autotokenizer

Document-Similarity-Finding-using-BERT

Visualizing and analyzing BERT self-attention heads during masked language modeling.

Projeto do desafio final do Bootcamp IA Expert, focado na criação de um chatbot no Google Colab utilizando modelos pre-treinados do Hugging Face (Zephyr-3B), AutoTokenizer, geracao de texto e interface grafica com Gradio.

LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs focusing on 中国的行政区划, 传统客栈, 中国旅游的总结与展望, 安全问题, 应对突发情况.

Exploring Hugging face various transformer models and datasets.

This notebook is part of my Udacity Generative AI Nanodegree. It’s designed to sharpen familiarity with PyTorch and Hugging Face by exploring documentation, loading models/tokenizers, and writing minimal runnable code for real-world model interaction.

Mini RAG system that allows users to upload PDF documents and ask questions about their content. The entire process, from document analysis to answer generation, runs on your local machine using open-source Hugging Face models, ensuring privacy and eliminating the need for external API keys

Generate insights and rankings for potential candidates

Tool for generating smart and secure prompts for language models!