Experiments
Topic

Experiments

Hands-on experiments in LLM fine-tuning, rocket recovery physics, and performance benchmarking.

2 posts · updated weekly
SystemsEngineeringFindingsResearchInference
Most recent
Fine-Tuning Large Language Models: PEFT, LoRA, and QLoRA in Practice
Experiments

Dec 18, 2024 · 4 min read

Fine-Tuning Large Language Models: PEFT, LoRA, and QLoRA in Practice

Full parameter training requires clusters of H100s. Parameter-Efficient Fine-Tuning (PEFT) with low-rank matrix decomposition brings specialized adaptation to a single GPU.

SpaceX Caught a Rocket With the Launch Tower
Experiments

Oct 14, 2024 · 1 min read

SpaceX Caught a Rocket With the Launch Tower

On 13 October 2024, the Super Heavy booster came back to the pad and was caught mid-air by a pair of mechanical arms, on the first attempt.

Sorted by most recent.