jkallini / mrt5Links
Code repository for the paper "MrT5: Dynamic Token Merging for Efficient Byte-level Language Models."
☆41Updated last month
Alternatives and similar repositories for mrt5
Users that are interested in mrt5 are comparing it to the libraries listed below
Sorting:
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆57Updated 9 months ago
- Official implementation of "BERTs are Generative In-Context Learners"☆28Updated 2 months ago
- ☆79Updated 9 months ago
- Official implementation of ECCV24 paper: POA☆24Updated 9 months ago
- Efficient encoder-decoder architecture for small language models (≤1B parameters) with cross-architecture knowledge distillation and visi…☆27Updated 3 months ago
- This repo is based on https://github.com/jiaweizzhao/GaLore☆28Updated 8 months ago
- ☆55Updated 3 weeks ago
- A repository for research on medium sized language models.☆76Updated last year
- Code for Zero-Shot Tokenizer Transfer☆128Updated 4 months ago
- Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)☆31Updated 2 months ago
- This is the official repository for Inheritune.☆111Updated 3 months ago
- ☆80Updated last year
- Code and pretrained models for the paper: "MatMamba: A Matryoshka State Space Model"☆59Updated 6 months ago
- ☆58Updated 2 weeks ago
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…☆45Updated last month
- ☆25Updated last year
- ☆49Updated 6 months ago
- The code repository for the CURLoRA research paper. Stable LLM continual fine-tuning and catastrophic forgetting mitigation.☆44Updated 9 months ago
- Official code repo for paper "Great Memory, Shallow Reasoning: Limits of kNN-LMs"☆23Updated last month
- Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More☆31Updated 2 weeks ago
- A byte-level decoder architecture that matches the performance of tokenized Transformers.☆63Updated last year
- ☆34Updated 11 months ago
- Code, results and other artifacts from the paper introducing the WildChat-50m dataset and the Re-Wild model family.☆29Updated 2 months ago
- ReBase: Training Task Experts through Retrieval Based Distillation☆29Updated 4 months ago
- Official Code for Paper: Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation☆67Updated last week
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…☆62Updated 7 months ago
- One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation☆40Updated 7 months ago
- GoldFinch and other hybrid transformer components☆45Updated 10 months ago
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆36Updated last year
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆26Updated 7 months ago