24 citations · 33 across the 13 of their papers we have counts for
14 papers
Shieldstral
Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +273
We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7 its size on text safety benchmarks and set…
Voxtral TTS
Mistral-AI, :, Alexander H. Liu +186
We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid…
Voxtral Realtime
Mistral-AI, :, Alexander H. Liu +166
We introduce Voxtral Realtime, a natively streaming automatic speech recognition model that matches offline transcription quality at sub-second latency. Unlike approaches that adap…
Ministral 3
Alexander H. Liu, Kartik Khandelwal, Sandeep Subramanian +116
We introduce the Ministral 3 series, a family of parameter-efficient dense language models designed for compute and memory constrained applications, available in three model sizes:…
Devstral: Fine-tuning Language Models for Coding Agent Applications
Abhinav Rastogi, Adam Yang, Albert Q. Jiang +100
We introduce Devstral-Small, a lightweight open source model for code agents with the best performance among models below 100B size. In this technical report, we give an overview o…
-Parametrization for Mixture of Experts
Jan Małaśnicki, Kamil Ciebiera, Mateusz Boruń +8
Recent years have seen a growing interest and adoption of LLMs, with Mixture-of-Experts (MoE) emerging as a leading architecture in extremely large models. Currently, the largest o…
Voxtral
Alexander H. Liu, Andy Ehrenberg, Andy Lo +103
We present Voxtral Mini and Voxtral Small, two multimodal audio chat models. Voxtral is trained to comprehend both spoken audio and text documents, achieving state-of-the-art perfo…
Decoupled Relative Learning Rate Schedules
Jan Ludziejewski, Jan Małaśnicki, Maciej Pióro +8
In this work, we introduce a novel approach for optimizing LLM training by adjusting learning rates across weights of different components in Transformer models. Traditional method…
Projected Compression: Trainable Projection for Efficient Transformer Compression
Maciej Stefaniak, Michał Krutul, Jan Małaśnicki +6
Large language models have steadily increased in size to achieve improved performance; however, this growth has also led to greater inference time and computational demands. Conseq…
Magistral
Mistral-AI, :, Abhinav Rastogi +98
We introduce Magistral, Mistral's first reasoning model and our own scalable reinforcement learning (RL) pipeline. Instead of relying on existing implementations and RL traces dist…
Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient
Jan Ludziejewski, Maciej Pióro, Jakub Krajewski +8
Mixture of Experts (MoE) architectures have significantly increased computational efficiency in both research and real-world applications of large-scale machine learning models. Ho…
MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts
Maciej Pióro, Kamil Ciebiera, Krystian Król +7
State Space Models (SSMs) have become serious contenders in the field of sequential modeling, challenging the dominance of Transformers. At the same time, Mixture of Experts (MoE)…
Scaling Laws for Fine-Grained Mixture of Experts
Jakub Krajewski, Jan Ludziejewski, Kamil Adamczewski +9
Mixture of Experts (MoE) models have emerged as a primary solution for reducing the computational cost of Large Language Models. In this work, we analyze their scaling properties,…
Mixture of Tokens: Continuous MoE through Cross-Example Aggregation
Szymon Antoniak, Michał Krutul, Maciej Pióro +7
Mixture of Experts (MoE) models based on Transformer architecture are pushing the boundaries of language and vision tasks. The allure of these models lies in their ability to subst…