Spaces:
Running
Running
| title: README | |
| emoji: 🐢 | |
| colorFrom: purple | |
| colorTo: gray | |
| sdk: static | |
| pinned: false | |
| <div class="grid lg:grid-cols-3 gap-x-4 gap-y-7"> | |
| <p class="lg:col-span-3"> | |
| Intel and Hugging Face are building powerful optimization tools to accelerate training and inference with Transformers. | |
| </p> | |
| <a | |
| href="https://huggingface.co/blog/intel" | |
| class="block overflow-hidden group" | |
| > | |
| <div | |
| class="w-full h-40 object-cover mb-10 bg-indigo-100 rounded-lg flex items-center justify-center dark:bg-gray-900 dark:group-hover:bg-gray-850" | |
| > | |
| <img | |
| alt="" | |
| src="https://cdn-media.huggingface.co/marketing/intel-page/Intel-Hugging-Face-alt-version2-org-page.png" | |
| class="w-40" | |
| /> | |
| </div> | |
| <div class="underline">Learn more about Hugging Face collaboration with Intel AI</div> | |
| </a> | |
| <a | |
| href="https://github.com/huggingface/optimum" | |
| class="block overflow-hidden group" | |
| > | |
| <div | |
| class="w-full h-40 object-cover mb-10 bg-indigo-100 rounded-lg flex items-center justify-center dark:bg-gray-900 dark:group-hover:bg-gray-850" | |
| > | |
| <img | |
| alt="" | |
| src="/blog/assets/25_hardware_partners_program/carbon_inc_quantizer.png" | |
| class="w-40" | |
| /> | |
| </div> | |
| <div class="underline">Quantize Transformers with Intel® Neural Compressor and Optimum</div> | |
| </a> | |
| <a href="https://huggingface.co/blog/generative-ai-models-on-intel-cpu" class="block overflow-hidden group"> | |
| <div | |
| class="w-full h-40 object-cover mb-10 bg-indigo-100 rounded-lg flex items-center justify-center dark:bg-gray-900 dark:group-hover:bg-gray-850" | |
| > | |
| <img | |
| alt="" | |
| src="/blog/assets/143_q8chat/thumbnail.png" | |
| class="w-40" | |
| /> | |
| </div> | |
| <div class="underline">Quantizing 7B LLM on Intel CPU</div> | |
| </a> | |
| <div class="lg:col-span-3"> | |
| <p class="mb-2"> | |
| Intel optimizes the most widely adopted and innovative AI software | |
| tools, frameworks, and libraries for Intel® architecture. Whether | |
| you are computing locally or deploying AI applications on a massive | |
| scale, your organization can achieve peak performance with AI | |
| software optimized for Intel® Xeon® Scalable platforms. | |
| </p> | |
| <p class="mb-2"> | |
| Intel’s engineering collaboration with Hugging Face offers state-of-the-art hardware and software acceleration to train, fine-tune and predict with Transformers. | |
| </p> | |
| <p> | |
| Useful Resources: | |
| </p> | |
| <ul> | |
| <li class="ml-6"><a href="https://huggingface.co/hardware/intel" class="underline" data-ga-category="intel-org" data-ga-action="clicked partner page" data-ga-label="partner page">- Intel AI + Hugging Face partner page</a></li> | |
| <li class="ml-6"><a href="https://github.com/IntelAI" class="underline" data-ga-category="intel-org" data-ga-action="clicked intel ai github" data-ga-label="intel ai github">- Intel AI GitHub</a></li> | |
| <li class="ml-6"><a href="https://www.intel.com/content/www/us/en/developer/partner/hugging-face.html" class="underline" data-ga-category="intel-org" data-ga-action="clicked intel partner page" data-ga-label="intel partner page">- Developer Resources from Intel and Hugging Face</a></li> | |
| </ul> | |
| </div> | |
| <div class="lg:col-span-3"> | |
| <p class="mb-2"> | |
| To get started with Intel® hardware and software optimizations, download and install the Optimum-Intel® | |
| and Intel® Extension for Transformers libraries with the following commands: | |
| </p> | |
| <pre><code> | |
| $ python -m pip install "optimum-intel[extras]"@git+https://github.com/huggingface/optimum-intel.git | |
| $ python -m pip install intel-extension-for-transformers | |
| </code></pre> | |
| <p> | |
| <i>For additional information on these two libraries including installation, features, and usage, see the two links below.</i> | |
| </p> | |
| <p class="mb-2"> | |
| Next, find your desired model (and dataset) by searching in the search box at the top-left of Hugging Face’s website. | |
| Add “intel” to your search to narrow your search to Intel®-pretrained models. | |
| </p> | |
| <p class="mb-2"> | |
| On the model’s page (called a “Model Card”) you will find description and usage information, an embedded | |
| inferencing demo, and the associated dataset. In the upper-right of your screen, click “Use in Transformers” | |
| for helpful code hints on how to import the model to your own workspace with an established Hugging Face pipeline and tokenizer. | |
| </p> | |
| <p> | |
| Library Source and Documentation: | |
| </p> | |
| <ul> | |
| <li class="ml-6"><a href="https://github.com/huggingface/optimum-intel" class="underline" data-ga-category="intel-org" data-ga-action="clicked optimum intel" data-ga-label="optimum intel">- 🤗 Optimum-Intel® library</a></li> | |
| <li class="ml-6"><a href="https://github.com/intel/intel-extension-for-transformers" class="underline" data-ga-category="intel-org" data-ga-action="clicked intel extension for transformers" data-ga-label="intel extension for transformers">- Intel® Extension for Transformers</a></li> | |
| </ul> | |
| </div> | |
| </div> |