Merge from main branch and update code style

Signed-off-by: Cheng, Penghui <penghui.cheng@intel.com>

Author: PenghuiCheng

.github/workflows/test_openvino_examples.yml

@@ -0,0 +1,46 @@
+name: OpenVINO - Examples Test
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: 0 1 * * 1  # run weekly: every Monday at 1am
+  push:
+    paths:
+    - '.github/workflows/test_openvino_examples.yml'
+    - 'examples/openvino/*'
+  pull_request:
+    paths:
+    - '.github/workflows/test_openvino_examples.yml'
+    - 'examples/openvino/*'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  build:
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.8", "3.10"]
+
+    runs-on: ubuntu-20.04
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Setup Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install dependencies
+      run: |
+        pip install optimum[openvino] jstyleson nncf pytest
+        pip install -r examples/openvino/audio-classification/requirements.txt
+        pip install -r examples/openvino/image-classification/requirements.txt
+        pip install -r examples/openvino/question-answering/requirements.txt
+        pip install -r examples/openvino/text-classification/requirements.txt
+
+    - name: Test examples
+      run: |
+        python -m pytest examples/openvino/test_examples.py

Makefile

@@ -22,11 +22,11 @@ REAL_CLONE_URL = $(if $(CLONE_URL),$(CLONE_URL),$(DEFAULT_CLONE_URL))
 # Run code quality checks
 style_check:
 	black --check .
-	ruff .
+	ruff check .
 
 style:
 	black .
-	ruff . --fix
+	ruff check . --fix
 
 # Run tests for the library
 test:

README.md

@@ -202,6 +202,26 @@ Quantization aware training (QAT) is applied in order to simulate the effects of
 You can find more examples in the [documentation](https://huggingface.co/docs/optimum/intel/index).
 
 
+## IPEX
+To load your IPEX model, you can just replace your `AutoModelForXxx` class with the corresponding `IPEXModelForXxx` class. You can set `export=True` to load a PyTorch checkpoint, export your model via TorchScript and apply IPEX optimizations : both operators optimization (replaced with customized IPEX operators) and graph-level optimization (like operators fusion) will be applied on your model.
+```diff
+  from transformers import AutoTokenizer, pipeline
+- from transformers import AutoModelForCausalLM
++ from optimum.intel import IPEXModelForCausalLM
+
+
+  model_id = "gpt2"
+- model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16)
++ model = IPEXModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, export=True)
+  tokenizer = AutoTokenizer.from_pretrained(model_id)
+  pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+  results = pipe("He's a dreadful magician and")
+
+```
+
+For more details, please refer to the [documentation](https://intel.github.io/intel-extension-for-pytorch/#introduction).
+
+
 ## Running the examples
 
 Check out the [`examples`](https://github.com/huggingface/optimum-intel/tree/main/examples) directory to see how 🤗 Optimum Intel can be used to optimize models and accelerate inference.

examples/neural_compressor/language-modeling/run_clm.py

@@ -228,15 +228,18 @@ class OptimizationArguments:
         metadata={"help": "Quantization methodology for weight only quantization. Choose from 'RTN' and 'GPTQ'."},
     )
     damp_percent: float = field(
-
         default=0.01,
-        metadata={"help": "Percentage of Hessian's diagonal values average, which will be added to Hessian's diagonal to increase numerical stability, used for GPTQ quantization"},
+        metadata={
+            "help": "Percentage of Hessian's diagonal values average, which will be added to Hessian's diagonal to increase numerical stability, used for GPTQ quantization"
+        },
     )
     gptq_block_size: int = field(
         default=128,
         metadata={"help": "Block size. sub weight matrix size to run GPTQ."},
     )
-    num_calibration_samples: int = field(default=128, metadata={"help": "Number of examples to use for the GPTQ calibration step."})
+    num_calibration_samples: int = field(
+        default=128, metadata={"help": "Number of examples to use for the GPTQ calibration step."}
+    )
     use_max_length: bool = field(
         default=False,
         metadata={"help": "Set all sequence length to be same length of args.gptq_pad_max_length"},