-
This is my personal account
- Pittsburgh
- http://searchivarius.org/about
- @srchvrs
-
nmslib Public
Forked from nmslib/nmslibNon-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.
-
Evaluation of Models for Ranking of Long Documents
-
-
py_mtasklite Public
A missing piece of the Python multitask (both threads and processes) API: An extension that supports stateful worker pools & size-aware iterators.
-
-
-
-
-
inpars_light Public
Scripts to reproduce InPars light paper
-
accelerate Public
Forked from huggingface/accelerate🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
Python Apache License 2.0 UpdatedDec 29, 2024 -
py_stateful_map Public
A missing piece of the Python multitask (both threads and processes) API: An extension that supports stateful worker pools & size-aware iterators.
-
FlagEmbedding Public
Forked from FlagOpen/FlagEmbeddingRetrieval and Retrieval-augmented LLMs
Python MIT License UpdatedAug 19, 2024 -
BlogCode Public
Code used in Leonid Boytsov's blog: http://searchivarius.org
-
-
transformers Public
Forked from huggingface/transformers🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Python Apache License 2.0 UpdatedApr 27, 2022 -
AccurateLuceneBM25 Public
Improving the effectiveness Lucene's BM25 (and testing it using Yahoo! Answers and Stack Overflow collections)
-
MSMARCO-Passage-Ranking-Submissions Public
Forked from microsoft/MSMARCO-Passage-Ranking-SubmissionsSubmission archive for the MS MARCO passage ranking leaderboard
Python MIT License UpdatedJan 27, 2022 -
MSMARCO-Document-Ranking-Submissions Public
Forked from microsoft/MSMARCO-Document-Ranking-SubmissionsSubmission archive for the MS MARCO document ranking leaderboard
Python Creative Commons Attribution 4.0 International UpdatedJan 27, 2022 -
-
pytorch-pretrained-BERT-mod Public
A slightly modified version of the older version of the transformer library pytorch-pretrained-BERT
-
DeepNLP-models-Pytorch Public
Forked from DSKSD/DeepNLP-models-PytorchPytorch implementations of various Deep NLP models in cs-224n(Stanford Univ)
Jupyter Notebook MIT License UpdatedOct 15, 2019 -
fastscancount Public
Forked from lemire/fastscancountFast implementations of the scancount algorithm: C++ header-only library
C++ Apache License 2.0 UpdatedOct 7, 2019 -
anserini Public
Forked from castorini/anseriniA Lucene toolkit for replicable information retrieval research
Java UpdatedSep 25, 2019 -
pystruct Public
Forked from pystruct/pystructSimple structured learning framework for python
-
PermTest Public
Permutation algorithms to test statistical significance of experimental results.
-
mgiza Public
Forked from moses-smt/mgizaA word alignment tool based on famous GIZA++, extended to support multi-threading, resume training and incremental training.
C++ UpdatedDec 24, 2018 -
OpenNMT-py Public
Forked from OpenNMT/OpenNMT-pyOpen Source Neural Machine Translation in PyTorch
-
sparse_text_util Public
A nearly SVMLight (but without the class label) Python writer
C++ UpdatedJun 23, 2018 -
TOROS N2 - lightweight approximate Nearest Neighbor library which runs faster even with large datasets
C++ Apache License 2.0 UpdatedDec 10, 2017 -
EphyraQuestionAnalysis Public
A collection of OpenEphyra components necessary for question analysis