TMLC Academy

Important Links for The Program

Orientation Session

Understanding the key terms under AI Umbrella

Introduction to AI

Introduction to AI (Slides)

The Evolution of Transformers to Large Language Models (LLMs)

Introduction to Generative AI (GenAI)

Understanding Key Concepts and Terminologies in Generative AI

Steps in Generative AI Pipeline

4 important steps in Generative AI Pipeline

Steps to access OpenAI Playground

Fine-tuning a Model using OpenAI Playground : Build a FAQ Bot

Fine-tuning a Model using OpenAI Playground : A step by step approach

Fine-Tuning a Model using OpenAI API

LLM model selection criteria and framework

Project 1: Finetuning OpenAI models for the Customer Support use-case

Evaluating Finetuned OpenAI Model: A Step by Step Guide

Open-Source vs. Closed-Source Models in Generative AI

Basic Prompt Engineering Techniques

Introduction to Vector Embeddings

Quantization

Hugging Face Models : An Introduction

Hugging Face Datasets : An Introduction

How to use BERT for simple tasks

HuggingFace Exercise

Demo : Hugging Face AutoModel

Customer Support Ticket Tagging

Advanced Fine-tuning Techniques

Finetuning Llama 3.2 for Customer Support

Merge LoRa adapter model with Base model

Week 2: Session Recording

Optimization Methods for LLMs (PPO, DPO)

DPO optimized Fine-Tuning for Mistral 7B for Organizational Security Protocols

Project 2: Fine-Tuning a Hugging Face Model for Customer Support or Organizational Use Case

Week 2: Streamlit Session

Introduction to RAG

Retrieval Augmented Generation

Vector Database

Introduction to LangChain

Introduction to Langchain

Personal Resource Assistant using Langchain

Retrieval Optimization Techniques

Hybrid Search and Re-ranking Optimization

Memory in LLMs

Finetuning a Vector Embeddings Model

Introduction to LlamaIndex with Qdrant vector database and Cross-encoder Re-ranking models

No Code RAG: RAG using OpenAI Assistants

Evaluating RAG results

Week 3: Discussion on RAG Architectures, Designs and Methods

Week 3: Live Session PPT

Project 3: Building an Optimized RAG Pipeline for Legal Query Resolution

AI Agents : An Introduction

Introduction to Agents

Email Generating Agent with CrewAI

Tools in AI Agents

Multi AI Agent Blog Generator using CrewAI

LangChain Agents

LlamaIndex Agents

LangGraph Agents

Agentic RAG with Phidata

Serving AI Agent with FastAPI

Router in Agentic RAG

Human-in-Loop workflows for Agents

Text to SQL

Corrective RAG (CRAG)

Project 4: Context-Aware AI Email Assistant

Project 5: Conversational BI Agent

LLM Model Serving

Hugging Face Inference Endpoints

GGUF (GPT-Generated Unified Format)

Llama.cpp -> Conversion from .safetensors to .gguf

Ollama: Running Large Language Models Locally with Ease

LLM Evaluation

LLM Evaluation PPT

vLLM: Enabling faster inference and serving for LLMs

Docker and Docker Compose

AWS Deployment

Cerebrium: Serverless Model Deployment

AWS Bedrock