Assisted Generation: a new direction toward low-latency text generation
Large language models are all the rage these days, with many companies investing significant resources to scale them up and unlock new capabilities. However, as humans with ever-decreasing attention spans, we also dislike their slow response times. Latency is critical for a good user experience, and smaller models are often used despite their lower quality (e.g. in code completion). Why
Read moreIntroducing RWKV – An RNN with the advantages of a transformer
ChatGPT and chatbot-powered applications have captured significant attention in the Natural Language Processing (NLP) domain. The community is constantly seeking strong, reliable and open-source models for their applications and use cases. The rise of these powerful models stems from the democratization and widespread adoption of transformer-based models, first introduced by Vaswani et al. in 2017. These models significantly outperformed previous SoTA NLP models based on Recurrent Neural Networks (RNNs), which were considered dead after that paper. Through this blogpost, we […]
Read moreHugging Face Selected for the French Data Protection Agency Enhanced Support Program
This blog post was originally published on LinkedIn on 05/15/2023 We are happy to announce that Hugging Face has been selected by the CNIL (French Data Protection Authority) to benefit from its Enhanced Support program! This new program picked three companies with “strong potential for economic development” out of over 40 candidates, who will receive support in understanding and implementing their duties with respect to data protection – a daunting and necessary endeavor in the context of the rapidly evolving […]
Read moreLarge-scale Near-deduplication Behind BigCode
People who are interested in document-level near-deduplication at a large scale, and have some understanding of hashing, graph and text processing. Motivations It is important to take care of our data before feeding it to the model, at least Large Language
Read moreInstruction-tuning Stable Diffusion with InstructPix2Pix
This post explores instruction-tuning to teach Stable Diffusion to follow instructions to translate or process input images. With this method, we can prompt Stable Diffusion using an input image and an “instruction”, such as – Apply a cartoon filter to the natural image. Figure 1: We explore the instruction-tuning
Read moreAudit shows that safetensors is safe and ready to become the default
Hugging Face, in close collaboration with EleutherAI and Stability AI, has ordered an external security audit of the safetensors library, the results of which allow all three organizations to move toward making the library
Read more