Stanford

entities · 10 notes linked

Related: Large Language Models · Deep Learning · Meta · Open Source AI · Instruction Fine Tuning · AI Agents · Clustering · K Means

Notes

• A detailed example of how to generate your data in parallel with PyTorch Star — Using PyTorch Dataset and DataLoader with multicore parallel data generation
• Aho/Ullman Foundations of Computer Science — Free classic CS theory textbook by Aho and Ullman, out of print since 1992
• Bit Twiddling Hacks — Reference collection of low-level C bit manipulation tricks
• ConvNetJS — JavaScript library for training neural networks in the browser
• DSPy — Python framework replacing prompt engineering with optimizable typed signatures
• Finding the K in K-Means Clustering — Gap statistic method to determine optimal cluster count in k-means
• GitHub - tatsu-lab/stanford_alpaca: Code and documentation to train Stanford's Alpaca models, and generate the data. — Instruction-following LLaMA model fine-tuned via self-instruct data
• Paths to the Future: A Year at Google Brain — Personal account of working at Google Brain on TensorFlow development
• Why LLaMa Is A Big Deal — LLaMA enables GPT-3-class LLM inference on consumer hardware
• elvis (@omarsar0) on X — Stanford CME295 new course on Transformers and LLMs announced