New batches start 11 August 2026. Enrol now →
Maruti AI Technology Enrol now

← Generative AI & Large Language Models

Generative AI & Large Language Models

Large Language Model

Fine-tune LLMs with LoRA and QLoRA, then build multi-agent AI systems

Go beyond using LLMs to building and fine-tuning them: apply LoRA and QLoRA to adapt open-source models, benchmark them against frontier LLMs, and build multimodal chatbots with Gradio. You'll also design autonomous multi-agent systems where models collaborate on real tasks.

25h
of content
9
modules
128
lessons
Fees from
₹8,000

per level · 3 levels · complete programme ₹33,000

Duration
7 mo
Enrol now Talk to us first

Fees by level

Start at any level, or take the complete programme. The fee you pay for a level is locked for you.

LevelWhat it coversDurationFee
Beginner Start from zero 2 mo ₹8,000
Intermediate Build working projects 2 mo ₹11,000
Advanced Get job-ready 3 mo ₹14,000
Complete programme (all levels) ₹33,000

All fees are in Indian Rupees and include applicable taxes. See our pricing & payment terms.

The complete curriculum

This is the entire syllabus — all 9 modules and 128 lessons, in the order you'll learn them. Nothing hidden.

↓ Download full curriculum (PDF)
01 Introduction to Course 1 lesson ▶
  1. 1.1Introduction to course LLM Engineering
02 Building LLM Products 17 lessons ▶
  1. 2.1Introduction to Large Language model engineering
  2. 2.2Ollama setup - windows
  3. 2.3Ollama setup Mac
  4. 2.4Building LLM Applications & best practises
  5. 2.5Key Skills & Tools for AI development
  6. 2.6Understanding frontier models gpt, claude, open source llms
  7. 2.7Power of local llms - hindi tutor
  8. 2.8Creating AI Powered Web Summarizer using Gemini and BS4
  9. 2.9Comparing LLM models
  10. 2.10Leveraging GPTs canvas feature
  11. 2.11Gemini vs Cohere for analytical tasks
  12. 2.12Evaluating metaAI and perplexity
  13. 2.13Introduction to transformers
  14. 2.14Enhancing LLM reliability through prompt engineering
  15. 2.15Understanding llm parameters
  16. 2.16Understanding gpt tokenization
  17. 2.17Claude 3.5s Alignment and Artifact Creation
03 Build a multimodal chatbot : LLMS, Agents, Gradio UI 9 lessons ▶
  1. 3.1Building MultiModal Chatbots
  2. 3.2Mastering multiple AI APIs
  3. 3.3Building Advanced AI Assistants with LLMs
  4. 3.4Building Multimodal AI Assistants
  5. 3.5Creating Adversarial AI Conversations with OpenAI & Claude
  6. 3.6Introduction to Gradio
  7. 3.7Implementing Streaming Responses from LLM APIs
  8. 3.8Advanced Chatbot Development
  9. 3.9Practical Implementation - Chatbot Creation
04 Open Source Gen AI:Build Autonomous Solutions with Gen AI 14 lessons ▶
  1. 4.1Getting Started with Hugging Face
  2. 4.2Exploring Hugging Face
  3. 4.3Google Colab Free Cloud platform for ML
  4. 4.4Running AI Models with Google Colab & Hugging Face
  5. 4.5Using Google Colab+HuggingFace
  6. 4.6Hugging Face Transformers for AI Tasks
  7. 4.7Hugging Face Pipelines Simplifying AI Tasks
  8. 4.8Tokenization for LLMs
  9. 4.9Tokenization in Modern AI LLAMA 3.1
  10. 4.10Comparing Tokenizers in Open source AI Models
  11. 4.11Efficient Inference with Open Source LLMs on Hugging Face
  12. 4.12Efficiently Running LLMs with Quantisation
  13. 4.13Combining Frontier & Open Source Models for Audio- Text
  14. 4.14Building synthetic data for AI Model Development
05 LLM Showdown:Evaluating Models 22 lessons ▶
  1. 5.1Choosing b w open source & closed source llms
  2. 5.2Scaling Laws, Model Size and Evaluating LLM Performance
  3. 5.3Evaluating Real World LLMs beyond Benchmarks
  4. 5.4Choosing the Best LLM for Coding Projects
  5. 5.5Closed vs Open LLMs
  6. 5.6How to compare Open Source Language Models
  7. 5.7Human Evaluation of LLMs with Chatbot Arena
  8. 5.8How LLMS are transforming industries
  9. 5.9AI Powered Python to C++
  10. 5.10Python to C++ Code Implementation
  11. 5.11Comparing GPT-4 and Claude 3.5 Sonnet for code generation
  12. 5.12GPT vs Claude Code Generation
  13. 5.13Leveraging LLMs for Code Optimisation
  14. 5.14How LLMs handle complex code conversion tasks
  15. 5.15Claude vs Python for Code Generation
  16. 5.16Building LLM powered Code Generation UIs
  17. 5.17Open Source LLMs for Code Generation Hugging Face Endpoints Explored
  18. 5.18Deploying Code Generation Models with Hugging Face Inference Endpoints
  19. 5.19Building Hybrid LLM Systems for Code Conversion
