diff --git a/notebooks/124-hugging-face-hub/124-hugging-face-hub.ipynb b/notebooks/124-hugging-face-hub/124-hugging-face-hub.ipynb index 2d2035adf73..b1cae68b185 100644 --- 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", @@ -665,38 +664,7 @@ }, "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 } @@ -704,4 +672,4 @@ }, "nbformat": 4, "nbformat_minor": 4 -} \ No newline at end of file +} diff --git a/notebooks/214-grammar-correction/214-grammar-correction.ipynb b/notebooks/214-grammar-correction/214-grammar-correction.ipynb index a9067aa6223..37440b3d756 100644 --- 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 index 9d4e050a208..f569c34d182 100644 --- 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 -} \ No newline at end of file +} 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 index 86d2abcb501..1f474ad3a22 100644 --- 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 -} \ No newline at end of file +} 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 index 0ff7698de5e..2afb006aa98 100644 --- 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 @@ -69,7 +69,7 @@ "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 \"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\" " ] }, @@ -716,64 +716,7 @@ }, "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 index d0750e05ebc..277166f6be2 100644 --- 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 index 12d6318e25c..daaf4f55ade 100644 --- 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 -} \ No newline at end of file +} diff --git a/notebooks/245-typo-detector/245-typo-detector.ipynb b/notebooks/245-typo-detector/245-typo-detector.ipynb index 96fe342dc3e..16af94aa1e7 100644 --- 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 index be123118a73..3feb87fcb4a 100644 --- 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 index a1668f42662..f1e8e0cd04f 100644 --- 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 index cb586dc3408..6fec5359df7 100644 --- 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", diff --git a/notebooks/248-stable-diffusion-xl/248-stable-diffusion-xl.ipynb b/notebooks/248-stable-diffusion-xl/248-stable-diffusion-xl.ipynb index c041984c570..e889a84f83a 100644 --- a/notebooks/248-stable-diffusion-xl/248-stable-diffusion-xl.ipynb +++ b/notebooks/248-stable-diffusion-xl/248-stable-diffusion-xl.ipynb @@ -71,7 +71,7 @@ "outputs": [], "source": [ "%pip install -q --extra-index-url https://download.pytorch.org/whl/cpu \"diffusers>=0.18.0\" \"invisible-watermark>=0.2.0\" \"transformers>=4.33.0\" \"accelerate\" \"onnx\" \n", - "%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\" gradio" ] }, @@ -844,7 +844,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -862,426 +862,7 @@ }, "widgets": { "application/vnd.jupyter.widget-state+json": { - "state": { - "0f29b4daf5b7425d8afc20ae349440e2": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HBoxModel", - "state": { - "children": [ - "IPY_MODEL_a56178b1af7d418b8c3295a6bb9770bf", - "IPY_MODEL_7605fde808194328a32fb6f72c875327", - "IPY_MODEL_a21315af04d745578af22903f36ef300" - ], - "layout": "IPY_MODEL_4cc91cb9f2714862941aab3adec7debb" - } - }, - "0fa9654212b649f28d6699872d84c897": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HBoxModel", - "state": { - "children": [ - "IPY_MODEL_932ddee42e3d47a89f8999ab8b06046e", - "IPY_MODEL_d2fd894ccff24e328fbc716962b1690d", - "IPY_MODEL_96b9bc983706487998abd2a971a12527" - ], - "layout": "IPY_MODEL_1c1f0e48df694e788ef74036ce19ea74" - } - }, - "1c1f0e48df694e788ef74036ce19ea74": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "1c37fc5fa1e1467481951a43132061b0": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLModel", - "state": { - "layout": "IPY_MODEL_2c662bd9359a4fffb0e4ed2739073f07", - "style": "IPY_MODEL_528f1b8a99ce44a482616858e6413713", - "value": "100%" - } - }, - "1e3f608093df4576b4816e23b8cec661": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "23670d8cc0ed4358822ca7b66377050a": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "2c662bd9359a4fffb0e4ed2739073f07": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "2c887f5aafc1450086851528c70bf7c7": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLStyleModel", - "state": { - "description_width": "", - "font_size": null, - "text_color": null - } - }, - "362b75c781294e29a31afce9bd148896": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "429028c73ec447578c0034584faea9ac": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "4cc91cb9f2714862941aab3adec7debb": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "50380b1b93f349eaaddc5a1d617fa169": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "DescriptionStyleModel", - "state": { - "description_width": "" - } - }, - "528f1b8a99ce44a482616858e6413713": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLStyleModel", - "state": { - "description_width": "", - "font_size": null, - "text_color": null - } - }, - "5d9402591c1849b585334096148e1a2a": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLModel", - "state": { - "layout": "IPY_MODEL_23670d8cc0ed4358822ca7b66377050a", - "style": "IPY_MODEL_c1b3ff600c5a43aa95d3935852f1ff53", - "value": "100%" - } - }, - "5eec6d73d0134f4da1fdb297739c9160": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "ProgressStyleModel", - "state": { - "description_width": "" - } - }, - "6976c606ade949a9b88c7e362134de17": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "72a1be20e9e847bb91afa6c13df2588f": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLStyleModel", - "state": { - "description_width": "", - "font_size": null, - "text_color": null - } - }, - "7605fde808194328a32fb6f72c875327": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "FloatProgressModel", - "state": { - "bar_style": "success", - "layout": "IPY_MODEL_6976c606ade949a9b88c7e362134de17", - "max": 15, - "style": "IPY_MODEL_9a020b1ba9af4cf5ab85e6916c14561e", - "value": 15 - } - }, - "86f6ecbc7a6f40a78f82bbc49fd3f605": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "8cb8b11f71f447dba57f35994bc8be14": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLModel", - "state": { - "layout": "IPY_MODEL_b5728c2fbaff4b5289fc67afdafb4be7", - "style": "IPY_MODEL_72a1be20e9e847bb91afa6c13df2588f", - "value": " 4/4 [00:10<00:00, 2.53s/it]" - } - }, - "932ddee42e3d47a89f8999ab8b06046e": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLModel", - "state": { - "layout": "IPY_MODEL_86f6ecbc7a6f40a78f82bbc49fd3f605", - "style": "IPY_MODEL_2c887f5aafc1450086851528c70bf7c7", - "value": "100%" - } - }, - "93b04d58e7094ae8be3df5ae99662058": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "FloatProgressModel", - "state": { - "bar_style": "success", - "layout": "IPY_MODEL_429028c73ec447578c0034584faea9ac", - "max": 4, - "style": "IPY_MODEL_5eec6d73d0134f4da1fdb297739c9160", - "value": 4 - } - }, - "96b9bc983706487998abd2a971a12527": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLModel", - "state": { - "layout": "IPY_MODEL_362b75c781294e29a31afce9bd148896", - "style": "IPY_MODEL_d5a7d855986f4b58be19550219a72e66", - "value": " 15/15 [00:32<00:00, 2.08s/it]" - } - }, - "98698ed2082a4906917b86a1bc1cbc81": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "98f0c18b5585455e8f7d72822ca6b1c7": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "9a020b1ba9af4cf5ab85e6916c14561e": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "ProgressStyleModel", - "state": { - "description_width": "" - } - }, - "9b8006e89d954c458763c7a568a2058b": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLModel", - "state": { - "layout": "IPY_MODEL_c75cbaaf31704cdb815a96373f5e189b", - "style": "IPY_MODEL_f9ca18e2d7854f0dbeae0db4b3e69dcb", - "value": " 7/7 [00:16<00:00, 2.26s/it]" - } - }, - "a21315af04d745578af22903f36ef300": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLModel", - "state": { - "layout": "IPY_MODEL_d4dff0637b154d7d8c2903e8cf58546f", - "style": "IPY_MODEL_d172fe30adf64f6eafccd0b660c35049", - "value": " 15/15 [00:32<00:00, 2.16s/it]" - } - }, - "a56178b1af7d418b8c3295a6bb9770bf": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLModel", - "state": { - "layout": "IPY_MODEL_ce6ff3481c0445cd953c158c9dc4a2f0", - "style": "IPY_MODEL_e5bc30aba8e142df8e84216b8245ff88", - "value": "100%" - } - }, - "b5728c2fbaff4b5289fc67afdafb4be7": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "b7224544fe6d4ac3a105075d10b26a76": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HBoxModel", - "state": { - "children": [ - "IPY_MODEL_1c37fc5fa1e1467481951a43132061b0", - "IPY_MODEL_cb58175b33ab44ddbaf6b8171691a696", - "IPY_MODEL_9b8006e89d954c458763c7a568a2058b" - ], - "layout": "IPY_MODEL_1e3f608093df4576b4816e23b8cec661" - } - }, - "c1b3ff600c5a43aa95d3935852f1ff53": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLStyleModel", - "state": { - "description_width": "", - "font_size": null, - "text_color": null - } - }, - "c75cbaaf31704cdb815a96373f5e189b": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "cb58175b33ab44ddbaf6b8171691a696": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "FloatProgressModel", - "state": { - "bar_style": "success", - "layout": "IPY_MODEL_cbc42060b3464476a515147494a621d8", - "max": 7, - "style": "IPY_MODEL_e8d143e3a4274680b8ffecfa3ffea761", - "value": 7 - } - }, - "cbc42060b3464476a515147494a621d8": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "ce6ff3481c0445cd953c158c9dc4a2f0": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "d10dbe0ff7a843218fc366e0a9a5f1a4": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "ProgressStyleModel", - "state": { - "description_width": "" - } - }, - "d172fe30adf64f6eafccd0b660c35049": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLStyleModel", - "state": { - "description_width": "", - "font_size": null, - "text_color": null - } - }, - "d2fd894ccff24e328fbc716962b1690d": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "FloatProgressModel", - "state": { - "bar_style": "success", - "layout": "IPY_MODEL_d33882183565419992a0dc9824a6799c", - "max": 15, - "style": "IPY_MODEL_d10dbe0ff7a843218fc366e0a9a5f1a4", - "value": 15 - } - }, - "d33882183565419992a0dc9824a6799c": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "d4dff0637b154d7d8c2903e8cf58546f": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "d5a7d855986f4b58be19550219a72e66": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLStyleModel", - "state": { - "description_width": "", - "font_size": null, - "text_color": null - } - }, - "e5bc30aba8e142df8e84216b8245ff88": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLStyleModel", - "state": { - "description_width": "", - "font_size": null, - "text_color": null - } - }, - "e8d143e3a4274680b8ffecfa3ffea761": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "ProgressStyleModel", - "state": { - "description_width": "" - } - }, - "ea319a86704140e59bfaa6b94b0c06bf": { - "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_98f0c18b5585455e8f7d72822ca6b1c7", - "style": "IPY_MODEL_50380b1b93f349eaaddc5a1d617fa169" - } - }, - "ebeb2f9c343f4f469f8b53c26ed0b6b1": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HBoxModel", - "state": { - "children": [ - "IPY_MODEL_5d9402591c1849b585334096148e1a2a", - "IPY_MODEL_93b04d58e7094ae8be3df5ae99662058", - "IPY_MODEL_8cb8b11f71f447dba57f35994bc8be14" - ], - "layout": "IPY_MODEL_98698ed2082a4906917b86a1bc1cbc81" - } - }, - "f9ca18e2d7854f0dbeae0db4b3e69dcb": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLStyleModel", - "state": { - "description_width": "", - "font_size": null, - "text_color": null - } - } - }, + "state": {}, "version_major": 2, "version_minor": 0 } diff --git a/notebooks/254-llm-chatbot/254-llm-chatbot.ipynb b/notebooks/254-llm-chatbot/254-llm-chatbot.ipynb index 91a3aec6099..e2f5687548a 100644 --- a/notebooks/254-llm-chatbot/254-llm-chatbot.ipynb +++ b/notebooks/254-llm-chatbot/254-llm-chatbot.ipynb @@ -57,7 +57,7 @@ "source": [ "%pip uninstall -q -y openvino-dev openvino openvino-nightly\n", "%pip install -q --extra-index-url https://download.pytorch.org/whl/cpu\\\n", - "\"git+https://github.com/huggingface/optimum-intel.git\"\\\n", + "\"git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\"\\\n", "\"nncf>=2.7\"\\\n", "\"openvino-nightly\"\\\n", "\"gradio\"\\\n", @@ -129,7 +129,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "1e8ca46ac6734f8c816a14cbe46964ce", + "model_id": "f167ed0bf6b34da38b665d880f16f699", "version_major": 