mlfoundations / scalingLinks
Language models scale reliably with over-training and on downstream tasks
☆99Updated last year
Alternatives and similar repositories for scaling
Users that are interested in scaling are comparing it to the libraries listed below
Sorting:
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆88Updated last year
- Replicating O1 inference-time scaling laws☆91Updated last year
- Simple and efficient pytorch-native transformer training and inference (batched)☆79Updated last year
- Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]☆147Updated last year
- ☆85Updated last year
- ☆108Updated last year
- ☆77Updated last year
- Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models☆48Updated 2 years ago
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated 2 years ago
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆137Updated last year
- Long Context Extension and Generalization in LLMs☆62Updated last year
- [NeurIPS'24 Spotlight] Observational Scaling Laws☆58Updated last year
- Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models☆68Updated 9 months ago
- A toolkit for scaling law research ⚖☆55Updated last year
- ☆75Updated last year
- ☆112Updated last year
- ☆53Updated last year
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆94Updated last year
- Organize the Web: Constructing Domains Enhances Pre-Training Data Curation☆76Updated 9 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated last year
- Self-Alignment with Principle-Following Reward Models☆169Updated 4 months ago
- ☆34Updated 2 years ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆78Updated last year
- ☆45Updated 2 years ago
- ☆51Updated 2 years ago
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆75Updated last year
- ☆91Updated last year
- The repository contains code for Adaptive Data Optimization☆32Updated last year
- ☆99Updated last year
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆63Updated last year