kyo-takano / chinchillaLinks
A toolkit for scaling law research ⚖
☆55Updated last year
Alternatives and similar repositories for chinchilla
Users that are interested in chinchilla are comparing it to the libraries listed below
Sorting:
- ☆53Updated last year
- Simple and efficient pytorch-native transformer training and inference (batched)☆79Updated last year
- Language models scale reliably with over-training and on downstream tasks☆99Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆88Updated last year
- ☆51Updated 2 years ago
- Triton Implementation of HyperAttention Algorithm☆48Updated 2 years ago
- ☆124Updated last year
- Using FlexAttention to compute attention with different masking patterns☆47Updated last year
- ☆53Updated 2 years ago
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆75Updated last year
- ☆38Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated last year
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆73Updated last year
- ☆92Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆135Updated last year
- ☆150Updated 2 years ago
- ☆57Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆87Updated 3 years ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆186Updated 2 weeks ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆247Updated 7 months ago
- Understand and test language model architectures on synthetic tasks.☆251Updated 3 weeks ago
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆137Updated last year
- Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models☆68Updated 9 months ago
- ☆20Updated 2 years ago
- Muon fsdp 2☆52Updated 5 months ago
- ☆45Updated 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
- Griffin MQA + Hawk Linear RNN Hybrid☆88Updated last year
- Awesome Triton Resources☆39Updated 9 months ago
- Experiment of using Tangent to autodiff triton☆82Updated 2 years ago