workaround issue with weights loading in 8bit in optimum notebooks

openvinotoolkit · Dec 26, 2023 · ffd83bc · ffd83bc
1 parent c6a92b2
commit ffd83bc
Show file tree

Hide file tree

Showing 19 changed files with 69 additions and 934 deletions.
diff --git a/notebooks/116-sparsity-optimization/116-sparsity-optimization.ipynb b/notebooks/116-sparsity-optimization/116-sparsity-optimization.ipynb
@@ -52,7 +52,7 @@
    "outputs": [],
    "source": [
     "%pip install -q \"openvino>=2023.1.0\"\n",
-    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git\" datasets onnx transformers>=4.33.0 --extra-index-url https://download.pytorch.org/whl/cpu"
+    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\" datasets onnx transformers>=4.33.0 --extra-index-url https://download.pytorch.org/whl/cpu"
    ]
   },
   {

diff --git a/notebooks/124-hugging-face-hub/124-hugging-face-hub.ipynb b/notebooks/124-hugging-face-hub/124-hugging-face-hub.ipynb
@@ -335,7 +335,7 @@
     }
    ],
    "source": [
-    "%pip install -q \"optimum-intel\"@git+https://github.com/huggingface/optimum-intel.git onnx"
+    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\" onnx"
    ]
   },
   {
@@ -428,7 +428,6 @@
    "source": [
     "### Convert model using Optimum CLI interface\n",
     "[back to top ⬆️](#Table-of-contents:)\n",
-    "",
     "\n",
     "Alternatively, you can use the Optimum CLI interface for converting models (supported starting optimum-intel 1.12 version).\n",
     "General command format:\n",
@@ -665,43 +664,12 @@
   },
   "widgets": {
    "application/vnd.jupyter.widget-state+json": {
-    "state": {
-     "076e75b32a964983a4a6df36c1c3d1e0": {
-      "model_module": "@jupyter-widgets/controls",
-      "model_module_version": "2.0.0",
-      "model_name": "DropdownModel",
-      "state": {
-       "_options_labels": [
-        "CPU",
-        "GPU",
-        "AUTO"
-       ],
-       "description": "Device:",
-       "index": 2,
-       "layout": "IPY_MODEL_6b2f876d11c646609ac313f511c02e54",
-       "style": "IPY_MODEL_afbbe0593d5f41fb8538ae616adaf924"
-      }
-     },
-     "6b2f876d11c646609ac313f511c02e54": {
-      "model_module": "@jupyter-widgets/base",
-      "model_module_version": "2.0.0",
-      "model_name": "LayoutModel",
-      "state": {}
-     },
-     "afbbe0593d5f41fb8538ae616adaf924": {
-      "model_module": "@jupyter-widgets/controls",
-      "model_module_version": "2.0.0",
-      "model_name": "DescriptionStyleModel",
-      "state": {
-       "description_width": ""
-      }
-     }
-    },
+    "state": {},
     "version_major": 2,
     "version_minor": 0
    }
   }
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}
diff --git a/notebooks/214-grammar-correction/214-grammar-correction.ipynb b/notebooks/214-grammar-correction/214-grammar-correction.ipynb
@@ -98,7 +98,7 @@
     }
    ],
    "source": [
-    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git\" \"openvino>=2023.1.0\" onnx gradio \"transformers>=4.33.0\" --extra-index-url https://download.pytorch.org/whl/cpu\n",
+    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\" \"openvino>=2023.1.0\" onnx gradio \"transformers>=4.33.0\" --extra-index-url https://download.pytorch.org/whl/cpu\n",
     "%pip install -q \"nncf>=2.7.0\" datasets jiwer"
    ]
   },
@@ -284,7 +284,7 @@
     "if grammar_checker_dir.exists():\n",
     "    grammar_checker_model = OVModelForSequenceClassification.from_pretrained(grammar_checker_dir, device=device.value)\n",
     "else:\n",
-    "    grammar_checker_model = OVModelForSequenceClassification.from_pretrained(grammar_checker_model_id, export=True, device=device.value)\n",
+    "    grammar_checker_model = OVModelForSequenceClassification.from_pretrained(grammar_checker_model_id, export=True, device=device.value, load_in_8bit=False)\n",
     "    grammar_checker_model.save_pretrained(grammar_checker_dir)"
    ]
   },

