jkallini / mrt5Links
Code repository for the paper "MrT5: Dynamic Token Merging for Efficient Byte-level Language Models."
☆51Updated last week
Alternatives and similar repositories for mrt5
Users that are interested in mrt5 are comparing it to the libraries listed below
Sorting:
- MEXMA: Token-level objectives improve sentence representations☆41Updated 9 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated last year
- ☆85Updated last year
- ☆58Updated 4 months ago
- ☆52Updated 8 months ago
- Efficient encoder-decoder architecture for small language models (≤1B parameters) with cross-architecture knowledge distillation and visi…☆30Updated 7 months ago
- Code for Zero-Shot Tokenizer Transfer☆137Updated 8 months ago
- Official implementation of "BERTs are Generative In-Context Learners"☆32Updated 6 months ago
- Repository for "I am a Strange Dataset: Metalinguistic Tests for Language Models"☆45Updated last year
- ☆82Updated last year
- A byte-level decoder architecture that matches the performance of tokenized Transformers.☆66Updated last year
- Code and pretrained models for the paper: "MatMamba: A Matryoshka State Space Model"☆61Updated 10 months ago
- A repository for research on medium sized language models.☆78Updated last year
- Improving Text Embedding of Language Models Using Contrastive Fine-tuning☆64Updated last year
- ☆48Updated last year
- A toolkit implementing advanced methods to transfer models and model knowledge across tokenizers.☆46Updated 3 months ago
- GoldFinch and other hybrid transformer components☆45Updated last year
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆73Updated 3 months ago
- Fork of Flame repo for training of some new stuff in development☆18Updated last month
- ☆81Updated last week
- Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTO…☆56Updated 2 weeks ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆43Updated this week
- A fast implementation of T5/UL2 in PyTorch using Flash Attention☆107Updated 6 months ago
- Official implementation of "GPT or BERT: why not both?"☆59Updated 2 months ago
- This is the official repository for Inheritune.☆115Updated 7 months ago
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…☆55Updated last week
- Code for PHATGOOSE introduced in "Learning to Route Among Specialized Experts for Zero-Shot Generalization"☆89Updated last year
- MatFormer repo☆62Updated 9 months ago
- Official code release for "SuperBPE: Space Travel for Language Models"☆68Updated 2 months ago
- Truly flash T5 realization!☆70Updated last year