Skip to main content
Spring-2024: LLM Projects Bootcamp
0%
Previous
Course data
Introduction
Zoom for Remote Participation
Project 1: Searching for meaning
Slack Invite Link
Glossary
Announcements
Day 1: Semantic Search
Lab 1: Getting started with Semantic Search
Sentence Bert Website
Day 1 Lesson Plan
MTEB Leaderboard for Sentence Embeddings
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Matryoshka Representation Learning
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
Transformers explained
Peter Bloem: Transformers from scratch
Jay Alammar: The Illustrated Transformer
Attention Networks: A simple way to understand Self Attention
Day 2: Attention is all you need
Attention is all you need
Summer 2024: Top 3 AI predictions
CO-STAR framework for systematic prompting
Day 3: Streamlit & Chainlit
Streamlit
Chainlit
Day 3: ANN Methods & Vector databases
Scikit-Learn: Nearest Neighbors
Faiss
Hnswlib
ANN Benchmarks
Qdrant
Annoy
Weaviate
Milvus
Day 3: Promptly Done
CO-STAR Framework for prompting
Winning a prompt engineering competition
Prompting Guide
Clustering the old faithful geyser
Day 3: RAG
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Ragas: Evaluating RAG
Awesome-LLM-RAG Github
Day 4: Visual Language Understanding
Study the SwinTransformer & TnT papers
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (copy)
[VIT]: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Swin transformer
Transformer in Transformer
Recap of Convolutional Neural Networks
Video: Visual Transformers
BERT: Paper reading
Day 4: Partial solution to project 1
Partial solution to the bootcamp project 1
Day 4: Ray Framework & Ray Serve
[Arxiv paper] Ray: A Distributed Framework for Emerging AI Applications
[Textbook] Learning Ray
Ray Framework Portal
Ray Youtube Channel
Understanding the Ray Serve Framework
Day 5: Visual Embeddings & Image Captioning
CLIP: Connecting text and images
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation (copy)
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models (copy)
LLaVA: Large Language and Vision Assistant
Encoders, Contrastive Learning & Sentence Encoder
CLIP Paper Reading
BLIP Paper Reading
BLIP-2 Paper Reading
Partial Solution Walkthrough, Approximate k-NN Explained
Jenkins
Jenkins portal
Jenkins YouTube Channel
Learn to use Jenkins
Spark & PySpark
Learn PySpark
Day 6: LLaVA - Visual Instruction Tuning
Llava Github
Visual Instruction Tuning
Improved Baselines with Visual Instruction Tuning
Llava-Next
Llava-RLHF
Llava-med
How to Fine-Tune LLaVA on a Custom Dataset
Day 7: Document AI
Fine-tuning Donut
Reincarnation of scientific documents
Fine-tune model for Document Question Answering
Huggingface blog: Accelerating Document AI
Rich feature hierarchies for accurate object detection and semantic segmentation
Fast R-CNN
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
OCR-free Document Understanding Transformer
Nougat: Neural Optical Understanding for Academic Documents
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
PubTables-1M: Towards comprehensive table extraction from unstructured documents
TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes
DiT: Self-supervised Pre-training for Document Image Transformer
Document AI with Transformers
"Awesome" Document Understanding
Document AI: Fine-tuning Donut for document-parsing using Hugging Face Transformers
Document Question Answering
PaddleOCR
Tesseract
EasyOCR
MMOCR
Explaining methods of Document AI
Day 9: Segmentation
Segment an original image with U-Net
Segment Anything
Grounded Segment Anything Demo
Grounded SAM
Yolo segmentation
FastSAM (CNN based Segment Anything Model) Github
U-Net: Convolutional Networks for Biomedical Image Segmentation
[DETR] End-to-End Object Detection with Transformers
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
Segment Anything
Fast Segment Anything
Huggingface Image Segmentation
Day 10: Diffusion Models
Denoising Diffusion Probabilistic Models
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
High-Resolution Image Synthesis with Latent Diffusion Models
SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
"Awesome" Diffusion Models (Curated List)
Coding Stable Diffusion from scratch in PyTorch
Lil'Log: What are diffusion models
Huggingface Diffusers
Day 12: LLM for Code Generation
Talking to the FoodMart database
Vanna: Chat with your database
Data Herald
SqlCoder
Foundational Research Papers
Attention is all you need (copy)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Sentence Bert
[VIT]: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
CLIP: Connecting text and images
(CLIP): Learning Transferable Visual Models From Natural Language Supervision
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
LLaVA: Large Language and Vision Assistant (copy)
Language Models: Foundational Papers
Userful Web Docs
Visual Studio
Spark
PyTorch
Numpy
Scikit-Learn
Huggingface
Mathplotlib
Next
Side panel
Categories
All categories
Data Science
Home
Upcoming Courses
Schedule
Teaching Faculty
Testimonials
Contact Us
Log in
Username
Username
Password
Password
Forgot your password?
Log in
Categories
Collapse
Expand
All categories
Data Science
Home
Upcoming Courses
Schedule
Teaching Faculty
Testimonials
Contact Us
Course info
Spring-2024: LLM Projects Bootcamp
Teacher:
Asif Qamar
Skill Level
:
Beginner
Tuition
:
US $1600
