Knowledgator / TurboT5
Truly flash T5 realization!
☆64Updated 10 months ago
Alternatives and similar repositories for TurboT5:
Users that are interested in TurboT5 are comparing it to the libraries listed below
- A fast implementation of T5/UL2 in PyTorch using Flash Attention☆96Updated 2 weeks ago
- Utilities for Training Very Large Models☆58Updated 6 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆40Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆80Updated 3 years ago
- ☆98Updated 10 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆59Updated 5 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
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆58Updated 2 months ago
- XTR: Rethinking the Role of Token Retrieval in Multi-Vector Retrieval☆49Updated 9 months ago
- Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTO…☆53Updated last week
- ☆49Updated last year
- ☆32Updated 9 months ago
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆115Updated 2 years ago
- Improving Text Embedding of Language Models Using Contrastive Fine-tuning☆61Updated 7 months ago
- ☆81Updated last year
- Easily run PyTorch on multiple GPUs & machines☆45Updated last week
- ☆47Updated 7 months ago
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆34Updated last year
- minimal pytorch implementation of bm25 (with sparse tensors)☆97Updated last year
- Supercharge huggingface transformers with model parallelism.☆76Updated 5 months ago
- Fast, Modern, Memory Efficient, and Low Precision PyTorch Optimizers☆88Updated 8 months ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆47Updated last year
- Load compute kernels from the Hub☆107Updated this week
- Code for Zero-Shot Tokenizer Transfer☆125Updated 2 months ago
- Code for NeurIPS LLM Efficiency Challenge☆57Updated 11 months ago
- ☆79Updated 11 months ago
- ☆38Updated 11 months ago
- Multipack distributed sampler for fast padding-free training of LLMs☆186Updated 7 months ago
- Using FlexAttention to compute attention with different masking patterns☆42Updated 6 months ago
- An unofficial pytorch implementation of 'Efficient Infinite Context Transformers with Infini-attention'☆51Updated 7 months ago