Skip to content

@deep-spin SARDINE Lab (DeepSPIN)

Change the repository type filter

All

    Repositories list

    95 repositories

    • MF2

      Public
      Python
      •0•6•0•0•Updated May 25, 2026May 25, 2026

    • entmaxkv

      Public
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •0•0•0•0•Updated May 20, 2026May 20, 2026

    • adasplash

      Public
      AdaSplash: Adaptive Sparse Flash Attention (aka Flash Entmax Attention)
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •2•43•1•0•Updated May 20, 2026May 20, 2026

    • dash-attention

      Public
      DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention
      0•0•0•0•Updated May 11, 2026May 11, 2026

    • SEQUOR

      Public
      Python
      •0•0•0•0•Updated May 8, 2026May 8, 2026

    • asentmax

      Public
      Code for Long-Context Generalization with Sparse Attention.
      Python
      •
      GNU General Public License v3.0
      •0•5•1•0•Updated Apr 21, 2026Apr 21, 2026

    • olmes

      Public
      Reproducible, flexible LLM evaluations
      Python
      •
      Apache License 2.0
      •90•0•0•0•Updated Apr 20, 2026Apr 20, 2026

    • LLaVA-NeXT

      Public
      LLaVA-NeXT architecture
      Jupyter Notebook
      •
      Apache License 2.0
      •464•3•0•0•Updated Feb 24, 2026Feb 24, 2026

    • math-benchmark

      Public
      Jupyter Notebook
      •0•0•0•0•Updated Feb 20, 2026Feb 20, 2026

    • EuroMoE

      Public
      0•0•0•0•Updated Feb 15, 2026Feb 15, 2026

    • sparse_kernel_regression

      Public
      Official code for the "Sparse Attention as Compact Kernel Regression" paper
      Python
      •0•1•0•0•Updated Feb 8, 2026Feb 8, 2026

    • eurollm-eval

      Public
      Jupyter Notebook
      •1•2•0•0•Updated Feb 5, 2026Feb 5, 2026

    • infinity-MNEMONIC

      Public
      Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
      Jupyter Notebook
      •
      Apache License 2.0
      •1.8k•0•0•0•Updated Jan 30, 2026Jan 30, 2026

    • tower-eval

      Public
      Python
      •5•29•0•0•Updated Nov 14, 2025Nov 14, 2025

    • gender-bias-qe-metrics

      Public
      Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality Estimation
      Jupyter Notebook
      •
      MIT License
      •0•0•0•0•Updated Oct 6, 2025Oct 6, 2025

    • it-iwslt-2025

      Public
      Code for the paper "Instituto de Telecomunicações at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning"
      Python
      •
      Apache License 2.0
      •0•2•0•0•Updated Sep 30, 2025Sep 30, 2025

    • lmms-eval

      Public
      Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.
      Python
      •
      Other
      •593•0•0•1•Updated Sep 26, 2025Sep 26, 2025

    • non-exchangeable-crc

      Public
      Jupyter Notebook
      •2•11•0•0•Updated Sep 25, 2025Sep 25, 2025

    • quest-decoding

      Public
      A package for sampling from Gibbs distributions during inference with LLMs.
      Python
      •
      Apache License 2.0
      •3•10•1•0•Updated Aug 14, 2025Aug 14, 2025

    • SparseModernBERT

      Public
      Python
      •
      MIT License
      •0•1•0•0•Updated Jul 15, 2025Jul 15, 2025

    • Megatron-LM-pretrain

      Public
      Ongoing research training transformer models at scale
      Python
      •
      Other
      •4k•2•0•1•Updated Jun 20, 2025Jun 20, 2025

    • triton-tutorial

      Public
      From a+b to sparsemax(QK^T)V in Triton!
      Jupyter Notebook
      •0•34•0•0•Updated Jun 19, 2025Jun 19, 2025

    • zsb

      Public
      Python
      •0•5•0•0•Updated Jun 9, 2025Jun 9, 2025

    • treqa

      Public
      LLM-based QAG framework for MT Evaluation
      Python
      •1•5•1•1•Updated May 13, 2025May 13, 2025

    • sparse-activations-cp

      Public
      Repository containing code to reproduce results of the paper "Sparse Activations as Conformal Predictors".
      Jupyter Notebook
      •1•2•1•0•Updated Apr 27, 2025Apr 27, 2025

    • torchtitan

      Public
      A PyTorch native library for large model training
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •834•0•0•0•Updated Apr 1, 2025Apr 1, 2025

    • fy-vi

      Public
      Jupyter Notebook
      •0•0•0•0•Updated Mar 21, 2025Mar 21, 2025

    • doce

      Public
      This is the a repo of DOCE
      Python
      •
      Apache License 2.0
      •0•2•0•0•Updated Mar 14, 2025Mar 14, 2025

    • latim

      Public
      Jupyter Notebook
      •
      MIT License
      •0•6•0•0•Updated Feb 24, 2025Feb 24, 2025

    • CHM-Net

      Public
      Modern Hopfield Networks with Continuous-Time Memories
      Python
      •
      MIT License
      •1•3•0•0•Updated Feb 21, 2025Feb 21, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.