A byte-level decoder architecture that matches the performance of tokenized Transformers.
☆67Apr 24, 2024Updated 2 years ago
Alternatives and similar repositories for spacebyte
Users that are interested in spacebyte are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for the paper "BPE stays on SCRIPT", "Which Pieces Does Unigram Tokenization Really Need?" and MinGram☆19Updated this week
- Code for the paper "Getting the most out of your tokenizer for pre-training and domain adaptation"☆22Feb 14, 2024Updated 2 years ago
- High performance pytorch modules☆18Jan 14, 2023Updated 3 years ago
- new optimizer☆20Aug 4, 2024Updated 2 years ago
- Implementation of MambaByte in "MambaByte: Token-free Selective State Space Model" in Pytorch and Zeta☆129Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Streaming Vocos☆31Jun 10, 2025Updated last year
- Master thesis: Exploring bias in German NLG (GPT-3 & GerPT-2). Applies regard classification and bias mitigation triggers.☆16Sep 25, 2024Updated last year
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Oct 22, 2023Updated 2 years ago
- ☆25Jan 22, 2024Updated 2 years ago
- ☆11Oct 11, 2023Updated 2 years ago
- HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation [ACL 2023]☆14Jul 11, 2023Updated 3 years ago
- NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates [WIP]☆25Jul 5, 2022Updated 4 years ago
- Official implementation of "GPT or BERT: why not both?"☆64Jul 28, 2025Updated last year
- Viterbi decoding in PyTorch☆42May 5, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Beyond Language Models: Byte Models are Digital World Simulators☆333Jun 6, 2024Updated 2 years ago
- unofficial pytorch implementation of HiFi-GAN with fast MISR.☆15Mar 21, 2023Updated 3 years ago
- An unofficial pytorch implementation of 'Efficient Infinite Context Transformers with Infini-attention'☆56Aug 19, 2024Updated last year
- ☆16Feb 6, 2024Updated 2 years ago
- Ukrainian ELECTRA model☆12Mar 11, 2023Updated 3 years ago
- Code for Bolmo: Byteifying the Next Generation of Language Models☆136Aug 1, 2026Updated last week
- ☆51Jan 18, 2024Updated 2 years ago
- [ACL 2025] 🔍 Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment☆11Apr 6, 2025Updated last year
- Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning☆30Jan 25, 2023Updated 3 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆15Apr 26, 2022Updated 4 years ago
- The codes for training sparsity predictor on LLaMA.☆18May 12, 2024Updated 2 years ago
- ☆60Nov 18, 2025Updated 8 months ago
- MIT iQuHACK 2022 x Microsoft x IonQ Challenge☆10Jan 30, 2022Updated 4 years ago
- Code for the paper "Function-Space Learning Rates"☆23Jun 3, 2025Updated last year
- [ICML 2026] Improving GPT via a simple normalization strategy☆15May 22, 2026Updated 2 months ago
- ☆12Apr 18, 2019Updated 7 years ago
- Scaling Sparse Fine-Tuning to Large Language Models☆19Jan 31, 2024Updated 2 years ago
- ☆16Mar 22, 2023Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Algorithms for byte-level language modelling☆25May 14, 2026Updated 3 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆281Oct 3, 2025Updated 10 months ago
- Minimal code to train ELMo models in recent versions of TensorFlow☆14Jun 16, 2026Updated last month
- ☆82Jan 22, 2025Updated last year
- RWKV-7 mini☆12Mar 29, 2025Updated last year
- ☆20Nov 14, 2025Updated 9 months ago
- Resources related to EMNLP 2021 paper "FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations"☆13Dec 14, 2021Updated 4 years ago