Datamodels for hugging face tokenizers
☆112Oct 3, 2026Updated last month
Alternatives and similar repositories for skeletoken
Users that are interested in skeletoken are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Nearly Inference Free Embeddings: make your RAG queries 500x faster☆90Apr 27, 2026Updated 6 months ago
- TokEval: intrinsic quality metrics for tokenizers across natural language, code, and math☆58Aug 31, 2026Updated 2 months ago
- A collection of Pythonic subword tokenisers and text preprocessing tools.☆15Oct 29, 2026Updated last week
- Label shift estimation for transfer difficulty with Familiarity.☆11Feb 4, 2025Updated last year
- FlexiTokens☆23Dec 27, 2025Updated 10 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆95Updated this week
- Code for SaGe subword tokenizer (EACL 2023)☆28Nov 30, 2024Updated last year
- A Multilingual Keyboard Layout-Based Typo Generator☆19Nov 23, 2025Updated 11 months ago
- Pre-train Static Word Embeddings☆112Sep 30, 2026Updated last month
- Check what an AI agent can access before you run it☆28Mar 8, 2026Updated 7 months ago
- Code for training CamemBERTa, a French language model based on DeBERTa V3. Development is done here https://gitlab.inria.fr/almanach/Came…☆14Nov 18, 2024Updated last year
- ☆109Jun 2, 2025Updated last year
- 🔢 Work with static vector models☆39Apr 21, 2025Updated last year
- [ICML'26] LEMUR reduces multi-vector retrieval for late interaction models such as ColBERT into regular single-vector retrieval.☆33Oct 6, 2026Updated last month
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Simple-to-use scoring function for arbitrarily tokenized texts.☆52Oct 18, 2026Updated 2 weeks ago
- Code for the paper "BPE stays on SCRIPT", "Which Pieces Does Unigram Tokenization Really Need?" and MinGram☆22Updated this week
- Using open source LLMs to build synthetic datasets for direct preference optimization☆74Feb 29, 2024Updated 2 years ago
- ☆11Jan 27, 2025Updated last year
- ☆103Jul 4, 2025Updated last year
- Next-generation Punkt sentence boundary detection with zero dependencies☆32Sep 28, 2026Updated last month
- A unified framework for attributing model behavior to model components, training data, and training dynamics.☆12Oct 25, 2026Updated last week
- Project for training, quantizing, and serving a static emebdding models.☆39Aug 7, 2026Updated 2 months ago
- ☆12Dec 24, 2025Updated 10 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [ACL'26 Findings] Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets☆20Jun 27, 2026Updated 4 months ago
- NLP with Rust for Python 🦀🐍☆72Aug 8, 2026Updated 2 months ago
- C inference engine for running GLiClass (Generalist and Lightweight Classification) models☆19May 21, 2025Updated last year
- Late Interaction Models Training & Retrieval☆904Jul 23, 2026Updated 3 months ago
- A Python library aimed at dissecting and augmenting NER training data.☆60May 11, 2023Updated 3 years ago
- ANE accelerated embedding models!☆21Dec 11, 2024Updated last year
- SpanMarker for Named Entity Recognition☆475Apr 10, 2026Updated 6 months ago
- BPE modification that implements removing of the intermediate tokens during tokenizer training.☆27Nov 25, 2024Updated last year
- Fast Diversification for Search & Retrieval☆503Sep 30, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Fast State-of-the-Art Static Embeddings☆2,271Updated this week
- Simply, faster, sentence-transformers☆144Aug 27, 2024Updated 2 years ago
- Fast Multimodal Semantic Deduplication & Filtering☆978Oct 4, 2026Updated last month
- PyLate efficient inference engine☆93Jan 7, 2026Updated 9 months ago
- My NER Experiments with ModernBERT and Ettin☆30Jul 17, 2025Updated last year
- bb25 is a fast, self-contained BM25 + Bayesian calibration implementation with a minimal Python API.☆153Mar 17, 2026Updated 7 months ago
- Crispy reranking models by Mixedbread☆55Sep 17, 2025Updated last year