epfml / schedules-and-scalingLinks
Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
☆73Updated 7 months ago
Alternatives and similar repositories for schedules-and-scaling
Users that are interested in schedules-and-scaling are comparing it to the libraries listed below
Sorting:
- Language models scale reliably with over-training and on downstream tasks☆97Updated last year
- Stick-breaking attention☆55Updated 2 months ago
- ☆52Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆126Updated 3 weeks ago
- nanoGPT-like codebase for LLM training☆94Updated 2 weeks ago
- ☆31Updated last year
- Exploration of automated dataset selection approaches at large scales.☆41Updated 2 months ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- ☆85Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆59Updated 7 months ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆66Updated 8 months ago
- ☆37Updated last year
- This repo is based on https://github.com/jiaweizzhao/GaLore☆28Updated 8 months ago
- ☆79Updated 9 months ago
- ☆25Updated 3 months ago
- Universal Neurons in GPT2 Language Models☆29Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆62Updated 4 months ago
- ☆26Updated last year
- ☆19Updated 10 months ago
- ☆53Updated 7 months ago
- Understand and test language model architectures on synthetic tasks.☆195Updated 2 months ago
- Sparse Autoencoder Training Library☆50Updated last month
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆67Updated 10 months ago
- ☆92Updated 8 months ago
- ☆45Updated last year
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- ☆33Updated 4 months ago
- Official implementation of "BERTs are Generative In-Context Learners"☆28Updated 2 months ago
- Using FlexAttention to compute attention with different masking patterns☆43Updated 8 months ago
- PyTorch library for Active Fine-Tuning☆77Updated 3 months ago