mickymultani

GPT-4-Vision-Architecture-Scanner

A web-based tool that utilizes GPT-4's vision capabilities to analyze and describe system architecture diagrams, providing instant insights and detailed breakdowns in an interactive chat interface.

Groq-RAG

RAG Chatbot powered by Groq LPU, Ollama and Langchain

Groqy-Chat

GROQ LPU Powered LLM chat engine

jsonQueryRAG

LLM query engine to retrieve augmented responses from json files.

nvidia-NIM-RAG

Project demonstrates the power and simplicity of NVIDIA NIM (NVIDIA Inference Model), a suite of optimized cloud-native microservices, by setting up and running a Retrieval-Augmented Generation (RAG) pipeline.

RAG-ChromaDB-Mistral7B

RAG (Retrievel Augmented Generation) implementation using ChromaDB, Mistral-7B-Instruct-v0.1 and gte-base for embeddings.

RAG-Mistral7b

RAG (Retrievel Augmented Generation) implementation using the Mistral-7B-Instruct-v0.1

RAG-with-Cross-Encoder-Reranker

Testing speed and accuracy of RAG with, and without Cross Encoder Reranker.

Streaming-LLM-Chat

Interactive chat application leveraging OpenAI's GPT-4 for real-time conversation simulations. Built with Flask, this project showcases streaming LLM responses in a user-friendly web interface.

TestingGemma2B

Evaluation of Google's Instruction Tuned Gemma-2B, an open-source Large Language Model (LLM). Aimed at understanding the breadth of the model's knowledge, its reasoning capabilities, and adherence to ethical guardrails, this project presents a systematic assessment across a diverse array of domains.

mickymultani/RAG-ChromaDB-Mistral7B

RAG (Retrievel Augmented Generation) implementation using ChromaDB, Mistral-7B-Instruct-v0.1 and gte-base for embeddings.

mickymultani/RAG-with-Cross-Encoder-Reranker

Testing speed and accuracy of RAG with, and without Cross Encoder Reranker.

mickymultani/Streaming-LLM-Chat

Interactive chat application leveraging OpenAI's GPT-4 for real-time conversation simulations. Built with Flask, this project showcases streaming LLM responses in a user-friendly web interface.

mickymultani/jsonQueryRAG

LLM query engine to retrieve augmented responses from json files.

mickymultani/GPT-4-Vision-Architecture-Scanner

A web-based tool that utilizes GPT-4's vision capabilities to analyze and describe system architecture diagrams, providing instant insights and detailed breakdowns in an interactive chat interface.

mickymultani/Groq-RAG

RAG Chatbot powered by Groq LPU, Ollama and Langchain

mickymultani/nvidia-NIM-RAG

Project demonstrates the power and simplicity of NVIDIA NIM (NVIDIA Inference Model), a suite of optimized cloud-native microservices, by setting up and running a Retrieval-Augmented Generation (RAG) pipeline.

mickymultani/Groqy-Chat

GROQ LPU Powered LLM chat engine

mickymultani/LLM-Architecture

Visualize some important concepts related to LLM architectures.

mickymultani/Apple-Pay-POC

Apple Pay Transaction Simulation PoC is a simple educational tool designed to demonstrate and explain the intricacies of the Apple Pay transaction process. This project simulates the tokenization of Primary Account Numbers (PAN) into Device Account Numbers (DAN) and the preparation and authorization of transactions,.

mickymultani/LLMToolKit

mickymultani/portfolio

Micky Multani's GitHub Portfolio

mickymultani/ZeroKnowledgeProofs

Interactive simulation of Zero-Knowledge Proofs using elliptic curve cryptography in Python, demonstrating secure credit score verification for lending processes.

mickymultani/API-Bench

API-Bench is a benchmarking PoC suite for comparing the performance of REST and gRPC APIs in a local development environment. This project systematically uses tools like ApacheBench, ghz, and Apache JMeter to measure and analyze various performance metrics such as response time, throughput, and error rates.

mickymultani/blaze-solana-wallet

Solana Wallet App POC. Fast and easy self custody solution.

mickymultani/ETH-BatchDepositor

Batch deposit tool to launch multiple validators.

mickymultani/JAX-Machinelearning

An interactive tutorial exploring automatic differentiation in machine learning using JAX, demonstrated through a hands-on example with the Iris dataset.

mickymultani/RAG-OpenAI

RAG (Retrievel Augmented Generation) implementation using the OpenAI LLM

mickymultani/RAG-Testing-Gemma7B-IT

mickymultani/Simple-Tokenizer

A sample of a few common tokenizers from Hugging Face's transformers

mickymultani/TestingGemma2B

Evaluation of Google's Instruction Tuned Gemma-2B, an open-source Large Language Model (LLM). Aimed at understanding the breadth of the model's knowledge, its reasoning capabilities, and adherence to ethical guardrails, this project presents a systematic assessment across a diverse array of domains.

mickymultani/rabbitmq-task-queue

A hands-on RabbitMQ project demonstrating a distributed task queue system. Explore message queuing, durability, and distributed processing with simple Python scripts. Ideal for learning asynchronous communication and RabbitMQ basics.

mickymultani/Claude3-Opus-FunctionCalling

Tutorial on how to use function calling with Anthropic Claude 3 Opus

mickymultani/ethStaking-grafana-prometheus

ETH Validator Performance Monitoring using Grafana and Prometheus

mickymultani/genAI-unitTester

Unit test case generation using LLMs for Solidity Smart Contracts

mickymultani/GPT-4o-mini-performance

GPT-4o-mini : Quick setup to test chat performance of various Open AI LLMs

mickymultani/OCR-Service

On-chain registry for Ethereum dapps

mickymultani/pinecone-RAG

Llama Index Pinecone RAG

mickymultani/QuantizeLLMs

Learn to quantize LLMs on HuggingFace

mickymultani/validator-performance-dashboard

ETH Validator KPI Dashbaord using BeaconCha.in API and Chart.js