Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Align optimum quantization calls with the latest API #1935

Merged
merged 1 commit into from
Apr 17, 2024
Merged

Align optimum quantization calls with the latest API #1935

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 4 additions & 3 deletions notebooks/code-language-id/code-language-id.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,7 +165,7 @@
"import evaluate\n",
"from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification\n",
"from optimum.intel import OVModelForSequenceClassification\n",
"from optimum.intel.openvino import OVConfig, OVQuantizer\n",
"from optimum.intel.openvino import OVConfig, OVQuantizer, OVWeightQuantizationConfig\n",
"from huggingface_hub.utils import RepositoryNotFoundError"
]
},
Expand Down Expand Up @@ -559,7 +559,8 @@
"base_model = AutoModelForSequenceClassification.from_pretrained(MODEL_ID)\n",
"\n",
"quantizer = OVQuantizer.from_pretrained(base_model)\n",
"quantization_config = OVConfig()"
"quantization_config = OVWeightQuantizationConfig()\n",
"ov_config = OVConfig(quantization_config=quantization_config)"
]
},
{
Expand Down Expand Up @@ -793,7 +794,7 @@
],
"source": [
"quantizer.quantize(\n",
" quantization_config=quantization_config,\n",
" ov_config=ov_config,\n",
" calibration_dataset=calibration_sample,\n",
" save_directory=QUANTIZED_MODEL_LOCAL_PATH,\n",
")"
Expand Down
5 changes: 3 additions & 2 deletions notebooks/dolly-2-instruction-following/dolly-2-instruction-following.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -288,7 +288,7 @@
],
"source": [
"import gc\n",
"from optimum.intel import OVQuantizer\n",
"from optimum.intel import OVQuantizer, OVConfig, OVWeightQuantizationConfig\n",
"\n",
"compressed_model_path = Path(f\"{model_path}_compressed\")\n",
"\n",
Expand All @@ -304,7 +304,8 @@
"if to_compress.value:\n",
" if not compressed_model_path.exists():\n",
" quantizer = OVQuantizer.from_pretrained(ov_model)\n",
" quantizer.quantize(save_directory=compressed_model_path, weights_only=True)\n",
" ov_config = OVConfig(quantization_config=OVWeightQuantizationConfig(bits=8))\n",
" quantizer.quantize(save_directory=compressed_model_path, ov_config=ov_config)\n",
" del quantizer\n",
" gc.collect()\n",
"\n",
Expand Down
5 changes: 3 additions & 2 deletions notebooks/named-entity-recognition/named-entity-recognition.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -315,7 +315,7 @@
],
"source": [
"from functools import partial\n",
"from optimum.intel import OVQuantizer\n",
"from optimum.intel import OVQuantizer, OVConfig, OVQuantizationConfig\n",
"\n",
"from optimum.intel import OVModelForTokenClassification\n",
"\n",
Expand All @@ -341,10 +341,11 @@
"quantized_ner_model_dir = \"quantized_ner_model\"\n",
"\n",
"# Apply static quantization and save the resulting model in the OpenVINO IR format\n",
"ov_config = OVConfig(quantization_config=OVQuantizationConfig(num_samples=len(calibration_dataset)))\n",
"quantizer.quantize(\n",
" calibration_dataset=calibration_dataset,\n",
" save_directory=quantized_ner_model_dir,\n",
" subset_size=len(calibration_dataset),\n",
" ov_config=ov_config,\n",
")"
]
},
Expand Down
Loading