PiotrNawrot / nanoT5
Fast & Simple repository for pre-training and fine-tuning T5-style models
β1,003Updated 8 months ago
Alternatives and similar repositories for nanoT5:
Users that are interested in nanoT5 are comparing it to the libraries listed below
- Cramming the training of a (BERT-type) language model into limited compute.β1,331Updated 10 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333β1,103Updated last year
- π€ A PyTorch library of curated Transformer models and their composable componentsβ885Updated last year
- Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"β1,060Updated last year
- The official implementation of βSophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-trainingββ957Updated last year
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascriptβ576Updated 10 months ago
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorchβ864Updated last year
- Fine-tune mistral-7B on 3090s, a100s, h100sβ711Updated last year
- YaRN: Efficient Context Window Extension of Large Language Modelsβ1,479Updated last year
- batched lorasβ341Updated last year
- A prize for finding tasks that cause large language models to show inverse scalingβ610Updated last year
- Generate textbook-quality synthetic LLM pretraining dataβ498Updated last year
- Tune any FALCON in 4-bitβ466Updated last year
- What would you do with 1000 H100s...β1,043Updated last year
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorchβ641Updated 4 months ago
- Extend existing LLMs way beyond the original training length with constant memory usage, without retrainingβ697Updated last year
- An open collection of implementation tips, tricks and resources for training large language modelsβ472Updated 2 years ago
- Salesforce open-source LLMs with 8k sequence length.β717Updated 3 months ago
- Minimalistic large language model 3D-parallelism trainingβ1,836Updated this week
- Code for fine-tuning Platypus fam LLMs using LoRAβ629Updated last year