diff --git a/notebooks/236-stable-diffusion-v2/236-stable-diffusion-v2-optimum-demo-comparison.ipynb b/notebooks/236-stable-diffusion-v2/236-stable-diffusion-v2-optimum-demo-comparison.ipynb
@@ -35,7 +35,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -q \"optimum-intel[openvino,diffusers]@git+https://github.com/huggingface/optimum-intel.git\" \"ipywidgets\" \"transformers>=4.33.0\" --extra-index-url https://download.pytorch.org/whl/cpu"
+    "%pip install -q \"optimum-intel[openvino,diffusers]@git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\" \"ipywidgets\" \"transformers>=4.33.0\" --extra-index-url https://download.pytorch.org/whl/cpu"
    ]
   },
   {
@@ -412,4 +412,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}
diff --git a/notebooks/236-stable-diffusion-v2/236-stable-diffusion-v2-optimum-demo.ipynb b/notebooks/236-stable-diffusion-v2/236-stable-diffusion-v2-optimum-demo.ipynb
@@ -41,7 +41,7 @@
     }
    ],
    "source": [
-    "%pip install -q \"optimum-intel[openvino,diffusers]@git+https://github.com/huggingface/optimum-intel.git\" \"ipywidgets\" \"transformers>=4.33\" --extra-index-url https://download.pytorch.org/whl/cpu"
+    "%pip install -q \"optimum-intel[openvino,diffusers]@git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\" \"ipywidgets\" \"transformers>=4.33\" --extra-index-url https://download.pytorch.org/whl/cpu"
    ]
   },
   {
@@ -345,4 +345,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}
diff --git a/notebooks/240-dolly-2-instruction-following/240-dolly-2-instruction-following.ipynb b/notebooks/240-dolly-2-instruction-following/240-dolly-2-instruction-following.ipynb
@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "ef2ed242-3561-464c-8d1c-cc3862e23702",
    "metadata": {},
@@ -32,6 +33,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "f97c435a",
    "metadata": {},
@@ -51,6 +53,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "08aa16b1-d2f6-4a3a-abfb-5ec278133c80",
    "metadata": {},
@@ -69,11 +72,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -q \"diffusers>=0.16.1\" \"transformers>=4.33.0\" \"openvino>=2023.2.0\" \"nncf>=2.6.0\" datasets onnx gradio --extra-index-url https://download.pytorch.org/whl/cpu\n",
-    "%pip install -q --upgrade \"git+https://github.com/huggingface/optimum-intel.git\" "
+    "%pip install -q \"diffusers>=0.16.1\" \"transformers>=4.33.0\" \"openvino>=2023.2.0\" \"nncf>=2.6.0\" onnx gradio --extra-index-url https://download.pytorch.org/whl/cpu\n",
+    "%pip install -q --upgrade \"git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\" "
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "367f84f8-33e8-4ad6-bd40-e6fd41d2d703",
    "metadata": {},
@@ -123,6 +127,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "93fec698-344d-48aa-8899-6821bf3e16bf",
    "metadata": {},
@@ -199,6 +204,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "5b1238c8-dcc9-4495-aeff-1ecbd8bd5082",
