without bm25_pt you either have to use really slow string-based code (rank-bm25) or run a server (elasticsearch) to do bm25 in python now, it's a pip package, and two lines; i made everything fast using huggingface & pytorch
AI
-

BM25 Search Implementation Performance Comparison with ElasticSearch
By
–
also shout out to @clifapt for running BM25 via ES on LoCo first: https://
x.com/clifapt/status
/1755303087873429667
… my implementation seems to be slightly less performant than ElasticSearch; not sure why. maybe because i'm using a subword tokenizer, or suboptimal hyperparams? -

Fast GPU-Enabled BM25 Implementation in PyTorch Achieves SOTA
By
–
implemented a fast, GPU-enabled BM25 in pytorch! BM25 is a simple search algorithm from the 70s that works as well as neural networks for most search problems; for all the advances we've made in neural text retrieval, it's still around got near SOTA on stanford LoCO benchmark
-

BM25_PT: Matrix Multiplication for Efficient Search Scoring
By
–
my library is here, bm25_pt: http://
github.com/jxmorris12/bm2
5_pt
… the key insight is that you can reduce the BM25 scoring to a single matrix multiplication. everything in the big fraction on the right side here can be stored in a big matrix of scores then, bm25(q) = bag(q) @ scores.T -

DataRobot Workbench February Release: Codespaces and Data Filtering
By
–
February's platform release is here with new updates including: Codespaces added to DataRobot Workbench to enhance the code-first experience New filter options for data-slice functionality added two new filter options – letting you set a range, inclusive, of the actual
-

Azure OpenAI Announces Assistants API and New Models
By
–
Azure OpenAI Service announces Assistants API, New Models for Finetuning, Text-to-Speech and more bit.ly/3Ijhnax We are launching Assistants API in public preview, new text-to-speech capabilities, upcoming updated models for GPT-4 Turbo preview and GPT-3.5 Turbo [Translated from EN to English]
→ View original post on X — @marktabnet, 2024-03-01 15:07 UTC
-

Language Models Achieve Human-Level Forecasting Capabilities
By
–
Approaching Human-Level Forecasting with Language Models Halawi et al.: https://
arxiv.org/abs/2402.18563 #Artificialintelligence #DeepLearning #MachineLearning -
Cohere Opens New York Office as Major AI Startup Expansion
By
–
Cohere is thrilled to open our New York office today New York is a key technology market and we’re excited to be one of the first major AI startups to establish a presence in the city. This will be an important hub for Cohere to connect our many existing partners and
-
Wrapping up Python, MLOps, ML and LLMs content sharing
By
–
That's a wrap! Every day, I share and simply content around Python, MLOps, Machine Learning & LLMs. Find me →
@Sumanth_077 Like/RT the first tweet and help this reach more people. -

Implementing _predict_single Method for k-NN Classification
By
–
Finally a '_predict_single' method as mentioned it predicts the class label for a single data point This is done by: 1. Calculating the distance between one point to all training examples 2. Selecting the k-nearest Neighbours, & returning the most common class label among them