deep-spin/MF2

Language: Python - Size: 1.69 MB - Last synced at: about 13 hours ago - Pushed at: about 20 hours ago - Stars: 3 - Forks: 0

deep-spin/it-iwslt-2025

Code for the paper "Instituto de Telecomunicações at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning"

Language: Python - Size: 31.3 KB - Last synced at: 8 days ago - Pushed at: 9 days ago - Stars: 1 - Forks: 0

deep-spin/lm-evaluation-harness Fork of EleutherAI/lm-evaluation-harness

A fork of lm-eval-harness.

Language: Python - Size: 24.1 MB - Last synced at: 27 days ago - Pushed at: 27 days ago - Stars: 0 - Forks: 0

deep-spin/entmax

The entmax mapping and its loss, a family of sparse softmax alternatives.

Language: Python - Size: 209 KB - Last synced at: 20 days ago - Pushed at: about 1 year ago - Stars: 440 - Forks: 47

deep-spin/triton-tutorial

From a+b to sparsemax(QK^T)V in Triton!

Language: Jupyter Notebook - Size: 35.6 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 1 - Forks: 0

deep-spin/adasplash

AdaSplash: Adaptive Sparse Flash Attention (aka Flash Entmax Attention)

Language: Python - Size: 149 KB - Last synced at: 28 days ago - Pushed at: 4 months ago - Stars: 8 - Forks: 1

deep-spin/quest-decoding

A package for sampling from Gibbs distributions during inference with LLMs.

Language: Python - Size: 1.02 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 8 - Forks: 2

deep-spin/zsb

Language: Python - Size: 55.4 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 2 - Forks: 0

deep-spin/treqa

LLM-based QAG framework for MT Evaluation

Language: Python - Size: 38.1 KB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

deep-spin/sparse-activations-cp

Repository containing code to reproduce results of the paper "Sparse Activations as Conformal Predictors".

Language: Jupyter Notebook - Size: 794 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 1 - Forks: 0

deep-spin/Megatron-LM-pretrain Fork of NVIDIA/Megatron-LM

Ongoing research training transformer models at scale

Language: Python - Size: 12.9 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 1 - Forks: 0

deep-spin/lmms-eval Fork of EvolvingLMMs-Lab/lmms-eval

Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.

Language: Python - Size: 7.39 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

deep-spin/fy-vi

Language: Jupyter Notebook - Size: 3.56 MB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0

deep-spin/doce

This is the a repo of DOCE

Language: Python - Size: 5.14 MB - Last synced at: 3 months ago - Pushed at: 4 months ago - Stars: 2 - Forks: 0

deep-spin/SpireLM

Language: Python - Size: 0 Bytes - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 0 - Forks: 0

deep-spin/CHM-Net

Modern Hopfield Networks with Continuous-Time Memories

Language: Python - Size: 71.3 KB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 0 - Forks: 0

deep-spin/tower-eval

Language: Python - Size: 1.07 MB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 28 - Forks: 4

deep-spin/Infinite-Video

\infty-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation

Language: Python - Size: 2.05 MB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 9 - Forks: 0

deep-spin/ssm-mt

Language: Jupyter Notebook - Size: 2.54 MB - Last synced at: 6 months ago - Pushed at: 6 months ago - Stars: 0 - Forks: 0

deep-spin/VLMEvalKit Fork of open-compass/VLMEvalKit

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

Size: 2.9 MB - Last synced at: 5 months ago - Pushed at: 6 months ago - Stars: 0 - Forks: 0

deep-spin/HFYN

Hopfield-Fenchel-Young Networks: A Unified Framework for Associative Memory Retrieval

Language: Jupyter Notebook - Size: 4.39 MB - Last synced at: 6 months ago - Pushed at: 6 months ago - Stars: 0 - Forks: 0

deep-spin/reranking-laws

Language: Jupyter Notebook - Size: 91.2 MB - Last synced at: 9 months ago - Pushed at: 9 months ago - Stars: 1 - Forks: 0

deep-spin/infinite-former

Language: Python - Size: 6.15 MB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 65 - Forks: 7

deep-spin/axolotl Fork of axolotl-ai-cloud/axolotl

Go ahead and axolotl questions

Language: Python - Size: 4.66 MB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 0 - Forks: 0

deep-spin/COMET Fork of Unbabel/COMET

A Neural Framework for MT Evaluation

Language: Python - Size: 2.51 MB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 0 - Forks: 0

deep-spin/SSHN

Sparse and Structured Hopfield Networks

Language: Python - Size: 1.65 MB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 2 - Forks: 0

deep-spin/Megatron-DeepSpeed Fork of microsoft/Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Language: Python - Size: 4.77 MB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 0 - Forks: 1

deep-spin/robust-mt

Size: 0 Bytes - Last synced at: about 1 year ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0

deep-spin/understanding-spigot

Code for the paper "Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning"

Language: Python - Size: 50.8 KB - Last synced at: about 1 year ago - Pushed at: about 4 years ago - Stars: 11 - Forks: 0

deep-spin/unn

Code for the paper "Modeling Structure with Undirected Neural Networks"

Language: Python - Size: 29.3 KB - Last synced at: about 1 year ago - Pushed at: about 3 years ago - Stars: 5 - Forks: 0

deep-spin/transformers Fork of huggingface/transformers

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

Size: 22.5 MB - Last synced at: about 1 year ago - Pushed at: almost 5 years ago - Stars: 0 - Forks: 0

deep-spin/sparse_continuous_distributions

This repository provides open-source code for sparse continuous distributions and corresponding Fenchel-Young losses.

Language: Python - Size: 255 KB - Last synced at: about 1 year ago - Pushed at: about 2 years ago - Stars: 15 - Forks: 4

deep-spin/sigmorphon-seq2seq

DeepSPIN's submission to SIGMORPHON 2020

Language: Python - Size: 2.28 MB - Last synced at: about 1 year ago - Pushed at: about 5 years ago - Stars: 4 - Forks: 1

deep-spin/SIGMORPHON2019

IT-IST's submission to SIGMORPHON 2019 Task 1

Language: Python - Size: 169 KB - Last synced at: about 1 year ago - Pushed at: almost 3 years ago - Stars: 3 - Forks: 1

deep-spin/qe-evaluation

Evaluation scripts for the 2019 machine translation quality estimation shared task

Language: Python - Size: 10.7 KB - Last synced at: about 1 year ago - Pushed at: over 6 years ago - Stars: 12 - Forks: 4

deep-spin/dgm.pt Fork of probabll/dgm.pt

Pytorch code for deep generative models

Language: Python - Size: 146 KB - Last synced at: about 1 year ago - Pushed at: over 5 years ago - Stars: 0 - Forks: 0

deep-spin/deep-spin.github.io

Website of the DeepSPIN ERC project.

Language: HTML - Size: 14.6 MB - Last synced at: about 1 year ago - Pushed at: about 5 years ago - Stars: 1 - Forks: 0

deep-spin/dylatentstruct

latent structured models in dynet

Language: C++ - Size: 158 KB - Last synced at: about 1 year ago - Pushed at: over 5 years ago - Stars: 0 - Forks: 0

deep-spin/speech-continuous-attention

Speech Classification using Continuous Attention Mechanisms

Language: Python - Size: 191 KB - Last synced at: about 1 year ago - Pushed at: about 3 years ago - Stars: 2 - Forks: 1

deep-spin/uncertainties_MT_eval

Code and data for the paper "Disentangling Uncertainty in Machine Translation Evaluation", accepted at EMNLP 2022.

Language: Python - Size: 145 KB - Last synced at: about 1 year ago - Pushed at: about 2 years ago - Stars: 21 - Forks: 3

deep-spin/qaware-decode

A repository for experiments in quality-aware decoding

Language: Python - Size: 76.2 KB - Last synced at: about 1 year ago - Pushed at: about 3 years ago - Stars: 13 - Forks: 5

deep-spin/sparse_text_generation

Language: Python - Size: 466 KB - Last synced at: about 1 year ago - Pushed at: over 2 years ago - Stars: 19 - Forks: 6

deep-spin/non-exchangeable-crc

Language: Jupyter Notebook - Size: 795 KB - Last synced at: about 1 year ago - Pushed at: almost 2 years ago - Stars: 6 - Forks: 2

deep-spin/scheduled-sampling-transformers

Code for the paper "Scheduled Sampling for Transformers"