2, "version_minor": 0 }, @@ -167,7 +167,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Selected model chatglm3-6b\n" + "Selected model tiny-llama-1b-chat\n" ] } ], @@ -208,7 +208,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 1, "id": "8cd910c2", "metadata": {}, "outputs": [ @@ -216,22 +216,16 @@ "name": "stdout", "output_type": "stream", "text": [ - "INFO:nncf:NNCF initialized successfully. Supported frameworks detected: torch, tensorflow, onnx, openvino\n" + "INFO:nncf:NNCF initialized successfully. Supported frameworks detected: torch, onnx, openvino\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "2023-12-21 21:33:05.855788: I tensorflow/core/util/port.cc:111] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n", - "2023-12-21 21:33:05.857870: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.\n", - "2023-12-21 21:33:05.883126: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n", - "2023-12-21 21:33:05.883147: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n", - "2023-12-21 21:33:05.883167: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n", - "2023-12-21 21:33:05.888388: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.\n", - "2023-12-21 21:33:05.889023: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", - "To enable the following instructions: AVX2 AVX512F AVX512_VNNI AVX512_BF16 AVX_VNNI AMX_TILE AMX_INT8 AMX_BF16 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n", - "2023-12-21 21:33:06.449452: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n" + "/home/ea/work/genai_env/lib/python3.8/site-packages/torch/cuda/__init__.py:138: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 11080). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:108.)\n", + " return torch._C._cuda_getDeviceCount() > 0\n", + "No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda'\n" ] } ], @@ -280,7 +274,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, "id": "91eb2ccf", "metadata": { "collapsed": false, @@ -288,50 +282,7 @@ "outputs_hidden": false } }, - "outputs": [ - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "c802a1fb556c4abdb38b967c02ef3ef6", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "Checkbox(value=True, description='Prepare INT4 model')" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "43b1bd84b5ef4fb0b015411fa3edc862", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "Checkbox(value=False, description='Prepare INT8 model')" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "ec15e0c8aaa54fc080d9d8d8938c233a", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "Checkbox(value=False, description='Prepare FP16 model')" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "from IPython.display import display\n", "\n", @@ -366,7 +317,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": null, "id": "c4ef9112", "metadata": { "collapsed": false, @@ -550,15 +501,19 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 5, "id": "281f1d07-998e-4e13-ba95-0264564ede82", "metadata": {}, "outputs": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - "Size of FP16 model is 11909.69 MB\n" + "ename": "NameError", + "evalue": "name 'fp16_model_dir' is not defined", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[0;32mIn[5], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m fp16_weights \u001b[38;5;241m=\u001b[39m \u001b[43mfp16_model_dir\u001b[49m \u001b[38;5;241m/\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mopenvino_model.bin\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 2\u001b[0m int8_weights \u001b[38;5;241m=\u001b[39m int8_model_dir \u001b[38;5;241m/\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mopenvino_model.bin\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 3\u001b[0m int4_weights \u001b[38;5;241m=\u001b[39m int4_model_dir \u001b[38;5;241m/\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mopenvino_model.bin\u001b[39m\u001b[38;5;124m\"\u001b[39m\n", + "\u001b[0;31mNameError\u001b[0m: name 'fp16_model_dir' is not defined" ] } ], @@ -1255,333 +1210,11 