|
Adapter Layer
|
Medium
|
End-to-End
|
|
|
Attention Block with RoPE
|
Hard
|
End-to-End
|
|
|
Autoencoder
|
Medium
|
End-to-End
|
|
|
Beam Search
|
Hard
|
End-to-End
|
|
|
Binary Classifier
|
Easy
|
End-to-End
|
|
|
BPE Encode Text
|
Hard
|
End-to-End
|
|
|
Causal Attention Lab
|
Medium
|
End-to-End
|
|
|
Causal LM Forward Pass
|
Medium
|
End-to-End
|
|
|
Causal LM with KV Cache Generation
|
Hard
|
End-to-End
|
|
|
Causal RoPE and SwiGLU Block
|
Hard
|
End-to-End
|
|
|
Causal Self-Attention Block
|
Medium
|
End-to-End
|
|
|
Cross-Attention Block
|
Medium
|
End-to-End
|
|
|
Data Augmentation
|
Medium
|
End-to-End
|
|
|
DDPM Sampler Loop
|
Hard
|
End-to-End
|
|
|
DDPM Training Step End-to-End
|
Medium
|
End-to-End
|
|
|
Decision Boundary Lab
|
Medium
|
End-to-End
|
|
|
Denoising Autoencoder Lab
|
Medium
|
End-to-End
|
|
|
Distributed Training Step End-to-End
|
Hard
|
End-to-End
|
|
|
Encoder-Decoder Beam Search
|
Hard
|
End-to-End
|
|
|
Encoder-Decoder Greedy Decode
|
Medium
|
End-to-End
|
|
|
Encoder-Decoder Transformer Forward Pass
|
Hard
|
End-to-End
|
|
|
Eval Loop with Metrics
|
Medium
|
End-to-End
|
|
|
Feature Normalization Pipeline
|
Easy
|
End-to-End
|
|
|
Gradient Accumulation
|
Medium
|
End-to-End
|
|
|
Gradient Clipping
|
Easy
|
End-to-End
|
|
|
GRU Sequence Forward Pass
|
Medium
|
End-to-End
|
|
|
Image Pattern Lab
|
Medium
|
End-to-End
|
|
|
Learning Rate Scheduler
|
Medium
|
End-to-End
|
|
|
Linear Regression
|
Easy
|
End-to-End
|
|
|
Logistic Regression From Scratch
|
Easy
|
End-to-End
|
|
|
LSTM Sequence Forward Pass
|
Medium
|
End-to-End
|
|
|
Mini-Batch Training
|
Medium
|
End-to-End
|
|
|
MLM Evaluation: Masked Accuracy
|
Medium
|
End-to-End
|
|
|
MLM Forward Pass
|
Medium
|
End-to-End
|
|
|
MLM Forward with Tied Output Head
|
Medium
|
End-to-End
|
|
|
MLM Masking Strategy
|
Medium
|
End-to-End
|
|
|
Model Checkpointing
|
Easy
|
End-to-End
|
|
|
Multi-Class Classifier
|
Easy
|
End-to-End
|
|
|
Multi-Head Attention Block
|
Hard
|
End-to-End
|
|
|
Nucleus Sampling Generation Loop
|
Hard
|
End-to-End
|
|
|
One RNN Language-Model Training Step
|
Hard
|
End-to-End
|
|
|
Patch Embedding with CLS Token
|
Medium
|
End-to-End
|
|
|
Polynomial Regression
|
Medium
|
End-to-End
|
|
|
RNN Sequence Forward Pass
|
Medium
|
End-to-End
|
|
|
Self-Attention Layer
|
Hard
|
End-to-End
|
|
|
Sequence Classifier
|
Medium
|
End-to-End
|
|
|
Simple CNN
|
Medium
|
End-to-End
|
|
|
Simple GAN Generator
|
Hard
|
End-to-End
|
|
|
Skip Connection Block
|
Medium
|
End-to-End
|
|
|
Tokenize and Pad Batch
|
Medium
|
End-to-End
|
|