SD Turbo and SDXL Turbo are two fast generative text-to-image models capable of generating viable images in as little as one step, a significant improvement over the 30+ steps often required with previous Stable Diffusion models. SD Turbo is a distilled version of Stable Diffusion 2.1, and SDXL Turbo is a distilled version of SDXL 1.0. We’ve previously shown how to accelerate Stable Diffusion inference with ONNX Runtime. Not only does ONNX Runtime provide performance benefits when used with SD […]

Addendum After consulting with the authors of the IPO paper, we discovered that the implementation of IPO in TRL was incorrect; in particular, the loss over the log-likelihoods of the completions needs to be averaged instead of summed. We have added a fix in this PR and re-run the experiments. The results are now consistent with the paper, with IPO on par with DPO and performing better than KTO in the paired preference setting. We have updated the post to […]

PatchTSMixer is a lightweight time-series modeling approach based on the MLP-Mixer architecture. It is proposed in TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting by IBM Research authors Vijay Ekambaram, Arindam Jati, Nam Nguyen, Phanwadee Sinthong and Jayant Kalagnanam. For effective mindshare and to promote open-sourcing – IBM Research joins hands with the HuggingFace team to release this model in the Transformers library. In the Hugging Face implementation, we provide PatchTSMixer’s capabilities to effortlessly facilitate lightweight mixing across patches, […]

New (01/2024): This blog post is strongly inspired by “Fine-tuning XLS-R on Multi-Lingual ASR” and “Fine-tuning MMS Adapter Models for Multi-Lingual ASR”. Introduction Last month, MetaAI released Wav2Vec2-BERT, as a    

Open-source LLMs have now reached a performance level that makes them suitable reasoning engines for powering agent workflows: Mixtral even surpasses GPT-3.5 on our benchmark, and its performance could easily be further enhanced with fine-tuning. We’ve released the simplest agentic library out there: smolagents! Go checkout the smolagents introduction blog here. Introduction Large Language Models (LLMs) trained for causal language modeling can tackle a wide range of    

11/13/2025 Update: we announced a new and deeper partnership with Google Cloud to enable companies to build their own AI with open    

Given the widespread adoption of LLMs, it is critical to understand their safety and risks in different scenarios before extensive deployments in the real world. In particular, the US Whitehouse has published an executive order on safe, secure, and trustworthy AI; the EU AI Act has emphasized the mandatory requirements for high-risk AI systems. Together with regulations, it is important to provide technical solutions to assess the risks of AI systems, enhance their safety, and potentially provide safe and aligned […]

In the rapidly evolving field of Natural Language Processing (NLP), Large Language Models (LLMs) have become central to AI’s ability to understand and generate human language. However, a significant challenge that persists is their tendency to hallucinate — i.e., producing content that may not align with real-world facts or the user’s input. With the constant release of new open-source models, identifying the most reliable ones, particularly in terms of their propensity to generate hallucinated content, becomes crucial. The Hallucinations Leaderboard […]

Recently, code generation models have become very popular, especially with the release of state-of-the-art open-source models such as BigCode’s StarCoder and Meta AI’s Code Llama. A growing number of works focuses on making Large Language Models (LLMs) more optimized and accessible. In this blog, we are happy to share the latest results of LLM optimization on Intel Xeon focusing on the popular code generation LLM, StarCoder. The StarCoder Model is a cutting-edge LLM specifically designed for assisting the user with […]

Today, the Patronus team is excited to announce the new Enterprise Scenarios Leaderboard, built using the Hugging Face Leaderboard Template in collaboration with their teams. The leaderboard aims to evaluate the performance of language models on real-world enterprise use cases. We currently support 6 diverse tasks – FinanceBench, Legal Confidentiality, Creative Writing, Customer Support Dialogue, Toxicity, and Enterprise PII. We measure the performance of models on metrics like accuracy, engagingness, toxicity, relevance, and Enterprise PII. Why do