PythonNut / superbpeLinks
Official code release for "SuperBPE: Space Travel for Language Models"
☆67Updated 2 months ago
Alternatives and similar repositories for superbpe
Users that are interested in superbpe are comparing it to the libraries listed below
Sorting:
- Code for Zero-Shot Tokenizer Transfer☆137Updated 8 months ago
- A toolkit implementing advanced methods to transfer models and model knowledge across tokenizers.☆46Updated 2 months ago
- Language models scale reliably with over-training and on downstream tasks☆99Updated last year
- Organize the Web: Constructing Domains Enhances Pre-Training Data Curation☆64Updated 4 months ago
- Long Context Extension and Generalization in LLMs☆60Updated last year
- ☆52Updated last year
- Simple and efficient pytorch-native transformer training and inference (batched)☆78Updated last year
- A fast implementation of T5/UL2 in PyTorch using Flash Attention☆107Updated 6 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated 11 months ago
- Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models☆63Updated 4 months ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆44Updated last year
- ☆49Updated last year
- ☆56Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆87Updated 2 months ago
- ☆85Updated last year
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆75Updated last year
- Official Code for M-RᴇᴡᴀʀᴅBᴇɴᴄʜ: Evaluating Reward Models in Multilingual Settings (ACL 2025 Main)☆35Updated 4 months ago
- Official code repo for paper "Great Memory, Shallow Reasoning: Limits of kNN-LMs"☆23Updated 4 months ago
- Code for ICML 25 paper "Metadata Conditioning Accelerates Language Model Pre-training (MeCo)"☆42Updated 2 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆34Updated 3 weeks ago
- ☆53Updated last year
- ☆48Updated last year
- ☆75Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆83Updated 10 months ago
- Synthetic Data Generation for Evaluation☆14Updated 7 months ago
- ☆39Updated last year
- [ICLR'25] Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"☆77Updated 9 months ago
- ☆22Updated last month
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆179Updated 3 months ago
- [NeurIPS 2024] Low rank memory efficient optimizer without SVD☆31Updated 2 months ago