Update README.md

README.md

@@ -24,7 +24,7 @@ We provide the [quantized pte](https://huggingface.co/pytorch/Phi-4-mini-instruc
 (The provided pte file is exported with at max_seq_length/max_context_length of 1024; if you wish to change this, re-export the quantized model following the instructions in [Exporting to ExecuTorch](#exporting-to-executorch).)  
 
 # Running in a mobile app
-The [pte file](https://huggingface.co/pytorch/Phi-4-mini-instruct-INT8-INT4/blob/main/phi4-mini-INT8-INT4.pte) can be run with ExecuTorch on a mobile phone.  See the [instructions](https://pytorch.org/executorch/main/llm/llama-demo-ios.html) for doing this in iOS.
+The [pte file](https://huggingface.co/pytorch/Phi-4-mini-instruct-INT8-INT4/blob/main/model.pte) can be run with ExecuTorch on a mobile phone.  See the [instructions](https://pytorch.org/executorch/main/llm/llama-demo-ios.html) for doing this in iOS.
 On iPhone 15 Pro, the model runs at 17.3 tokens/sec and uses 3206 Mb of memory.
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/66049fc71116cebd1d3bdcf4/521rXwIlYS9HIAEBAPJjw.png)
@@ -120,10 +120,10 @@ linear_config = Int8DynamicActivationIntxWeightConfig(
     weight_scale_dtype=torch.bfloat16,
 )
 quant_config = ModuleFqnToConfig({"_default": linear_config, "model.embed_tokens": embedding_config})
-quantization_config = TorchAoConfig(quant_type=quant_config, include_embedding=True, untie_embedding_weights=True, modules_to_not_convert=[])
+quantization_config = TorchAoConfig(quant_type=quant_config, include_input_output_embeddings=True, modules_to_not_convert=[])
 
 # either use `untied_model_id` or `untied_model_local_path`
-quantized_model = AutoModelForCausalLM.from_pretrained(untied_model_id, torch_dtype=torch.float32, device_map="auto", quantization_config=quantization_config)
+quantized_model = AutoModelForCausalLM.from_pretrained(untied_model_id, device_map="auto", torch_dtype=torch.bfloat16, quantization_config=quantization_config)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 # Push to hub
@@ -212,15 +212,15 @@ lm_eval --model hf --model_args pretrained=pytorch/Phi-4-mini-instruct-INT8-INT4
 We can run the quantized model on a mobile phone using [ExecuTorch](https://github.com/pytorch/executorch).
 Once ExecuTorch is [set-up](https://pytorch.org/executorch/main/getting-started.html), exporting and running the model on device is a breeze.
 
-We first convert the [quantized checkpoint](https://huggingface.co/pytorch/Phi-4-mini-instruct-INT8-INT4/blob/main/pytorch_model.bin) to one ExecuTorch's LLM export script expects by renaming some of the checkpoint keys.
-The following script does this for you.
+ExecuTorch's LLM export scripts require the checkpoint keys and parameters have certain names, which differ from those used in Hugging Face.
+So we first use a conversion script that converts the Hugging Face checkpoint key names to ones that ExecuTorch expects:
 ```Shell
-HF_MODEL_DIR=$(hf download pytorch/Phi-4-mini-instruct-INT8-INT4)
-python -m executorch.examples.models.phi_4_mini.convert_weights $HF_MODEL_DIR pytorch_model_converted.bin
+python -m executorch.examples.models.phi_4_mini.convert_weights $(hf download pytorch/Phi-4-mini-instruct-INT8-INT4) pytorch_model_converted.bin
 ```
 
-Once the checkpoint is converted, we can export to ExecuTorch's pte format with the XNNPACK delegate.
-The below command exports with a max_seq_length/max_context_length of 1024, but it can be changed as desired.
+Once we have the checkpoint, we export it to ExecuTorch with the XNNPACK backend as follows with a max_seq_length/max_context_length of 1024.
+
+(Note: ExecuTorch LLM export script requires config.json have certain key names. The correct config to use for the LLM export script is located at examples/models/phi_4_mini/config/config.json within the ExecuTorch repo.)
 
 ```Shell
 python-m executorch.examples.models.llama.export_llama \