calculated | content

WeightWatcher, HTSR theory, and the Renormalization Group

Fine-Tuned Llama3.2: Bad Instructions ?

What’s instructive about Instruct Fine-Tuning: a weightwatcher analysis

Describing Double Descent with WeightWatcher

SVDSmoothing LLM Layers with WeightWatcher

Evaluating LLMs with WeightWatcher Part III: The Magic of Mistral, a Story of Dragon Kings

Evaluating Fine-Tuned LLMs with WeightWatcher Part II: PEFT / LoRa Models

Evaluating Fine-Tuned LLMs with WeightWatcher

WeightWatcher new feature: fix_fingers=’clip_xmax’

WeightWatcher 0.7: March 2023