    "metadata": {},
@@ -296,6 +302,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "b6d9c4a5-ef75-4076-9f1c-f45a2259ec46",
    "metadata": {},
@@ -338,6 +345,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "b9b5da4d-d2fd-440b-b204-7fbc6966dd1f",
    "metadata": {},
@@ -362,6 +370,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "c58611d6-0a91-4efd-976e-4221acbb43cd",
    "metadata": {},
@@ -403,6 +412,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "27a01739-1363-42ef-927f-6a340bdbe7ba",
    "metadata": {},
@@ -454,6 +464,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "583202d2-6d29-4729-af2e-232d3ee0bc2c",
    "metadata": {},
@@ -524,6 +535,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "562f2dcf-75ef-4554-85e3-e04f486776cc",
    "metadata": {},
@@ -600,6 +612,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "50d918a9-1cbe-49a5-85ad-5e370c8af7f5",
    "metadata": {},
@@ -716,64 +729,7 @@
   },
   "widgets": {
    "application/vnd.jupyter.widget-state+json": {
-    "state": {
-     "2103f879d27c4e3398d099b0e053104f": {
-      "model_module": "@jupyter-widgets/controls",
-      "model_module_version": "2.0.0",
-      "model_name": "DescriptionStyleModel",
-      "state": {
-       "description_width": ""
-      }
-     },
-     "21ad65086ed34572ab6917206e71df50": {
-      "model_module": "@jupyter-widgets/controls",
-      "model_module_version": "2.0.0",
-      "model_name": "CheckboxModel",
-      "state": {
-       "description": "INT8 Compression",
-       "disabled": false,
-       "layout": "IPY_MODEL_c9a3e76301244505947a6863da7adb73",
-       "style": "IPY_MODEL_cb768e1a46314d8e9cb45d0c96280edc",
-       "value": true
-      }
-     },
-     "8bf68d1542064c918ed7f29ce76f442e": {
-      "model_module": "@jupyter-widgets/controls",
-      "model_module_version": "2.0.0",
-      "model_name": "DropdownModel",
-      "state": {
-       "_options_labels": [
-        "CPU",
-        "GPU",
-        "AUTO"
-       ],
-       "description": "Device:",
-       "index": 0,
-       "layout": "IPY_MODEL_ccc2b51fc350449d9e8abe13ccd03ed6",
-       "style": "IPY_MODEL_2103f879d27c4e3398d099b0e053104f"
-      }
-     },
-     "c9a3e76301244505947a6863da7adb73": {
-      "model_module": "@jupyter-widgets/base",
-      "model_module_version": "2.0.0",
-      "model_name": "LayoutModel",
-      "state": {}
-     },
-     "cb768e1a46314d8e9cb45d0c96280edc": {
-      "model_module": "@jupyter-widgets/controls",
-      "model_module_version": "2.0.0",
-      "model_name": "CheckboxStyleModel",
-      "state": {
-       "description_width": ""
-      }
-     },
-     "ccc2b51fc350449d9e8abe13ccd03ed6": {
-      "model_module": "@jupyter-widgets/base",
-      "model_module_version": "2.0.0",
-      "model_name": "LayoutModel",
-      "state": {}
-     }
-    },
+    "state": {},
     "version_major": 2,
     "version_minor": 0
    }

