AI, Deep Learning

Multi Modal: BLIP-2: Part 1
17:55
Multi Modal: BLIP-2: Part 1
Nightmares Pre-Training and Fine-Tuning LLMs
46:31
Nightmares Pre-Training and Fine-Tuning LLMs
Fast Distributed Inference Serving for LLMs
37:10
Fast Distributed Inference Serving for LLMs
LaMA-Adapter Finetuning: Source Code: Paper: PseudoCode
41:10
LaMA-Adapter Finetuning: Source Code: Paper: PseudoCode
LoRA - Low Rank Adaptation of Large Language Model: Source Code
42:04
LoRA - Low Rank Adaptation of Large Language Model: Source Code
Tool Former Source Code: LLM using API
40:02
Tool Former Source Code: LLM using API
SmoothQuant: Migrate Activation Difficulty to Weights
4:50
SmoothQuant: Migrate Activation Difficulty to Weights
SparseGPT : Get Rid of 100 Billion Parameters
1:11:41
SparseGPT : Get Rid of 100 Billion Parameters
Pre-training -LLAMA Source Code-Flash Attention-FSDPStrategy
1:05:39
Pre-training -LLAMA Source Code-Flash Attention-FSDPStrategy
GPTQ: Applied on LLAMA model.
30:32
GPTQ: Applied on LLAMA model.
An AI receptionist system design and open source discussion
15:08
An AI receptionist system design and open source discussion
Segment Anything Research by Meta AI
1:56:22
Segment Anything Research by Meta AI
GPTQ : Post-Training Quantization
55:20
GPTQ : Post-Training Quantization
Alpaca Model Open Source Code : Instruction-Following Model
50:53
Alpaca Model Open Source Code : Instruction-Following Model
HuggingFace: Text Generation Inference: Part 1
1:16:34
HuggingFace: Text Generation Inference: Part 1
OpenAI: Reinforcement Learning from Human Feedback
1:33:33
OpenAI: Reinforcement Learning from Human Feedback
Vision Transformer from Scratch and Training Implementation
2:00:30
Vision Transformer from Scratch and Training Implementation
BERT Architecture Implementation from Scratch
1:49:29
BERT Architecture Implementation from Scratch
Inside the Facebook Recommendation System: How it Works and How it's Designed
45:41
Inside the Facebook Recommendation System: How it Works and How it's Designed
DeepETA: How Uber Predicts Arrival Times Using Deep Learning
17:50
DeepETA: How Uber Predicts Arrival Times Using Deep Learning
Machine Learning System Design: Predicting Real Names from Nicknames
40:09
Machine Learning System Design: Predicting Real Names from Nicknames
MobileVIT 1 and 2 Paper Explained and Implementing in Code
1:33:41
MobileVIT 1 and 2 Paper Explained and Implementing in Code
NextVIT Paper Explained and Code Walkthrough
52:18
NextVIT Paper Explained and Code Walkthrough
MobileNet 1, 2, 3 Paper Explained and Implementation in Code
1:21:30
MobileNet 1, 2, 3 Paper Explained and Implementation in Code
Understanding the RCNN Family of Object Detection Models: From R-CNN to Mask R-CNN
20:06
Understanding the RCNN Family of Object Detection Models: From R-CNN to Mask R-CNN
Deep Learning Data Labeling Techniques Covered in Detail
26:50
Deep Learning Data Labeling Techniques Covered in Detail
EfficientNet Explained and Implementing it in Code
33:35
EfficientNet Explained and Implementing it in Code
Embedding Table Free Recommendation Systems
18:55
Embedding Table Free Recommendation Systems
Distributed Training in Deep Learning
33:06
Distributed Training in Deep Learning
MLOPS: Detecting Illegal Listings Distributed Machine Learning - Amazon Interview Question
46:08
MLOPS: Detecting Illegal Listings Distributed Machine Learning - Amazon Interview Question