catie-aq / flashT5Links
A fast implementation of T5/UL2 in PyTorch using Flash Attention
☆105Updated 2 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!☆67Updated last year
- Code for Zero-Shot Tokenizer Transfer☆128Updated 4 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.☆93Updated 2 years ago
- Fast, Modern, Memory Efficient, and Low Precision PyTorch Optimizers☆93Updated 10 months ago
- ☆108Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆80Updated 3 years ago
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆114Updated 2 years ago
- Official implementation of "GPT or BERT: why not both?"☆53Updated 2 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆73Updated 7 months ago
- Prune transformer layers☆69Updated last year
- Multipack distributed sampler for fast padding-free training of LLMs☆188Updated 9 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆62Updated 4 months ago
- ☆80Updated last year
- Various transformers for FSDP research☆37Updated 2 years ago
- ☆72Updated last year
- ☆34Updated 11 months ago
- Load compute kernels from the Hub☆139Updated this week
- ☆49Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆128Updated 3 weeks ago
- Understand and test language model architectures on synthetic tasks.☆197Updated 2 months ago
- ☆78Updated 11 months ago
- Minimum Bayes Risk Decoding for Hugging Face Transformers☆58Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆116Updated 5 months ago
- nanoGPT-like codebase for LLM training☆94Updated 2 weeks ago
- Utilities for Training Very Large Models☆58Updated 8 months ago
- minimal pytorch implementation of bm25 (with sparse tensors)☆101Updated last year
- ☆72Updated 2 years ago
- Manage scalable open LLM inference endpoints in Slurm clusters☆258Updated 10 months ago
- supporting pytorch FSDP for optimizers☆79Updated 5 months ago
- ☆20Updated last year