catie-aq / flashT5Links
A fast implementation of T5/UL2 in PyTorch using Flash Attention
☆107Updated 6 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!☆70Updated last year
- Code for Zero-Shot Tokenizer Transfer☆137Updated 8 months 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.☆95Updated 2 years ago
- A toolkit implementing advanced methods to transfer models and model knowledge across tokenizers.☆46Updated 3 months ago
- some common Huggingface transformers in maximal update parametrization (µP)☆82Updated 3 years ago
- ☆122Updated last year
- Official implementation of "GPT or BERT: why not both?"☆59Updated 2 months ago
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆116Updated 2 years ago
- Fast, Modern, and Low Precision PyTorch Optimizers☆112Updated last month
- Training and evaluation code for the paper "Headless Language Models: Learning without Predicting with Contrastive Weight Tying" (https:/…☆27Updated last year
- ☆82Updated last year
- minimal pytorch implementation of bm25 (with sparse tensors)☆104Updated last year
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆230Updated last year
- ☆39Updated last year
- Supercharge huggingface transformers with model parallelism.☆77Updated 2 months ago
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆136Updated last year
- ☆75Updated last year
- Datasets collection and preprocessings framework for NLP extreme multitask learning☆186Updated 2 months ago
- Multipack distributed sampler for fast padding-free training of LLMs☆201Updated last year
- [EMNLP'23] Official Code for "FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models"☆34Updated 3 months ago
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆65Updated last week
- LTG-Bert☆34Updated last year
- ☆49Updated last year
- Efficient encoder-decoder architecture for small language models (≤1B parameters) with cross-architecture knowledge distillation and visi…☆30Updated 7 months ago
- State-of-the-art paired encoder and decoder models (17M-1B params)☆50Updated 2 months ago
- Code repository for the c-BTM paper☆107Updated 2 years ago
- Experiments for efforts to train a new and improved t5☆76Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆89Updated 2 months ago
- Experiments with generating opensource language model assistants☆97Updated 2 years ago
- Official code release for "SuperBPE: Space Travel for Language Models"☆67Updated 2 months ago