U01M02-Foundations-to-Build-a-Large-Language-Model-From-Scratch

U01M01-Python-Environment-Setup-Video

U02M03-Converting-tokens-into-token-IDs

U02M02-Tokenizing-text

U02M04-Adding-special-context-tokens

U02M05-Byte-pair-encoding

U02M07-Creating-token-embeddings

U02M06-Data-sampling-with-a-sliding-window

U02M08-Encoding-word-positions

U03M03-A-simple-self-attention-mechanism-without-trainable-weights-Part-2

U03M02-A-simple-self-attention-mechanism-without-trainable-weights-Part-1

U03M01-Prerequisites-to-Chapter-3

U03M05-Implementing-a-compact-self-attention-Python-class

U03M07-Masking-additional-attention-weights-with-dropout

U03M06-Applying-a-causal-attention-mask

U03M04-Computing-the-attention-weights-step-by-step

U03M08-Implementing-a-compact-causal-self-attention-class

U03M09-Stacking-multiple-single-head-attention-layers

U04M02-Coding-an-LLM-architecture

U03M10-Implementing-multi-head-attention-with-weight-splits

U04M03-Normalizing-activations-with-layer-normalization

U04M05-Adding-shortcut-connections

U04M04-Implementing-a-feed-forward-network-with-GELU-activations

U04M06-Connecting-attention-and-linear-layers-in-a-transformer-block

U04M07-Coding-the-GPT-model

U04M08-Generating-text

U04M01-Prerequisites-to-Chapter-4

U05M01-Prerequisites-to-Chapter-5

U05M02-Using-GPT-to-generate-text

U05M03-Calculating-the-text-generation-loss-cross-entropy-and-perplexity

U05M06-Decoding-strategies-to-control-randomness

U05M07-Temperature-scaling

U05M04-Calculating-the-training-and-validation-set-losses

U05M08-Top-k-sampling

U05M09-Modifying-the-text-generation-function

U05M05-Training-an-LLM

U05M10-Loading-and-saving-model-weights-in-PyTorch

U05M11-Loading-pretrained-weights-from-OpenAI

U06M01-Prerequisites-to-Chapter-6

U06M02-Preparing-the-dataset

U06M04-Initializing-a-model-with-pretrained-weights

U06M03-Creating-data-loaders

U06M05-Adding-a-classification-head

U06M08-Using-the-LLM-as-a-spam-classifier

U06M06-Calculating-the-classification-loss-and-accuracy

U07M01-Preparing-a-dataset-for-supervised-instruction-fine-tuning

U06M07-Fine-tuning-the-model-on-supervised-data

U07M03-Creating-data-loaders-for-an-instruction-dataset

U07M04-Loading-a-pretrained-LLM

U07M06-Extracting-and-saving-responses

U07M05-Fine-tuning-the-LLM-on-instruction-data

U07M07-Evaluating-the-fine-tuned-LLM

U07M02-Organizing-data-into-training-batches