veryluckyxyz 的提交内容

A Case Study in CUDA Kernel Fusion

Lessons from the trenches on reproducible evaluation of language models

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

Zero-Shot Tokenizer Transfer

An Empirical Model of Large-Batch Training

Gradient Diversity: A Key Ingredient for Scalable Distributed Learning

Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models

Automatically Detecting Under-Trained Tokens in Large Language Models

Large Language Models for Data Annotation: A Survey

Refusal in LLMs is mediated by a single direction

Automated Multi Agent Chat

Orca: A Distributed Serving System for Transformer-Based Generative Models

Understanding Emergent Abilities of Language Models from the Loss Perspective

LoRA+: Efficient Low Rank Adaptation of Large Models

Does Transformer Interpretability Transfer to RNNs?

MiniCPM: Potential of Small Language Models W Scalable Training Strategies

Building BerkeleyDB

Rotational Equilibrium: How Weight Decay Balances Learning Across NeuralNetworks

Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference

Bad arguments against a universal basic income