huggingface

CLIP-based aesthetics predictor inspired by the interface of 🤗 huggingface transformers.

Easy to use LLM Prompt Injection Detection and Prompt Input Sanitization / Detector Python Package with support for local models, API-based safeguards, safeguard for tool calls, and LangChain guardrails.

An ASR (Automatic Speech Recognition) adversarial attack repository.

Interactive notes (Jupyter Notebooks) for building AI-powered applications

Generate degraded speech datasets for noise-robust ASR benchmarking

Developed a sophisticated machine learning model capable of generating diverse interview questions aligned with specific topics, ensuring depth of conversation. Integrated advanced Natural Language Processing (NLP) algorithms to analyse spoken responses, identifying grammatical errors & offering accurate corrections after the interview.

LLMtranslator translates and generates text in multiple languages.

🤗 Push your spaCy pipelines to the Hugging Face Hub

AI-powered semantic search engine for emojis in 50+ languages, developed in Python

First open-source TurboQuant KV cache compression for LLM inference. Drop-in for HuggingFace. pip install turboquant.

Building an AWS Solution Architect Agent with Generative AI

A collection of Voila web apps for geospatial applications

QA Bot for Hugging Face documentation to accelerate development within the ecosystem.

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking curves, compare variants with evidence — not vibes.

Quick start. Index multiple documents in a repository using HuggingFace embeddings. Save them in Chroma and / or FAISS for recall. Choose OpenAI or Azure OpenAI APIs to get answers to your questions - Q&A with OpenAI and Azure OpenAI.

Airflow Pipeline for Machine Learning

Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.

Read like a superhero: Turn PDFs into Bionic Reading format https://x.com/Benavent/status/1853508523638116689

ONNX implementation of the BGE-M3 multilingual embedding model and tokenizer with native C#, Java, and Python implementations. Generates all three embedding types: dense, sparse, and ColBERT vectors.

Upload & Merge CSV or JSON Data with Images to Notion Database