Excited to teach Advanced NLP at CMU this semester!
Slides are on the course page as the course proceeds:
cmu-l3.github.io/anlp-spring202…
Lectures will be uploaded to Youtube:
youtube.com/playlist?list=…
Sean Welleck
1,429 posts
Sean Welleck
@wellecks
Joined April 2011
- Lecture 11: Reinforcement Learning youtu.be/disWB7qwcOk - RL basics - Reward functions for NLP - Optimizing rewards (policy gradient) - Stabilizing learning (e.g., KL penalty, PPO)Excited to teach Advanced NLP at CMU this semester! Slides are on the course page as the course proceeds: cmu-l3.github.io/anlp-spring202… Lectures will be uploaded to Youtube: youtube.com/playlist?list=…
- Slides for my recent talk on: "Reasoning with inference-time compute" wellecks.com/data/welleck20… Papers: - Lean-STaR: arxiv.org/abs/2407.10040 - Easy-to-hard: arxiv.org/abs/2403.09472 - Compute-optimal inference: arxiv.org/abs/2408.00724 - Meta-generation: arxiv.org/abs/2406.16838
- Lecture 20: Advanced Post-Training youtu.be/yuJUkR2vvJM - Supervised Fine-tuning - Reward Modeling - Reinforcement Learning - Direct Preference OptimizationExcited to teach Advanced NLP at CMU this semester! Slides are on the course page as the course proceeds: cmu-l3.github.io/anlp-spring202… Lectures will be uploaded to Youtube: youtube.com/playlist?list=…
- Lecture 16: Parallelism and Scaling youtu.be/Mpg1YJfAEH0 - Basics of training on one device - Parallelization on multiple devices (e.g., data, tensor, pipeline parallel) - Combining and comparing strategiesExcited to teach Advanced NLP at CMU this semester! Slides are on the course page as the course proceeds: cmu-l3.github.io/anlp-spring202… Lectures will be uploaded to Youtube: youtube.com/playlist?list=…
- Lecture 5: Transformers - Attention - Transformers - Improved transformersExcited to teach Advanced NLP at CMU this semester! Slides are on the course page as the course proceeds: cmu-l3.github.io/anlp-spring202… Lectures will be uploaded to Youtube: youtube.com/playlist?list=…
- What do nucleus sampling, tree-of-thought, and PagedAttention have in common? They're all part of our new survey: "From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models" arxiv.org/abs/2406.16838
- Announcing the L3 Lab at CMU! cmu-l3.github.io We focus on Learning, Language, and Logic, including: - Principles of ML for language - ML in high-trust areas, such as verifying math and programs - ML systems that improve over time Recruiting PhD students for fall 2024!
- Lecture 19: Efficient Inference youtu.be/jbHgzU4r7yU - Basics of efficient LLM inference - Speeding up single-token and sequence generation - Speeding up meta-generation strategiesExcited to teach Advanced NLP at CMU this semester! Slides are on the course page as the course proceeds: cmu-l3.github.io/anlp-spring202… Lectures will be uploaded to Youtube: youtube.com/playlist?list=…
- Lecture 15: Quantization (Guest lecture by @Tim_Dettmers) youtu.be/YXZZaje76r4 - Quantization basics - Quantized foundation models: LLM.int8() - Finetuning foundation models: QLoRA - Quantization and usersExcited to teach Advanced NLP at CMU this semester! Slides are on the course page as the course proceeds: cmu-l3.github.io/anlp-spring202… Lectures will be uploaded to Youtube: youtube.com/playlist?list=…
- Lecture 9: Fine-tuning - Fine-tuning basics - Instruction tuning - Knowledge distillation - Efficient fine-tuning youtube.com/watch?v=3qW996…Excited to teach Advanced NLP at CMU this semester! Slides are on the course page as the course proceeds: cmu-l3.github.io/anlp-spring202… Lectures will be uploaded to Youtube: youtube.com/playlist?list=…
- Lecture 18: Advanced Inference Strategies youtu.be/jNpeYvZtJkw - Parallel, tree search, refinement strategies - Long chain-of-thought - Inference scaling lawsExcited to teach Advanced NLP at CMU this semester! Slides are on the course page as the course proceeds: cmu-l3.github.io/anlp-spring202… Lectures will be uploaded to Youtube: youtube.com/playlist?list=…
- Interested in LLMs and Lean? Check out LLMLean, a tool for using LLMs to suggest proof steps and complete proofs in Lean: github.com/cmu-l3/llmlean Here's an example of using LLMLean with GPT-4o to solve problems from Mathematics in Lean:
00:00 - Teaching a new course on Neural Code Generation with @dan_fried! cmu-codegen.github.io/s2024/ Here is the lecture on pretraining and scaling laws: cmu-codegen.github.io/s2024/static_f…
