JonasGeiping / cramming
Cramming the training of a (BERT-type) language model into limited compute.
☆1,296Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for cramming
- maximal update parametrization (µP)☆1,402Updated 4 months ago
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆970Updated 3 months 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…☆1,535Updated 9 months ago
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆851Updated last year
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways☆821Updated 2 years ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,045Updated 10 months ago
- Language Modeling with the H3 State Space Model☆513Updated last year
- A modular RL library to fine-tune language models to human preferences☆2,213Updated 8 months ago
- Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.☆980Updated 3 months ago
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,502Updated 10 months ago
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,282Updated 2 weeks ago
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆624Updated last year
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆939Updated 9 months ago
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,223Updated last year
- Convolutions for Sequence Modeling☆869Updated 5 months ago
- What would you do with 1000 H100s...☆903Updated 10 months ago
- An open collection of implementation tips, tricks and resources for training large language models☆460Updated last year
- 🤖 A PyTorch library of curated Transformer models and their composable components☆866Updated 7 months ago
- ☆2,686Updated this week
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆2,409Updated 3 months ago
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,041Updated 5 months ago
- Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"☆1,055Updated 8 months ago
- Task-based datasets, preprocessing, and evaluation for sequence models.☆561Updated this week
- ☆1,474Updated 3 weeks ago
- Foundation Architecture for (M)LLMs☆3,034Updated 7 months ago
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆551Updated 4 months ago
- Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch☆1,215Updated 2 years ago
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,624Updated last year
- A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick☆287Updated 11 months ago