -107,6 +107,7 @@ If you want to deploy and run a smaller model for educational purposes. From `ex
 ### Option C: Download and export Llama 3 8B instruct model
 
 You can export and run the original Llama 3 8B instruct model.
+> :warning: **use the main branch**: Llama 3 is only supported on the ExecuTorch main branch (not release 2.0)
 
 1. Llama 3 pretrained parameters can be downloaded from [Meta's official Llama 3 repository](https://github.com/meta-llama/llama3/).