JonasGeiping / crammingLinks
Cramming the training of a (BERT-type) language model into limited compute.
☆1,349Updated 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☆1,009Updated last year
- maximal update parametrization (µP)☆1,599Updated last year
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆969Updated last year
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆871Updated last year
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆634Updated 2 years ago
- Language Modeling with the H3 State Space Model☆518Updated last year
- 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…☆1,582Updated last year
- Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"☆1,063Updated last year
- Convolutions for Sequence Modeling☆898Updated last year
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways☆824Updated 2 years ago
- 🤖 A PyTorch library of curated Transformer models and their composable components☆895Updated last year
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,282Updated 9 months ago
- Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.☆1,007Updated last year
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,131Updated last year
- What would you do with 1000 H100s...☆1,100Updated last year
- Library for 8-bit optimizers and quantization routines.☆778Updated 3 years ago
- minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.☆474Updated 2 years ago
- Task-based datasets, preprocessing, and evaluation for sequence models.☆586Updated 2 weeks ago
- ☆2,882Updated 2 weeks ago
- Foundation Architecture for (M)LLMs☆3,113Updated last year
- ☆545Updated last year
- Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging F…☆575Updated last year
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆651Updated 8 months ago
- Code for the ALiBi method for transformer language models (ICLR 2022)☆542Updated last year
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,614Updated 3 months ago
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆600Updated last year
- A modular RL library to fine-tune language models to human preferences☆2,348Updated last year
- Organize your experiments into discrete steps that can be cached and reused throughout the lifetime of your research project.☆562Updated last year
- The repository for the code of the UltraFastBERT paper☆519Updated last year
- A prize for finding tasks that cause large language models to show inverse scaling☆615Updated last year