diff --git a/notebooks/241-riffusion-text-to-music/241-riffusion-text-to-music.ipynb b/notebooks/241-riffusion-text-to-music/241-riffusion-text-to-music.ipynb
@@ -68,7 +68,7 @@
    "outputs": [],
    "source": [
     "%pip install -q --extra-index-url https://download.pytorch.org/whl/cpu torch torchaudio \"diffusers>=0.16.1\" \"transformers>=4.33.0\"\n",
-    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git\" onnx \"gradio>=3.34.0\" \"openvino>=2023.1.0\""
+    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\" onnx \"gradio>=3.34.0\" \"openvino>=2023.1.0\""
    ]
   },
   {

diff --git a/notebooks/244-named-entity-recognition/244-named-entity-recognition.ipynb b/notebooks/244-named-entity-recognition/244-named-entity-recognition.ipynb
@@ -41,7 +41,7 @@
    "outputs": [],
    "source": [
     "%pip install -q \"diffusers>=0.17.1\" \"openvino>=2023.1.0\" \"nncf>=2.5.0\" \"gradio\" \"onnx>=1.11.0\" \"transformers>=4.33.0\" --extra-index-url https://download.pytorch.org/whl/cpu\n",
-    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git\""
+    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\""
    ]
   },
   {
@@ -217,7 +217,6 @@
    "source": [
     "## Compare the Original and Quantized Models\n",
     "[back to top ⬆️](#Table-of-contents:)\n",
-    "",
     "\n",
     "Compare the original [`distilbert-base-cased-finetuned-conll03-english`](https://huggingface.co/elastic/distilbert-base-cased-finetuned-conll03-english) model with quantized and converted to OpenVINO IR format models to see the difference."
    ]
@@ -228,7 +227,6 @@
    "source": [
     "### Compare performance\n",
     "[back to top ⬆️](#Table-of-contents:)\n",
-    "",
     "\n",
     "As the Optimum Inference models are API compatible with Hugging Face Transformers models, we can just use `pipleine()` from [Hugging Face Transformers API](https://huggingface.co/docs/transformers/index) for inference."
    ]
@@ -324,7 +322,6 @@
    "source": [
     "## Prepare demo for Named Entity Recognition OpenVINO Runtime\n",
     "[back to top ⬆️](#Table-of-contents:)\n",
-    "",
     "\n",
     "Now, you can try NER model on own text. Put your sentence to input text box, click Submit button, the model label the recognized entities in the text."
    ]
@@ -401,4 +398,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}
diff --git a/notebooks/245-typo-detector/245-typo-detector.ipynb b/notebooks/245-typo-detector/245-typo-detector.ipynb
@@ -51,7 +51,7 @@
    "outputs": [],
    "source": [
     "%pip install -q \"diffusers>=0.17.1\" \"openvino>=2023.1.0\" \"nncf>=2.5.0\" \"gradio\" \"onnx>=1.11.0\" \"transformers>=4.33.0\" --extra-index-url https://download.pytorch.org/whl/cpu\n",
-    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git\""
+    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\""
    ]
   },
   {

diff --git a/notebooks/247-code-language-id/247-code-language-id.ipynb b/notebooks/247-code-language-id/247-code-language-id.ipynb
@@ -104,7 +104,7 @@
    "outputs": [],
    "source": [
     "%pip install -q \"diffusers>=0.17.1\" \"openvino>=2023.1.0\" \"nncf>=2.5.0\" \"gradio\" \"onnx>=1.11.0\" \"transformers>=4.33.0\" \"evaluate\" --extra-index-url https://download.pytorch.org/whl/cpu\n",
-    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git\""
+    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\""
    ]
   },
   {

diff --git a/notebooks/248-stable-diffusion-xl/248-segmind-vegart.ipynb b/notebooks/248-stable-diffusion-xl/248-segmind-vegart.ipynb
@@ -35,7 +35,7 @@
    "source": [
     "%pip uninstall -q -y openvino-dev openvino openvino-nightly\n",
     "%pip install -q --extra-index-url https://download.pytorch.org/whl/cpu\\\n",
-    "torch transformers diffusers \"git+https://github.com/huggingface/optimum-intel.git\" gradio openvino-nightly"
+    "torch transformers diffusers \"git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\" gradio openvino-nightly"
    ]
   },
   {

diff --git a/notebooks/248-stable-diffusion-xl/248-ssd-b1.ipynb b/notebooks/248-stable-diffusion-xl/248-ssd-b1.ipynb
@@ -73,7 +73,7 @@
    },
    "outputs": [],
    "source": [
-    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git\"\n",
+    "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\"\n",
     "%pip install -q \"openvino>=2023.1.0\"\n",
     "%pip install -q --upgrade-strategy eager \"invisible-watermark>=0.2.0\" \"transformers>=4.33\" \"accelerate\" \"onnx\" \"onnxruntime\" safetensors \"diffusers>=0.22.0\"\n",
     "%pip install -q gradio"
@@ -210,7 +210,7 @@
     "\n",
     "\n",
     "if not model_dir.exists():\n",
-    "    text2image_pipe = OVStableDiffusionXLPipeline.from_pretrained(model_id, compile=False, device=device.value, export=True)\n",
+    "    text2image_pipe = OVStableDiffusionXLPipeline.from_pretrained(model_id, compile=False, device=device.value, export=True, load_in_8bit=False)\n",
     "    text2image_pipe.half()\n",
     "    text2image_pipe.save_pretrained(model_dir)\n",
     "    text2image_pipe.compile()\n",