Language: Python - Size: 133 MB - Last synced at: about 1 year ago - Pushed at: over 5 years ago - Stars: 24 - Forks: 4

deep-spin/ot-hallucination-detection

Language: Python - Size: 25.4 KB - Last synced at: about 1 year ago - Pushed at: about 2 years ago - Stars: 4 - Forks: 1

deep-spin/vqa-multimodal-continuous-attention

Language: Python - Size: 79.1 KB - Last synced at: about 1 year ago - Pushed at: over 3 years ago - Stars: 3 - Forks: 0

deep-spin/crest

Code for CREST: A Joint Framework for Rationalization and Counterfactual Text Generation, accepted at ACL 2023.

Language: Python - Size: 1.91 MB - Last synced at: about 1 year ago - Pushed at: about 2 years ago - Stars: 6 - Forks: 1

deep-spin/hallucinations-in-nmt

Size: 1.57 MB - Last synced at: about 1 year ago - Pushed at: over 1 year ago - Stars: 17 - Forks: 3

deep-spin/translation_llm

Language: Jupyter Notebook - Size: 51.8 KB - Last synced at: about 1 year ago - Pushed at: over 1 year ago - Stars: 3 - Forks: 2

deep-spin/robust_MT_evaluation

Repository for "BLEU Meets COMET: Combining Lexical and Neural Metrics Towards Robust Machine Translation Evaluation", accepted at EAMT 2023.

Language: Jupyter Notebook - Size: 821 KB - Last synced at: about 1 year ago - Pushed at: about 2 years ago - Stars: 15 - Forks: 0

deep-spin/UA_COMET

Repository for "Uncertainty-Aware Machine Translation Evaluation", accepted to Findings of EMNLP 2021.

Language: Python - Size: 795 MB - Last synced at: about 1 year ago - Pushed at: almost 4 years ago - Stars: 34 - Forks: 2

deep-spin/OpenNMT-APE 📦

Language: Python - Size: 134 MB - Last synced at: about 1 year ago - Pushed at: over 4 years ago - Stars: 33 - Forks: 12

deep-spin/qe-corpus-builder Fork of Unbabel/word-level-qe-corpus-builder

Builds a WMT18-like corpus for word-level QE with annotations in the source and target words.

Language: Python - Size: 36.2 MB - Last synced at: about 1 year ago - Pushed at: almost 3 years ago - Stars: 4 - Forks: 4

deep-spin/lmt_hallucinations

Language: Shell - Size: 21.5 KB - Last synced at: about 1 year ago - Pushed at: about 2 years ago - Stars: 13 - Forks: 0

deep-spin/lp-sparsemap

LP-SparseMAP: Differentiable sparse structured prediction in coarse factor graphs

Language: C++ - Size: 2.08 MB - Last synced at: 6 months ago - Pushed at: over 1 year ago - Stars: 41 - Forks: 8

deep-spin/megablocks Fork of stanford-futuredata/megablocks

Language: Python - Size: 3.75 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0

deep-spin/Megatron-LM-Megablocks Fork of stanford-futuredata/Megatron-LM

Ongoing research training transformer models at scale

Language: Python - Size: 3.39 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0

deep-spin/explainable-qe-shared-task

IST-Unbabel 2021 Submission for the Quality Estimation Shared Task

Language: Jupyter Notebook - Size: 269 KB - Last synced at: about 1 year ago - Pushed at: almost 3 years ago - Stars: 9 - Forks: 2

deep-spin/sparse-communication

Language: Jupyter Notebook - Size: 7.08 MB - Last synced at: about 1 year ago - Pushed at: over 3 years ago - Stars: 11 - Forks: 1

deep-spin/sparse-marginalization-lvm

Official PyTorch (Lightning) implementation of the NeurIPS 2020 paper "Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity".

