Pinned Repositories
akbar2habibullah
attention-based-retrieval
This work showcasing the emerge ability of Transformer model to extract the most "important" information inside its attention layer. Ideally, we should extract attention layer directly from inference process to get the most influential token inside a sequence.
chavyv-xyz-2024
Major update for my personal website. Build with Next 14, LangChain, Google AI Platform, Open-LLM (Llama-3, Gemma 2, Mixtral), Groq Cloud, Wikipedia Retrieval, Upstash Redis and Vector, Splitbee, Notion as CMS, attention-based retrieval system, and AI Agent.
chavyv-xyz-angular
This is my personal web for portofolio showcase. Built by many technology to achieve perfect score on Lighthouse. Check it by yourself 🙌
fish-counter
glaze-cloak
Implementation of the Glaze image cloaking algorithm for protecting against unauthorized AI training.
jung-world-model
kreasof-ai-web
Homunculus-Project
Long term project about a custom AI architecture. Consist of cutting-edge technique in machine learning such as Flash-Attention, Group-Query-Attention, ZeRO-Infinity, BitNet, etc.
lawful-diffusion
Lawful Diffusion, ethical way to address copyright violation in text-to-image generative model.
akbar2habibullah's Repositories
akbar2habibullah/chavyv-xyz-angular
This is my personal web for portofolio showcase. Built by many technology to achieve perfect score on Lighthouse. Check it by yourself 🙌
akbar2habibullah/glaze-cloak
Implementation of the Glaze image cloaking algorithm for protecting against unauthorized AI training.
akbar2habibullah/chavyv-xyz-2024
Major update for my personal website. Build with Next 14, LangChain, Google AI Platform, Open-LLM (Llama-3, Gemma 2, Mixtral), Groq Cloud, Wikipedia Retrieval, Upstash Redis and Vector, Splitbee, Notion as CMS, attention-based retrieval system, and AI Agent.
akbar2habibullah/akbar2habibullah
akbar2habibullah/attention-based-retrieval
This work showcasing the emerge ability of Transformer model to extract the most "important" information inside its attention layer. Ideally, we should extract attention layer directly from inference process to get the most influential token inside a sequence.
akbar2habibullah/fish-counter
akbar2habibullah/jung-world-model
akbar2habibullah/kreasof-ai-web
akbar2habibullah/leetcode
This repository contains "my" solutions to various LeetCode problems. The solutions provided in this repository are generated by an AI and are intended to be used for educational purposes only. They are not intended to be used as a substitute for your own problem-solving skills.
akbar2habibullah/LLM-RAG-tutorial
akbar2habibullah/mbak-ai-web-ui
Mbak AI Web UI - Moderator livestream TikTok dengan AI agent, powered by LLM Google Gemini 🤗
akbar2habibullah/ml-model-pytorch-MNIST
Starterpack Popular ML Model Architecture Implementation based on MNIST datasets
akbar2habibullah/multiple-LLM-generation
This is a simple algorithm to implement convergent generations (focusing multiple idea into one coherent output) and divergent generations (expanding one idea into multiple output) in LLM API.
akbar2habibullah/SNN-MNIST
Spiking Neural Network with Norse