catie-aq / flashT5Links
A fast implementation of T5/UL2 in PyTorch using Flash Attention
☆107Updated 4 months ago
Alternatives and similar repositories for flashT5
Users that are interested in flashT5 are comparing it to the libraries listed below
Sorting:
- Truly flash T5 realization!☆68Updated last year
- Code for Zero-Shot Tokenizer Transfer☆135Updated 6 months ago
- Official implementation of "GPT or BERT: why not both?"☆56Updated last week
- some common Huggingface transformers in maximal update parametrization (µP)☆82Updated 3 years ago
- Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.☆93Updated 2 years ago
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆116Updated 2 years ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆82Updated 2 weeks ago
- ☆114Updated last year
- Fast, Modern, and Low Precision PyTorch Optimizers☆103Updated last week
- ☆81Updated last year
- A toolkit implementing advanced methods to transfer models and model knowledge across tokenizers.☆40Updated last month
- Official code release for "SuperBPE: Space Travel for Language Models"☆62Updated 3 weeks ago
- minimal pytorch implementation of bm25 (with sparse tensors)☆104Updated last year
- State-of-the-art paired encoder and decoder models (17M-1B params)☆38Updated this week
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆136Updated last year
- Multipack distributed sampler for fast padding-free training of LLMs☆199Updated 11 months ago
- Code repository for the c-BTM paper☆107Updated last year
- Understand and test language model architectures on synthetic tasks.☆221Updated 3 weeks ago
- Supercharge huggingface transformers with model parallelism.☆77Updated 2 weeks ago
- Datasets collection and preprocessings framework for NLP extreme multitask learning☆185Updated 3 weeks ago
- ☆39Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆61Updated 9 months ago
- Training and evaluation code for the paper "Headless Language Models: Learning without Predicting with Contrastive Weight Tying" (https:/…☆27Updated last year
- Efficient encoder-decoder architecture for small language models (≤1B parameters) with cross-architecture knowledge distillation and visi…☆29Updated 5 months ago
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆62Updated 2 months ago
- Minimum Bayes Risk Decoding for Hugging Face Transformers☆58Updated last year
- ☆100Updated 2 years ago
- Language models scale reliably with over-training and on downstream tasks☆97Updated last year
- Experiments with generating opensource language model assistants☆97Updated 2 years ago
- Manage scalable open LLM inference endpoints in Slurm clusters☆268Updated last year