Language: Python - Size: 530 KB - Last synced at: about 1 year ago - Pushed at: about 4 years ago - Stars: 27 - Forks: 8

deep-spin/tutorial

Web page for our tutorial on latent structure for NLP

Size: 17.3 MB - Last synced at: about 1 year ago - Pushed at: almost 6 years ago - Stars: 47 - Forks: 4

deep-spin/OpenNMT-entmax

Language: Python - Size: 132 MB - Last synced at: about 1 year ago - Pushed at: about 6 years ago - Stars: 14 - Forks: 3

deep-spin/translation-hypothesis-ensembling

Language: Shell - Size: 18.6 KB - Last synced at: about 1 year ago - Pushed at: almost 2 years ago - Stars: 3 - Forks: 0

deep-spin/towerllm-alignment Fork of huggingface/alignment-handbook

Code for alignment for the towerllm project.

Language: Python - Size: 138 KB - Last synced at: about 1 year ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0

deep-spin/fairseq-multi-mt Fork of facebookresearch/fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Language: Python - Size: 11.9 MB - Last synced at: about 1 year ago - Pushed at: over 3 years ago - Stars: 1 - Forks: 0

deep-spin/mcan-vqa-continuous-attention

Language: Python - Size: 131 KB - Last synced at: about 1 year ago - Pushed at: almost 5 years ago - Stars: 21 - Forks: 2

deep-spin/pyturbo

Neural dependency parser with higher-order features

Language: Python - Size: 861 KB - Last synced at: about 1 year ago - Pushed at: about 5 years ago - Stars: 6 - Forks: 1

deep-spin/entmax-jax

The entmax mapping in JAX

Language: Python - Size: 17.6 KB - Last synced at: about 1 year ago - Pushed at: over 3 years ago - Stars: 11 - Forks: 1

deep-spin/S7

Smoothing and Shrinking the Sparse Seq2Seq Search Space

Language: Python - Size: 1.95 MB - Last synced at: about 1 year ago - Pushed at: over 4 years ago - Stars: 6 - Forks: 0

deep-spin/chunk-based_knn-mt

Language: Python - Size: 17.8 MB - Last synced at: about 1 year ago - Pushed at: over 2 years ago - Stars: 5 - Forks: 1

deep-spin/efficient_kNN_MT

Language: Python - Size: 18.6 MB - Last synced at: about 1 year ago - Pushed at: about 3 years ago - Stars: 5 - Forks: 2

deep-spin/stopes Fork of facebookresearch/stopes

A library for preparing data for machine translation research (monolingual preprocessing, bitext mining, etc.) built by the FAIR NLLB team.

Size: 2.03 MB - Last synced at: about 1 year ago - Pushed at: over 2 years ago - Stars: 1 - Forks: 0

deep-spin/spectra-rationalization

Repository for SPECTRA: Sparse Structured Text Rationalization, accepted at EMNLP 2021 main conference.

Language: Python - Size: 431 KB - Last synced at: about 1 year ago - Pushed at: over 1 year ago - Stars: 9 - Forks: 2

deep-spin/tutorial-latent-struct-src

Sources for our slides for the latent structure in NLP tutorial

Language: TeX - Size: 3.33 MB - Last synced at: about 1 year ago - Pushed at: almost 6 years ago - Stars: 3 - Forks: 0

deep-spin/TVmax

Language: Python - Size: 110 KB - Last synced at: about 1 year ago - Pushed at: over 3 years ago - Stars: 2 - Forks: 1

deep-spin/fairseq-m2m100 Fork of facebookresearch/fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Size: 18.4 MB - Last synced at: about 1 year ago - Pushed at: over 2 years ago - Stars: 0 - Forks: 0

deep-spin/spec

The Explanation Game: Towards Prediction Explainability through Sparse Communication

Language: Python - Size: 169 KB - Last synced at: about 1 year ago - Pushed at: over 4 years ago - Stars: 4 - Forks: 1

deep-spin/sparsefinder-mlm

Code for training and evaluating MLM models for our paper "Predicting Attention Sparsity in Transformers"

Language: Python - Size: 178 KB - Last synced at: about 1 year ago - Pushed at: over 3 years ago - Stars: 0 - Forks: 1

deep-spin/sparsefinder

Code for "Predicting Attention Sparsity in Transformers"

Language: Python - Size: 69.3 KB - Last synced at: about 1 year ago - Pushed at: over 3 years ago - Stars: 0 - Forks: 0

deep-spin/quati

Simple and modular library for document classification and sequence tagging.

Language: Python - Size: 108 KB - Last synced at: about 1 year ago - Pushed at: over 4 years ago - Stars: 2 - Forks: 1