Did you know that with @AbacusAI
's unique #MLOps / #LLMOps platform, you can 10x your Enterprise #DataScience Abilities? You can! Use #GenerativeAI to build end-to-end #AI Systems & Agents at enterprise scale! Start now: https://
abacus.ai
—
#ML #MachineLearning #LLMs #GenAI
MACHINE LEARNING
-
Abacus AI Platform: 10x Your Enterprise Data Science Abilities
By
–
-
TheProfessor: Advanced LLM Merging Conversational AI Platform
By
–
TheProfessor is a merge of #LLMs, created with help from @AbacusAI
's #GenerativeAI team. It can be used for many things with its conversational #AI, reasoning, scientific, medical, & mathematical skills interactive brainstorming: https://
huggingface.co/abacusai/ThePr
ofessor-155b
… -
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 -
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 -
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
-
Predict Method for Class Labels Using Single Point Prediction
By
–
A 'predict' method that predicts the class labels for a set of data points. It calls '_predict_single' method that actually predicts the class label for a single data point.
-
Implementing Fit Method and Euclidean Distance in KNN Algorithm
By
–
Next define the "fit" method that takes the training data(X) and it's corresponding labels(y) and stores them. This is the reason why the computation cost is high as it stores all the training data! And also a method to calculates the euclidean distance between two data points.
-
KNNClassifier Class Initialization and K Value Selection
By
–
Define the KNNClassifier class and initialize the number of Neighbours (k) to be considered in __init__ method Defining the K value is critical in KNN! A small value of k means noise will have a higher influence on the result and a large value makes it computationally expensive