Pre-train Static Word Embeddings
☆108Jun 9, 2026Updated last month
Alternatives and similar repositories for tokenlearn
Users that are interested in tokenlearn 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☆80Apr 27, 2026Updated 2 months ago
- Fast State-of-the-Art Static Embeddings☆2,159Jun 6, 2026Updated last month
- Fast Multimodal Semantic Deduplication & Filtering☆946May 24, 2026Updated last month
- Code Roberta version of RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder☆10Mar 16, 2023Updated 3 years ago
- 🔢 Work with static vector models☆39Apr 21, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Official Rust Implementation of Model2Vec☆197May 24, 2026Updated last month
- Load embeddings and featurize your sentences.☆31Oct 23, 2024Updated last year
- Check what an AI agent can access before you run it☆27Mar 8, 2026Updated 4 months ago
- YASEM - Yet Another Splade|Sparse Embedder - A simple and efficient library for SPLADE embeddings☆13May 22, 2025Updated last year
- Late Interaction Models Training & Retrieval☆875Jul 13, 2026Updated last week
- Datamodels for hugging face tokenizers☆108Jun 18, 2026Updated last month
- FlexiTokens☆23Dec 27, 2025Updated 6 months ago
- Generalist and Lightweight Model for Text Classification☆233Updated this week
- Plug-and-play document AI with zero-shot models.☆126May 11, 2026Updated 2 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.
- bb25 is a fast, self-contained BM25 + Bayesian calibration implementation with a minimal Python API.☆148Mar 17, 2026Updated 4 months ago
- Starbucks: Improved Training for 2D Matryoshka Embeddings☆25Jun 30, 2025Updated last year
- Fast Diversification for Search & Retrieval☆492May 24, 2026Updated last month
- State-of-the-art paired encoder and decoder models (17M-1B params)☆74Aug 6, 2025Updated 11 months ago
- A blueprint for AI development, focusing on applied examples of RAG, information extraction, analysis and fine-tuning in the age of LLMs …☆66Feb 6, 2025Updated last year
- A framework for benchmarking embedding models in hybrid search scenarios (BM25 + vector search) using Weaviate.☆40Updated this week
- ☆77May 14, 2026Updated 2 months ago
- Architecture pattern for combining a fast LLM voice loop with a slower SLM that tracks hard facts.☆15Apr 27, 2026Updated 2 months ago
- Fine-tune ModernBERT with custom tokenizers, curriculum learning, and next-gen optimizers.☆74Jan 16, 2026Updated 6 months 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.
- A framework for evaluating semantic search across custom datasets, metrics, and embedding backends.☆39Jul 9, 2026Updated last week
- Hallucination-prevention RAG system with verbatim span extraction. Ensures all generated content is grounded in source documents with exa…☆202Jul 13, 2026Updated last week
- ☆11Sep 27, 2024Updated last year
- Trainable embedding transformation for confidence estimation, feature extraction, explainability and conversion from dense to sparse.☆28Jun 23, 2026Updated 3 weeks ago
- A RAG that can scale 🧑🏻💻☆11May 28, 2024Updated 2 years ago
- Efficient and scalable zero-shot entity linking☆140May 21, 2026Updated 2 months ago
- ☆18Jul 1, 2025Updated last year
- Word Sense Linking model is designed to identify and disambiguate spans of text to their most suitable senses from a reference inventory.☆13Aug 23, 2024Updated last year
- Training code for Sparse Autoencoders on Embedding models☆39Jul 11, 2026Updated last week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Low latency, High Accuracy, Custom Query routers for Humans and Agents. Built by Prithivi Da☆122Mar 31, 2025Updated last year
- Robust and fast topic models with sentence-transformers.☆118Updated this week
- Efficient few-shot learning with cross-encoders.☆68Feb 16, 2024Updated 2 years ago
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆90Feb 10, 2026Updated 5 months ago
- Bayesian probability transforms for BM25 retrieval scores☆77Jun 20, 2026Updated last month
- ☆57Dec 27, 2025Updated 6 months ago
- Knowledgeable Embedding: Injecting dynamically updatable entity knowledge into embeddings to enhance RAG☆15Aug 31, 2025Updated 10 months ago