Update README.md (#2)

- Update README.md (177d8fd1827f7b799c2ee5d6f1e19ee533dc0cb5)
- Update README.md (6a8bc56c3b3fa3140058e5f18b9baa30d3dd06a6)


Co-authored-by: Adam Stachowicz <astachowicz@users.noreply.huggingface.co>

README.md

@@ -25,9 +25,9 @@ It is strongly recommended to train this model doing bf16 mixed-precision traini
 
 [Here](https://github.com/huggingface/optimum-habana/blob/main/examples/question-answering/run_qa.py) is a question-answering example script to fine-tune a model on SQuAD. You can run it with BERT Large with the following command:
 ```bash
-python run_qa.py \
+PT_HPU_LAZY_MODE=0 python run_qa.py \
   --model_name_or_path bert-large-uncased-whole-word-masking \
-  --gaudi_config_name gaudi_config_name_or_path \
+  --gaudi_config_name Habana/bert-large-uncased-whole-word-masking \
   --dataset_name squad \
   --do_train \
   --do_eval \
@@ -39,7 +39,9 @@ python run_qa.py \
   --doc_stride 128 \
   --output_dir /tmp/squad/ \
   --use_habana \
-  --use_lazy_mode \
+  --torch_compile_backend hpu_backend \
+  --torch_compile \
+  --use_lazy_mode false \
   --throughput_warmup_steps 3 \
   --bf16
 ```