[ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation
-
Updated
Dec 16, 2024 - Python
GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
lsh-algorithmHere are 61 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
[ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation
Locality Sensitive Hashing in Rust with Python bindings
Locality Sensitive Hashing, fuzzy-hash, min-hash, simhash, aHash, pHash, dHash。基于 Hash值的图片相似度、文本相似度
一个基于 fasttext + faiss 的商品内容相关推荐实现,nginx+uwsgi+flask / gunicorn+uvicorn+fastapi 提供api查询接口,增加Spark实现 Ansj+Word2vec+LSH+Phoenix
ProbMinHash – A Class of Locality-Sensitive Hash Algorithms for the (Probability) Jaccard Similarity
sketch similarity minhash locality-sensitive-hashing jaccard-similarity jaccard-similarity-estimation lsh-algorithm minhash-sketches
TreeMinHash: Fast Sketching for Weighted Jaccard Similarity Estimation
minhash sketching locality-sensitive-hashing similarity-measures hash-algorithm jaccard-similarity jaccard similarity-metric jaccard-distance similarity-search sketching-algorithm jaccard-index jaccard-similarity-estimation minwise-hashing lsh-algorithm weighted-sets minwise-hashing-algorithm locality-sensitive jaccard-coefficient
A Query Efficient Natural Language Attack in a Black Box Setting
A Robust Library in C# for Similarity Estimation
Approximate UniFrac via Weighted MinHash 🦀
big-data metagenomics minhash locality-sensitive-hashing beta-diversity microbiome rejection-sampling streaming-algorithms lsh-algorithm unifrac weighted-jaccard ruzicka-similarity weighted-minhash bray-curtis
Search your object with hash
hashing search-engine deeplearning object-detection object-search yolov3 lsh-implementation lsh-algorithm
使用线程池的高并发 LSH 算法, C++ 实现
A semantic search indexing system designed to efficiently retrieve top matching results from a database of 20 million documents. Given the embedding of a search query, it quickly identifies and returns the most relevant documents
database clustering indexing semantic-search hamming-distance advanced-database pq ivf lsh-algorithm
An implementation of LSH Forrest based off of the following paper (http://infolab.stanford.edu/~bawa/Pub/similarity.pdf).
search go golang lsh similarity search-algorithm searching-algorithms lsh-forest similarity-search lsh-algorithm lsh-forrest
Build content-based image retrieval system using deep learning, applied some large scale similarity search technicals like Kdtree, LSH, Faiss.
deep-learning vgg16 image-retrieval kdtree faiss image-search-engine large-scale-optimization lsh-algorithm
Recommendation System on cryptocurrency, using data collected from users' tweets + 10-Fold Cross Validation ( Based on the cryptocoins from each user's tweets, the program runs algorithms on the data, resulting in the recommendation of other cryptocoins for each user) ( readme in greek but soon to be translated in English )
c text-mining tweets clustering cryptocurrency datascience recommendation-system nearest-neighbors clustering-algorithm hypercube lsh-implementation lsh-algorithm
Scalable mining of multidimensional time series motifs.
Implementation of algorithms for big data using python, numpy, pandas.
python bloom-filter lsh streams frequent-itemset-mining pcy frequent-itemsets stream-mining shingling big-data-processing lsh-algorithm min-hasing similar-items a-priori multistage-pcy multihash-pcy
Lab assignments for the course ID2222-Data Mining at KTH
Repository for all assignments of the course COL761: Data Mining (Fall 2020), taught at IIT Delhi
data-mining r-tree frequent-itemset-mining fp-tree apriori-algorithm gspan-algorithm gaston fsg top-k-query fp-tree-c-implementation lsh-algorithm subgraph-mining
Example on the Local Sensitive Hashing (LSH) algorithm. Relevant for Big Data
Add this topic to your repoTo associate your repository with the lsh-algorithm topic, visit your repo's landing page and select "manage topics." |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |