Rubens Zimbres's repositories
Gemini-RAG
Chatbot that uses Gemini-1.0-Pro to answer questions, with memory by using LangChain. Also, it's enriched by RAG and deployed in Dialogflow
CyberBotLLM
4 chatbots with memory made with Langchain, VertexAI and Gemini, as a cyber challenge to capture and expose RAG content.
GDE-Sprints
A repository of code developed in Google Developer Experts sprints
Machine_Learning_CTF_Challenges
CTF challenges designed and implemented in machine learning applications
OWASP-Survey
Data preparation for the 2024 OWASP Top 10 for LLMs Survey
WeightWatcher-Examples
User Examples of the WeightWatcher project
www-project-top-10-for-large-language-model-applications
OWASP Foundation Web Respository
Cyber-Metrics
Metrics
DamnVulnerableLLMProject
A LLM explicitly designed for getting hacked
DRAFT-reconstruct-dataset-cyber
DRAFT : Dataset Reconstruction Attack From Trained ensembles. Source code associated with the paper "Trained Random Forests Completely Reveal your Dataset" authored by Julien Ferry, Ricardo Fukasawa, Timothée Pascal, and Thibaut Vidal (2024)
grype-vuln-scanner
A vulnerability scanner for container images and filesystems
llama-datasets-RAG
Github repo for storing LlamaDatasets
llama_index
LlamaIndex (formerly GPT Index) is a data framework for your LLM applications
magika-malware-analysis
Detect file content types with deep learning
minGPT-Karpathy
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
MoleculeSTM-NLP-Molecule
Multi-modal Molecule Structure-text Model for Text-based Editing and Retrieval, Nat Mach Intell 2023 (https://www.nature.com/articles/s42256-023-00759-6)
MultiCoT-LangChain-Tables
Repository to demonstrate Chain of Table reasoning with multiple tables powered by LangGraph
mvt-Pegasus
MVT (Mobile Verification Toolkit) helps with conducting forensics of mobile devices in order to find signs of a potential compromise.
NeurIPS-llm-efficiency-challenge
Code for NeurIPS LLM Efficiency Challenge
Python-algos
All Algorithms implemented in Python
RAG_Maestro-scrap-arxiv
Building a chatbot powered with a RAG pipeline to read,summarize and quote the most relevant papers related to the user query.
vllm-highmem-inference-LLM
A high-throughput and memory-efficient inference and serving engine for LLMs