  20. 5.20AI Code Generation Comprehensive Comparison
  21. 5.21Evaluating Code Generation Models
  22. 5.22Evaluating LLM Performance in Real World Applications
06 Mastering RAG 11 lessons ▶
  1. 6.1What is RAG(Retrieval Augmented Generation)
  2. 6.2Building a RAG System from Scratch
  3. 6.3RAG Practical Implementation
  4. 6.4Vector Embeddings & their role in RAG
  5. 6.5Simplifying RAG with LangChain
  6. 6.6Effective Text Splitting for RAG Applications
  7. 6.7Preparing Data for Vector Databases in RAG Applications
  8. 6.8Understanding Vector Embeddings & RAG Systems
  9. 6.9Visualising Vector Embeddings
  10. 6.10RAG Hands On Codes
  11. 6.11Troubleshooting & optimising RAG Systems
07 Fine Tuning Frontier LLMs using LoRA , QLoRA 19 lessons ▶
  1. 7.1Finetuning LLMs - From Inference to Training
  2. 7.2Finding and Crafting Datasets for LLM Fine Tuning Sources & Techniques
  3. 7.3Evaluating LLMs
  4. 7.4LLM Deployment Pipeline
  5. 7.5Prompting, RAG & Fine Tuning When to use which approach
  6. 7.6How to create a balanced dataset for LLM Training
  7. 7.7Building Effective ML Baselines for NLP Tasks
  8. 7.8Feature Scaling in ML
  9. 7.9Linear Regression in ML
  10. 7.10Random Forest Regression
  11. 7.11Bag of Words NLP Implementing Count Vectorizer for Text Analysis in ML
  12. 7.12Support Vector Regression in ML
  13. 7.13Comparing GPT-4 Mini to Traditional AI Models in price estimation
  14. 7.14LLMs vs Traditional ML
  15. 7.15LoRA, QLoRA, PEFT
  16. 7.16Fine Tuning GPT Models with Open API & Monitoring Tools
  17. 7.17Mastering LLM Fine Tuning
  18. 7.18Monitoring & Interpreting LLM Fine tuning process
  19. 7.19Why fine tuning LLMs might fail and how to overcome it
08 Fine-tuned Open Source Models to compete with Frontier Models 20 lessons ▶
  1. 8.1Parameter Efficient Fine Tuning for LLMs
  2. 8.2Fine Tuning LLMs with Limited GPU Memory using QLoRA
  3. 8.3Hyperparameters & best practices in LoRA QLoRA
  4. 8.4Reducing LLM Size without sacrificing performance
  5. 8.5Advanced Quantisation Techniques for reducing LLM Memory Footprint
  6. 8.6Tokenization strategies in LLMs
  7. 8.7Efficient Loading, Tokenization and Fine Tuning of LLaMA 3.1
  8. 8.8Navigating HuggingFace_s LLM Leaderboard & selecting base models
  9. 8.9Impact of Quantization on LLM Performance
  10. 8.10Optimising LLAMA to compete with GPT 4
  11. 8.11Epochs and training dynamics in LLM Fine Tuning
  12. 8.12Setting optimal hyperparameters for LLM Fine Tuning
  13. 8.13Monitoring & Optimising LLM Fine Tuning with W&B
  14. 8.14Tracking & visualising LLM Fine tuning Progress
  15. 8.15Visualising Model training with W&B , Hugging Face
  16. 8.16End to End LLM Fine tuning for Business Solutions
  17. 8.17Training Process in LLMs
  18. 8.18Token Prediction & Real Time Monitoring in LLM Fine Tuning
  19. 8.19Fine Tuned Models vs Frontier Models & Performance Optimisation
  20. 8.20Evaluating & Comparing Fine tuned LLMs
09 Build autonomous multi agent systems collaborating with models 15 lessons ▶
  1. 9.1LLMS with Multi Agent & Serverless Deployment
  2. 9.2Efficiently running LLMs in cloud environments
  3. 9.3Deploying AI Models as Serverless APIs in the Cloud
  4. 9.4Building production ready RAG Systems
  5. 9.5Understanding Vector spaces in RAG
  6. 9.6RAG Value proposition & core mechanics
  7. 9.7Hybrid Ensemble architecture for pricing
  8. 9.8Mastering Structured Outputs for LLM Automation
  9. 9.9Mastering structured output with GPT-4
  10. 9.10Defining Agentic AI Hallmarks
  11. 9.11The architecture of Autonomy
  12. 9.12Agents Core Loop Building from scratch
  13. 9.13Gradio AI Interface
  14. 9.14Real Time Monitoring for autonomous AI agents
  15. 9.15Autonomus agent framework

Tools you'll use

PythonLangChainHugging FaceOpenAI APIRAGGradioC++Canva

Every course includes

Live, instructor-led classes Course materials & lab access Doubt-clearing sessions Final assessment + one free re-attempt Verifiable certificate

How certification works

Related courses

Generative AI & Large Language Models

AI Video Generation

Create AI-generated films, transformation videos and visual effects

from ₹3,500· 3 levels
4 mo
Generative AI & Large Language Models

Gen AI

Build RAG chatbots and LLM apps with LangChain, from Python fundamentals up

from ₹7,500· 3 levels
8 mo
Generative AI & Large Language Models

Gen AI Tools

Master ChatGPT and AI image tools for content, branding and SEO work

from ₹3,500· 3 levels
4 mo