Scribd
Upload
4 views2 pages

Generative AI Roadmap

The document outlines a comprehensive roadmap for understanding Generative AI, covering fundamentals such as artificial neural networks, transformer architectures, and tokenization. It includes sections on large language models, model training techniques, evaluation metrics, and best practices for backend hosting and serving. Additionally, it addresses production considerations like monitoring, scaling, and containerization.

Uploaded by

22metadata
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views2 pages

Generative AI Roadmap

The document outlines a comprehensive roadmap for understanding Generative AI, covering fundamentals such as artificial neural networks, transformer architectures, and tokenization. It includes sections on large language models, model training techniques, evaluation metrics, and best practices for backend hosting and serving. Additionally, it addresses production considerations like monitoring, scaling, and containerization.

Uploaded by

22metadata
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Roadmap

Whats Gen AI ?
Fundamentals
ANN-Artificial neural networks basics
Transformer and encoder-decoder architectures
Tokenization
Attention mechanism
Differences between GPT, BERT, T5, etc.
Large Language Models (LLMs)
Overview of LLMs
Open-source LLMs & Hugging Face
LangChain
Vector Databases (Vector DBs)
Llama Index
Gen AI Workflow
Model Training
Training locally ,via API
Pytorch & CUDA
System optimization for LLMs (Quantization, LoRA, PEFT, etc.)
Finetuning the LLM
Reinforcement Learning from Human Feedback (RLHF)
Evaluation & Metrics
Model evaluation (BLEU, ROUGE, perplexity, etc.)
Prompt engineering strategies
Inference : Running and testing a trained model
RAG (Retrieval Augmented Generation)
Backend Hosting & Serving (FastAPI )
Production best practices
Monitoring, logging, A/B testing of Gen AI applications
Scaling with GPUs/TPUs
Containerization (Docker) on Azure VMs

You might also like