Prajwalgn-07 / GenerativeAIWithLLM

GenerativeAIWithLLM

Certificate

Week1

Week1 Lab

Transformer Architecture

• Attention is all you need
• BLOOM: Big 176B Model
  • Overview -Vector Space Model

Pre-training and scaling laws

• Scaling laws for neural language models

Model architectures and pre-training objectives

• What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization
• HuggingFace Tasks
• Model Hub
• LLaMA: Open and Efficient Foundation Language Models

Scaling laws and compute-optimal models

• Language Models are Few-Shot Learners
• Training Compute-Optimal Large Language Models
• BloombergGPT: A Large Language Model for Finance

Hand written notes

Week2

Week2 Lab

Multi-task, instruction fine-tuning

• Scaling Instruction-Finetuned Language Models
• Introducing FLAN: More generalizable Language Models with Instruction Fine-Tuning

Model Evaluation Metrics

• HELM - Holistic Evaluation of Language Models
• General Language Understanding Evaluation (GLUE) benchmark
• SuperGLUE
• ROUGE: A Package for Automatic Evaluation of Summaries
• Measuring Massive Multitask Language Understanding (MMLU)
• BigBench-Hard - Beyond the Imitation Game: Quantifying and Extrapolating the Capabilities of Language Models

Parameter- efficient fine tuning (PEFT)

• Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning
• On the Effectiveness of Parameter-Efficient Fine-Tuning

LoRA

• LoRA Low-Rank Adaptation of Large Language Models
• QLoRA: Efficient Finetuning of Quantized LLMs

Prompt tuning with soft prompts

• The Power of Scale for Parameter-Efficient Prompt Tuning

Week3

Week3 Lab

Reinforcement Learning from Human-Feedback (RLHF)

• Training language models to follow instructions with human feedback
• Learning to summarize from human feedback

Proximal Policy Optimization (PPO)

• Proximal Policy Optimization Algorithms
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Scaling human feedback

• Constitutional AI: Harmlessness from AI Feedback

Advanced Prompting Techniques

• Chain-of-thought Prompting Elicits Reasoning in Large Language Models
• PAL: Program-aided Language Models
• ReAct: Synergizing Reasoning and Acting in Language Models

LLM powered application architectures

• LangChain Library (GitHub)
• Who Owns the Generative AI Platform?

Credits:

• Deep Learning.ai