JonasGeiping / crammingLinks
Cramming the training of a (BERT-type) language model into limited compute.
☆1,361Updated last year
Alternatives and similar repositories for cramming
Users that are interested in cramming are comparing it to the libraries listed below
Sorting:
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆1,019Updated last year
- maximal update parametrization (µP)☆1,657Updated last year
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆981Updated last year
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆876Updated 2 years ago
- Language Modeling with the H3 State Space Model☆521Updated 2 years ago
- Convolutions for Sequence Modeling☆910Updated last year
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,299Updated last year
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways☆828Updated 3 years ago
- Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackab…☆1,585Updated last year
- Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"☆1,064Updated last year
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆638Updated 2 years ago
- Task-based datasets, preprocessing, and evaluation for sequence models.☆594Updated last week
- A prize for finding tasks that cause large language models to show inverse scaling☆620Updated 2 years ago
- 🤖 A PyTorch library of curated Transformer models and their composable components☆894Updated last year
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,712Updated 2 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,138Updated 2 years ago
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆654Updated last year
- Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.☆1,009Updated last year
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆612Updated last year
- minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.☆490Updated 2 years ago
- What would you do with 1000 H100s...☆1,143Updated 2 years ago
- A repository for research on medium sized language models.☆524Updated 7 months ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆2,508Updated last year
- ☆792Updated last week
- A modular RL library to fine-tune language models to human preferences☆2,374Updated last year
- A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick☆293Updated 2 years ago
- Everything you want to know about Google Cloud TPU☆555Updated last year
- ☆551Updated last year
- Organize your experiments into discrete steps that can be cached and reused throughout the lifetime of your research project.☆565Updated last year
- Finetuning Large Language Models on One Consumer GPU in 2 Bits☆734Updated last year