Popular GitHub Repositories for Umap

Uniform Manifold Approximation and Projection

Visualization for a Retrieval-Augmented Generation (RAG) Assistant ????

Using machine learning on your anki collection to enhance the scheduling via semantic clustering and semantic similarity

Comparing FC VAE / FCN VAE / PCA / UMAP on MNIST / FMNIST

Workshop (6 hours): Clustering (Hdbscan, LCA, Hopach), dimension reduction (UMAP, GLRM), and anomaly detection (isolation forests).

KNRScore是一个Python库，用于计算K近邻秩相似度。该指标用于量化两张地图或嵌入之间局部结构的相似性。

Taxonomy Completion with Embedding Quantization and an LLM-based Pipeline: A Case Study in Computational Linguistics

This project clusters products by their titles and assigns topics. Initially using BERT, PCA, and t-SNE, the results were noisy. The improved approach with SBERT, UMAP, and HDBSCAN provides clearer clusters. Topics are assigned using Llama-3-8b.

Deep Classiflie is a framework for developing ML models that bolster fact-checking efficiency. As a POC, the initial alpha release of Deep Classiflie generates/analyzes a model that continuously classifies a single individual's statements (Donald Trump) using a single ground truth labeling source (The Washington Post). For statements the model deems most likely to be labeled falsehoods, the @DeepClassiflie twitter bot tweets out a statement analysis and model interpretation "report"

This project visualizes Wikipedia articles in 3D space using embeddings. Each node represents an article, and the distance between nodes indicates the similarity of the articles.

umart generates umap art

Investigating wav2vec2 context representations and the effects of fine-tuning

Executed Fine-tuning & Benchmarking, optimizing 12+ LLMs (Gemma-family, Mistral, LLaMA, etc) across 6+ datasets (GSM8K, BoolQ, IMDB, Alpaca-GPT4 & more). Delivered a research-level contribution—model training, evaluation, insights, DeepMind benchmark comparisons & documentation. Also crafting a custom dataset from open-sourced V0 system prompts.?

Executed Fine-tuning & Benchmarking, optimizing 12+ LLMs (Gemma-family, Mistral, LLaMA, etc) across 6+ datasets (GSM8K, BoolQ, IMDB, Alpaca-GPT4 & more). Delivered a research-level contribution—model training, evaluation, insights, benchmark comparisons & documentation. Also crafting a custom dataset from open-sourced V0 system prompts.?

Deep_classiflie_db is the backend data system for managing Deep Classiflie metadata, analyzing Deep Classiflie intermediate datasets and orchestrating Deep Classiflie model training pipelines. Deep_classiflie_db includes data scraping modules for the initial model data sources. Deep Classiflie depends upon deep_classiflie_db for much of its analytical and dataset generation functionality but the data system is currently maintained as a separate repository here to maximize architectural flexibility. Depending on how Deep Classiflie evolves (e.g. as it supports distributed data stores etc.), it may make more sense to integrate deep_classiflie_db back into deep_classiflie. Currently, deep_classiflie_db releases are synchronized to deep_classiflie releases. To learn more, visit deepclassiflie.org.

利用UMAP算法控制多智能体集群的线性化和降维。

App for deriving local / global explanations of UMAP embeddings based on principal component analysis (PCA).

Adapted BERTopic pipeline for Topic Modeling the arXiv dataset

Using BERTopic to show the path of technological advancements in the different phases of the economic cycle (January 2005- January 2023).

Interdisciplinary research project exploring AI bias, interpretability, and cultural influence through computational models trained on diverse philosophical corpora. Python, PyTorch, Transformers, UMAP, Streamlit.