Today we release Idefics2 our newest 8B Vison-Language Model!
💪 With only 8B parameters Idefics is one of the strongest open models out there
📋 We used multiple OCR datasets, including PDFA and IDL from Ross Wightman and Pablo Montalvo, and increased resolution up to 980x980 to improve…

Interested in generating images with Hugging Face models? On @Intel CPUs? In less than 5 seconds? Our new blog post shows you how to optimize diffusion models with Optimum Intel, OpenVINO, IPEX, and more 🚀 🚀🚀

huggingface.co/blog/stable-di…

#GenerativeAI #MLOps #ComputerVision

Tired of your slow Stable Diffusion model ? 🎨

Go up to 1.6x faster by statically reshaping your model with OpenVINO ⚡️

➡️ Give it a try huggingface.co/docs/optimum/i…

Speed-up inference by 2.4x with OpenVINO quantization 🚀

📕 Check out our blog post to see how we did on a ViT!
huggingface.co/blog/openvino

🏭 The hardware optimization floodgates are open!🔥

Diffusers 0.3.0 supports an experimental ONNX exporter and pipeline for Stable Diffusion 🎨

To find out how to export your own checkpoint and run it with onnxruntime, check the release notes:

github.com/huggingface/di…

ONNX Runtime inference for Seq2Seq models has never been so easy ! 🚀

With 🤗 Optimum, you can now export your T5 model to the ONNX format and perform ONNX Runtime inference using 🤗 Transformers pipelines.

➡️ Start here huggingface.co/docs/optimum/v…

Together with Lewis Tunstall, I gave a talk today on the MLOps world about acceleration Transformers with Hugging Face Optimum🌍🚀

We covered how to accelerate DistilBERT up to ~3x faster latency while keeping > 99.7% accuracy🏎💨 

📕 philschmid.de/static-quantiz…
⭐️github.com/philschmid/opt…

Evaluation is one of the most important aspects of ML but today’s evaluation landscape is scattered and undocumented which makes evaluation unnecessarily hard.

For that reason we are excited to release 🤗 Evaluate!

github.com/huggingface/ev…

Let’s take a tour:

Optimum v1.2 adds ACCELERATED inference pipelines - including text generation - for onnxruntime🚀

Learn how to accelerate RoBERTa for Question-Answering including quantization and optimization with 🤗Optimum in our blog 🦾🔥

📕huggingface.co/blog/optimum-i…
⭐️github.com/huggingface/op…

You can now accelerate inference by applying quantization to models from the Hugging Face Hub 🔥

➡️ With 🤗 Optimum, you can easily apply static and dynamic quantization on your model before exporting it to the ONNX format 🤯

Start here 👉 huggingface.co/docs/optimum/m…

TIL you can apply *static quantization* to Transformer models 🤯!

This technique finds the best quant. scheme by feeding data through the model to observe the activation patterns ahead of inference time 🔮

With 🤗Optimum, you can do this easily with any dataset from the Hub 🥳

One small step for 🤗 Optimum, a giant leap for using 🤗 Transformers with Graphcore IPUs 🚀

With this initial release, start accelerating your trainings with IPUs. We're only getting started - star the repo to follow along! 🌟
github.com/huggingface/op…

I will present tomorrow at EMNLP21 (Session 9F) 'Block Pruning for Faster Transformers', a paper we proposed with Ella Charlaix Victor Sanh Sasha Rush (ICLR) Hugging Face . I will describe how we managed to speedup fine-tuned transformers by more than 2.5x while preserving accuracy !

We are proud to collaborate with Intel AI to Accelerate AI for Production! 🤝🦾

Check out how to easily quantize and prune models with our new 🤗 Optimum library, integrating Intel LPOT:
huggingface.co/hardware

Reply if you spotted this billboard on US 101 by SFO this week! 😎