Skip to content

@deep-spin DeepSPIN

Change the repository type filter

All

    Repositories list

    66 repositories

    • lmms-eval

      Public
      Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.
      Python
      •
      Other
      •169•0•0•0•Updated Dec 17, 2024Dec 17, 2024

    • Megatron-LM-pretrain

      Public
      Ongoing research training transformer models at scale
      Python
      •
      Other
      •2.4k•0•0•1•Updated Dec 17, 2024Dec 17, 2024

    • tower-eval

      Public
      Python
      •4•26•0•0•Updated Dec 12, 2024Dec 12, 2024

    • HFYN

      Public
      Hopfield-Fenchel-Young Networks: A Unified Framework for Associative Memory Retrieval
      Jupyter Notebook
      •
      MIT License
      •0•0•0•0•Updated Dec 3, 2024Dec 3, 2024

    • quest-decoding

      Public
      A package for sampling from Gibbs distributions during inference with LLMs.
      Python
      •
      Apache License 2.0
      •1•6•1•0•Updated Nov 25, 2024Nov 25, 2024

    • doce

      Public
      This is the a repo of DOCE
      Jupyter Notebook
      •
      Apache License 2.0
      •0•2•0•0•Updated Nov 22, 2024Nov 22, 2024

    • reranking-laws

      Public
      Jupyter Notebook
      •0•1•0•0•Updated Oct 15, 2024Oct 15, 2024

    • mt-pref-alignment

      Public
      Python
      •0•0•0•0•Updated Oct 10, 2024Oct 10, 2024

    • axolotl

      Public
      Go ahead and axolotl questions
      Python
      •
      Apache License 2.0
      •893•0•0•0•Updated Sep 26, 2024Sep 26, 2024

    • nanotron

      Public
      Minimalistic large language model 3D-parallelism training
      Python
      •
      Apache License 2.0
      •132•0•0•0•Updated Sep 19, 2024Sep 19, 2024

    • infinite-former

      Public
      Python
      •7•64•2•7•Updated Aug 29, 2024Aug 29, 2024

    • sigmorphon-seq2seq

      Public
      DeepSPIN's submission to SIGMORPHON 2020
      Python
      •
      MIT License
      •1•5•1•1•Updated Jul 25, 2024Jul 25, 2024

    • Megatron-DeepSpeed

      Public
      Ongoing research training transformer language models at scale, including: BERT & GPT-2
      Python
      •
      Other
      •2.4k•1•0•2•Updated Jul 12, 2024Jul 12, 2024

    • SSHN

      Public
      Sparse and Structured Hopfield Networks
      Python
      •
      MIT License
      •0•2•0•0•Updated Jul 4, 2024Jul 4, 2024

    • entmax

      Public
      The entmax mapping and its loss, a family of sparse softmax alternatives.
      Python
      •
      MIT License
      •44•418•10•2•Updated Jun 22, 2024Jun 22, 2024

    • COMET

      Public
      A Neural Framework for MT Evaluation
      Python
      •
      Apache License 2.0
      •82•0•0•0•Updated Jun 11, 2024Jun 11, 2024

    • robust-mt

      Public
      0•0•0•0•Updated Mar 6, 2024Mar 6, 2024

    • spectra-rationalization

      Public
      Repository for SPECTRA: Sparse Structured Text Rationalization, accepted at EMNLP 2021 main conference.
      Python
      •
      MIT License
      •2•10•1•0•Updated Feb 14, 2024Feb 14, 2024

    • hallucinations-in-nmt

      Public
      3•18•1•1•Updated Jan 16, 2024Jan 16, 2024

    • towerllm-alignment

      Public
      Code for alignment for the towerllm project.
      Python
      •
      Apache License 2.0
      •418•1•0•0•Updated Nov 29, 2023Nov 29, 2023

    • lp-sparsemap

      Public
      LP-SparseMAP: Differentiable sparse structured prediction in coarse factor graphs
      C++
      •
      MIT License
      •8•41•3•1•Updated Nov 20, 2023Nov 20, 2023

    • translation_llm

      Public
      Jupyter Notebook
      •
      MIT License
      •3•8•0•0•Updated Nov 10, 2023Nov 10, 2023

    • translation-hypothesis-ensembling

      Public
      Shell
      •0•3•0•0•Updated Oct 17, 2023Oct 17, 2023

    • non-exchangeable-crc

      Public
      Jupyter Notebook
      •2•8•0•0•Updated Oct 9, 2023Oct 9, 2023

    • robust_MT_evaluation

      Public
      Repository for "BLEU Meets COMET: Combining Lexical and Neural Metrics Towards Robust Machine Translation Evaluation", accepted at EAMT 2023.
      machine-translationquality-estimationinterpretabilityrobustnessmachine-translation-metricseamt
      Jupyter Notebook
      •
      Apache License 2.0
      •0•18•0•0•Updated Jul 19, 2023Jul 19, 2023

    • uncertainties_MT_eval

      Public
      Code and data for the paper "Disentangling Uncertainty in Machine Translation Evaluation", accepted at EMNLP 2022.
      machine-translationuncertainty-quantificationquality-estimationinterpretabilityemnlp2022
      Python
      •
      Apache License 2.0
      •3•23•0•0•Updated Jun 23, 2023Jun 23, 2023

    • lmt_hallucinations

      Public
      Shell
      •0•17•0•0•Updated Jun 13, 2023Jun 13, 2023

    • crest

      Public
      Code for CREST: A Joint Framework for Rationalization and Counterfactual Text Generation, accepted at ACL 2023.
      Python
      •
      MIT License
      •1•8•0•0•Updated May 29, 2023May 29, 2023

    • ot-hallucination-detection

      Public
      Python
      •1•5•0•0•Updated May 28, 2023May 28, 2023

    • sparse_continuous_distributions

      Public
      This repository provides open-source code for sparse continuous distributions and corresponding Fenchel-Young losses.
      Python
      •
      MIT License
      •4•16•0•1•Updated May 10, 2023May 10, 2023