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.7" + "version": "3.8.10" }, "widgets": { "application/vnd.jupyter.widget-state+json": { - "state": { - "00e933d04a98467a97ee0fd5aacd2c93": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "CheckboxModel", - "state": { - "description": "Prepare FP16 model", - "disabled": false, - "layout": "IPY_MODEL_64ad62f21060421aabbd8456c48697d3", - "style": "IPY_MODEL_a39a1b814f3d4fd5b535216f429ae000", - "value": false - } - }, - "0f954bac863d48f5ab0b9eb779f0a82d": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "DropdownModel", - "state": { - "_options_labels": [ - "INT4", - "FP16" - ], - "description": "Model to run:", - "index": 0, - "layout": "IPY_MODEL_b2994422e6b34af9bff3d3c0cf1f161d", - "style": "IPY_MODEL_a4b7e815e1ab4f808a22dc551e8a6b36" - } - }, - "0feae37e49714d3caf29da081719dc69": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "CheckboxStyleModel", - "state": { - "description_width": "" - } - }, - "107ea5d1ee5e4720b57eee0b12c341f0": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "1f7ebe01ae0f49b3aa26fefe1d2c9630": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "375501ad8742471ca56c5ffcac5ee9f8": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "4910e7d802ec4b2683801e7ac17ca700": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "FloatProgressModel", - "state": { - "bar_style": "success", - "layout": "IPY_MODEL_5778c5124e5641cd88242830477a7ab3", - "max": 7, - "style": "IPY_MODEL_bf691f1d350149d69dff8cf5f08dd9e8", - "value": 7 - } - }, - "4af32a190c7a4896a06743fe05c7b56b": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "DropdownModel", - "state": { - "_options_labels": [ - "CPU", - "GPU.0", - "GPU.1", - "AUTO" - ], - "description": "Device:", - "index": 0, - "layout": "IPY_MODEL_aa16bf7c3b94482295f85dec38155ee1", - "style": "IPY_MODEL_4fdefc6d2c57438380fa16eb0645ab3a" - } - }, - "4fdefc6d2c57438380fa16eb0645ab3a": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "DescriptionStyleModel", - "state": { - "description_width": "" - } - }, - "54390732209e40b18d54807210fd46ce": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "5778c5124e5641cd88242830477a7ab3": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "5ab2c71dcf87422cbde965d6f0661ef0": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLModel", - "state": { - "layout": "IPY_MODEL_1f7ebe01ae0f49b3aa26fefe1d2c9630", - "style": "IPY_MODEL_b469729a7d3140b0b035aaa8e7733186", - "value": " 7/7 [00:08<00:00, 1.13s/it]" - } - }, - "64ad62f21060421aabbd8456c48697d3": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "7723267ce24448fcbe4658b6e20cd404": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "DropdownModel", - "state": { - "_options_labels": [ - "tiny-llama-1b-chat", - "red-pajama-3b-chat", - "llama-2-chat-7b", - "mpt-7b-chat", - "qwen-7b-chat", - "chatglm2-6b", - "mistal-7b", - "zephyr-7b-beta", - "neural-chat-7b-v3-1", - "notus-7b-v1", - "youri-7b-chat" - ], - "description": "Model:", - "index": 5, - "layout": "IPY_MODEL_375501ad8742471ca56c5ffcac5ee9f8", - "style": "IPY_MODEL_f62810db78ab4b4ba44f59e98baf7333" - } - }, - "86350f1ebcba4f22a502ef4e6419fb69": { - "model_module": "@jupyter-widgets/output", - "model_module_version": "1.0.0", - "model_name": "OutputModel", - "state": { - "layout": "IPY_MODEL_107ea5d1ee5e4720b57eee0b12c341f0", - "outputs": [ - { - "data": { - "text/html": "
Searching for Mixed-Precision Configuration ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 112/112 • 0:04:36 • 0:00:00\n
\n", - "text/plain": "Searching for Mixed-Precision Configuration \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[35m100%\u001b[0m \u001b[38;2;0;104;181m112/112\u001b[0m • \u001b[38;2;0;104;181m0:04:36\u001b[0m • \u001b[38;2;0;104;181m0:00:00\u001b[0m\n" - }, - "metadata": {}, - "output_type": "display_data" - } - ] - } - }, - "9ad05ac3909b405582d93594f549fd94": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "CheckboxModel", - "state": { - "description": "Prepare INT4 model", - "disabled": false, - "layout": "IPY_MODEL_54390732209e40b18d54807210fd46ce", - "style": "IPY_MODEL_0feae37e49714d3caf29da081719dc69", - "value": true - } - }, - "9df482a97a8c48048c1b14d023c192be": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLModel", - "state": { - "layout": "IPY_MODEL_fe514aa9268c40d79cbcce1266bc47c9", - "style": "IPY_MODEL_e19a4ef87232458081076551a2f030b2", - "value": "Loading checkpoint shards: 100%" - } - }, - "a39a1b814f3d4fd5b535216f429ae000": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "CheckboxStyleModel", - "state": { - "description_width": "" - } - }, - "a4b7e815e1ab4f808a22dc551e8a6b36": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "DescriptionStyleModel", - "state": { - "description_width": "" - } - }, - "aa16bf7c3b94482295f85dec38155ee1": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "b2994422e6b34af9bff3d3c0cf1f161d": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "b469729a7d3140b0b035aaa8e7733186": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLStyleModel", - "state": { - "description_width": "", - "font_size": null, - "text_color": null - } - }, - "bba76ebbf6d741fcbc92b3a210464899": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HBoxModel", - "state": { - "children": [ - "IPY_MODEL_9df482a97a8c48048c1b14d023c192be", - "IPY_MODEL_4910e7d802ec4b2683801e7ac17ca700", - "IPY_MODEL_5ab2c71dcf87422cbde965d6f0661ef0" - ], - "layout": "IPY_MODEL_eeb37297a8f94696bd754a96f0057b12" - } - }, - "bc30bb99906245b18e4c752439fe8f03": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "CheckboxStyleModel", - "state": { - "description_width": "" - } - }, - "bf691f1d350149d69dff8cf5f08dd9e8": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "ProgressStyleModel", - "state": { - "description_width": "" - } - }, - "dda49cfd9dd04af69ba91d10f8e4e175": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "e19a4ef87232458081076551a2f030b2": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "HTMLStyleModel", - "state": { - "description_width": "", - "font_size": null, - "text_color": null - } - }, - "eeb37297a8f94696bd754a96f0057b12": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "f1d5bbc922ce40d6885cb8ee7f6f9e50": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "f486dd77a1a04c8295a25d2df0cd3f3f": { - "model_module": "@jupyter-widgets/output", - "model_module_version": "1.0.0", - "model_name": "OutputModel", - "state": { - "layout": "IPY_MODEL_dda49cfd9dd04af69ba91d10f8e4e175", - "outputs": [ - { - "data": { - "text/html": "
Applying Weight Compression ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 114/114 • 0:06:09 • 0:00:00\n
\n", - "text/plain": "Applying Weight Compression \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[35m100%\u001b[0m \u001b[38;2;0;104;181m114/114\u001b[0m • \u001b[38;2;0;104;181m0:06:09\u001b[0m • \u001b[38;2;0;104;181m0:00:00\u001b[0m\n" - }, - "metadata": {}, - "output_type": "display_data" - } - ] - } - }, - "f62810db78ab4b4ba44f59e98baf7333": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "DescriptionStyleModel", - "state": { - "description_width": "" - } - }, - "fe514aa9268c40d79cbcce1266bc47c9": { - "model_module": "@jupyter-widgets/base", - "model_module_version": "2.0.0", - "model_name": "LayoutModel", - "state": {} - }, - "ff880044976144c1b775423eaa85fcbb": { - "model_module": "@jupyter-widgets/controls", - "model_module_version": "2.0.0", - "model_name": "CheckboxModel", - "state": { - "description": "Prepare INT8 model", - "disabled": false, - "layout": "IPY_MODEL_f1d5bbc922ce40d6885cb8ee7f6f9e50", - "style": "IPY_MODEL_bc30bb99906245b18e4c752439fe8f03", - "value": false - } - } - }, + "state": {}, "version_major": 2, "version_minor": 0 } diff --git a/notebooks/254-llm-chatbot/254-rag-chatbot.ipynb b/notebooks/254-llm-chatbot/254-rag-chatbot.ipynb index f6d1def9712..1c796486010 100644 --- a/notebooks/254-llm-chatbot/254-rag-chatbot.ipynb +++ b/notebooks/254-llm-chatbot/254-rag-chatbot.ipynb @@ -72,7 +72,7 @@ "source": [ "%pip uninstall -q -y openvino-dev openvino openvino-nightly\n", "%pip install -q --extra-index-url https://download.pytorch.org/whl/cpu\\\n", - "\"git+https://github.com/huggingface/optimum-intel.git\"\\\n", + "\"git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\"\\\n", "\"nncf>=2.7\"\\\n", "\"openvino-nightly\"\\\n", "\"gradio\"\\\n", @@ -397,7 +397,7 @@ " return\n", " if not llm_model_configuration[\"remote\"]:\n", " ov_model = OVModelForCausalLM.from_pretrained(\n", - " pt_model_id, export=True, compile=False\n", + " pt_model_id, export=True, compile=False, load_in_8bit=False\n", " )\n", " ov_model.half()\n", " ov_model.save_pretrained(fp16_model_dir)\n", @@ -423,7 +423,7 @@ " int8_model_dir.mkdir(parents=True, exist_ok=True)\n", " if not llm_model_configuration[\"remote\"]:\n", " if fp16_model_dir.exists():\n", - " ov_model = OVModelForCausalLM.from_pretrained(fp16_model_dir, compile=False)\n", + " ov_model = OVModelForCausalLM.from_pretrained(fp16_model_dir, compile=False, load_in_8bit=False)\n", " else:\n", " ov_model = OVModelForCausalLM.from_pretrained(\n", " pt_model_id, export=True, compile=False\n", @@ -507,7 +507,7 @@ " if not llm_model_configuration[\"remote\"]:\n", " if not fp16_model_dir.exists():\n", " model = OVModelForCausalLM.from_pretrained(\n", - " pt_model_id, export=True, compile=False\n", + " pt_model_id, export=True, compile=False, load_in_8bit=False\n", " ).half()\n", " model.config.save_pretrained(int4_model_dir)\n", " ov_model = model._original_model\n", @@ -1452,7 +1452,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.7" + "version": "3.8.10" }, "widgets": { "application/vnd.jupyter.widget-state+json": { diff --git a/notebooks/260-pix2struct-docvqa/260-pix2struct-docvqa.ipynb b/notebooks/260-pix2struct-docvqa/260-pix2struct-docvqa.ipynb index c89ee5b59d8..f31cdf30e25 100644 --- a/notebooks/260-pix2struct-docvqa/260-pix2struct-docvqa.ipynb +++ b/notebooks/260-pix2struct-docvqa/260-pix2struct-docvqa.ipynb @@ -60,7 +60,7 @@ "outputs": [], "source": [ "%pip install -q torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu\n", - "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git\" \"openvino>=2023.1.0\" \"transformers>=4.33.0\" onnx gradio --extra-index-url https://download.pytorch.org/whl/cpu" + "%pip install -q \"git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\" \"openvino>=2023.1.0\" \"transformers>=4.33.0\" onnx gradio --extra-index-url https://download.pytorch.org/whl/cpu" ] }, { diff --git a/notebooks/266-speculative-sampling/266-speculative-sampling.ipynb b/notebooks/266-speculative-sampling/266-speculative-sampling.ipynb index 7b3f93264ab..0f7ce635f13 100644 --- a/notebooks/266-speculative-sampling/266-speculative-sampling.ipynb +++ b/notebooks/266-speculative-sampling/266-speculative-sampling.ipynb @@ -61,7 +61,7 @@ "source": [ "%pip install -q --upgrade pip\n", "%pip install -q --upgrade transformers torch gradio openvino accelerate onnx ipywidgets --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/267-distil-whisper-asr/267-distil-whisper-asr.ipynb b/notebooks/267-distil-whisper-asr/267-distil-whisper-asr.ipynb index 63dc4d4e36e..f7594ae8fa5 100644 --- a/notebooks/267-distil-whisper-asr/267-distil-whisper-asr.ipynb +++ b/notebooks/267-distil-whisper-asr/267-distil-whisper-asr.ipynb @@ -57,7 +57,7 @@ }, "outputs": [], "source": [ - "%pip install -q \"transformers>=4.35\" onnx \"git+https://github.com/huggingface/optimum-intel.git\" --extra-index-url https://download.pytorch.org/whl/cpu\n", + "%pip install -q \"transformers>=4.35\" onnx \"git+https://github.com/huggingface/optimum-intel.git@478ad6985647fd581712aafc0f948da56dbf0f94\" --extra-index-url https://download.pytorch.org/whl/cpu\n", "%pip install -q \"openvino>=2023.2.0\" datasets \"gradio>=4.0\" \"librosa\" \"soundfile\"\n", "%pip install -q \"nncf>=2.6.0\" \"jiwer\"" ] @@ -101,7 +101,7 @@ "\n", "processor = AutoProcessor.from_pretrained(distil_model_id)\n", "\n", - "pt_distil_model = AutoModelForSpeechSeq2Seq.from_pretrained(distil_model_id)\n", + "pt_distil_model = AutoModelForSpeechSeq2Seq.from_pretrained(distil_model_id, load_in_8bit=False)\n", "pt_distil_model.eval();" ] }, diff --git a/notebooks/271-sdxl-turbo/271-sdxl-turbo.ipynb b/notebooks/271-sdxl-turbo/271-sdxl-turbo.ipynb index a4c82a25a8c..3f008e7bfcd 100644 --- a/notebooks/271-sdxl-turbo/271-sdxl-turbo.ipynb +++ b/notebooks/271-sdxl-turbo/271-sdxl-turbo.ipynb @@ -34,7 +34,7 @@ "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" ] }, {