LLM Training & Pre-Training Cheat Sheets

Catastrophic forgetting in fine-tuning cheat sheet

Catastrophic forgetting is the loss of earlier skills after further training. Compare general and task performance before and after fine-tuning.

#LLM Training & Pre-Training

→ Read the article

Fine-Tuning cheat sheet

Fine-tuning shapes how a model responds; new facts belong in retrieval, not in the weights.

#LLM Training & Pre-TrainingAnimated

→ Topic: Fine-Tuning

LoRA vs QLoRA vs full fine-tuning cheat sheet

LoRA fine tuning trains small added weights; QLoRA also reduces base-model memory. Compare both with full fine-tuning and choose a method.

#LLM Training & Pre-Training

→ Read the article

Pre-Training cheat sheet

Pre-training decides what a model knows; every later stage only changes how it uses that knowledge.

#LLM Training & Pre-TrainingAnimated

→ Topic: Pre-Training

Reward Model Architecture cheat sheet

The score only ranks answers, and the policy compounds every bias in it until it learns to game the score.

#LLM Training & Pre-TrainingAnimated

→ Topic: Reward Model Architecture

RLHF cheat sheet

RLHF matches what annotators preferred, so a rising reward score can still hide a worse model.

#LLM Training & Pre-TrainingAnimated

→ Topic: RLHF

Scaling Laws cheat sheet

Scaling laws forecast loss before a run starts; balancing data with size beats adding parameters alone.

#LLM Training & Pre-TrainingAnimated

→ Topic: Scaling Laws

What is fine-tuning? cheat sheet

LLM fine-tuning changes a pre-trained model using task examples. Learn when to use it instead of a better prompt or retrieval.

#LLM Training & Pre-Training

→ Read the article