Course Objectives

[TM-LLM-Embeddings] (376)

I can identify various types of embeddings (tokens, hidden states, output, key, and query) in a language model and explain their purpose.

[TM-SelfAttention] (376)

I can explain the purpose and components of a self-attention layer (key, query, value; multi-head attention; positional encodings).

[TM-TransformerDataFlow] (376)

I can identify the shapes of data flowing through a Transformer-style language model.

[TM-Scaling] (376)

I can analyze how the computational requirements of a model scale with number of parameters and context size.

[TM-LLM-Generation] (376)

I can extract and interpret model outputs (token logits) and use them to generate text.

[TM-LLM-Compute] (376)

I can analyze the computational requirements of training and inference of generative AI systems.

[OG-Eval-Experiment] (both)

I can design and execute valid experiments to evaluate model performance.

Criteria

• I partition data appropriately (train/val/test) before any model fitting.
• I can explain why we need held-out data and what goes wrong without it.
• I can select metrics appropriate to the task and stakeholder needs.
• I can interpret learning curves (loss/metric vs epoch) to understand training dynamics.

Assessed in

• notebook Train a simple image classifier
• notebook Regression in scikit-learn
• notebook Classification in scikit-learn
• notebook MNIST with PyTorch

[OG-LLM-Prompting] (376)

I can critique and refine prompts to improve the quality of responses from an LLM.

[OG-LLM-Tokenization] (376)

I can explain how inputs get chunked into tokens, how outputs are generated token by token, and how this affects usage of the model.

[OG-LLM-ConversationAsDocument] (376)

I can explain how a conversation with an LLM can be represented as a carefully structured document, including system messages, tool calls, and multimodal inputs and outputs.

[OG-LLM-Advanced] (376)

I can apply techniques such as Retrieval-Augmented Generation, in-context learning, tool use, and multi-modal input to solve complex tasks with an LLM.

[OG-LLM-Eval] (376)

I can apply and critically analyze evaluation strategies for generative models.

[OG-LLM-Train] (376)

I can describe the overall process of training a state-of-the-art dialogue LLM.

[OG-SelfSupervised] (376)

I can explain how self-supervised learning can be used to train foundation models on massive datasets without labeled data.

[OG-Theory-Feedback] (376)

I can explain how feedback tuning can improve the performance and reliability of a model / agent.

[Overall-Impact] (both)

I can analyze real-world situations to identify potential negative impacts of AI systems.

Criteria

• Given a scenario, I can identify at least two distinct stakeholder groups who might be affected differently.
• I can articulate how training data distribution might differ from deployment conditions.
• I can identify feedback loops where model outputs might affect future training data or user behavior.
• I can flag concerns that warrant careful analysis before deployment.

Assessed in

• activity AI Implications - Topics

[Overall-LLM-Failures] (376)

I can identify common types of failures in LLMs, such as hallucination (confabulation) and bias.