RAIVNLab / AdANNSLinks
Code repository for the paper - "AdANNS: A Framework for Adaptive Semantic Search"
☆65Updated 2 years ago
Alternatives and similar repositories for AdANNS
Users that are interested in AdANNS are comparing it to the libraries listed below
Sorting:
- XTR: Rethinking the Role of Token Retrieval in Multi-Vector Retrieval☆59Updated last year
- XTR/WARP (SIGIR'25) is an extremely fast and accurate retrieval engine based on Stanford's ColBERTv2/PLAID and Google DeepMind's XTR.☆173Updated 7 months ago
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆79Updated last year
- ReLM is a Regular Expression engine for Language Models☆107Updated 2 years ago
- Code for NeurIPS LLM Efficiency Challenge☆59Updated last year
- ☆31Updated last year
- minimal pytorch implementation of bm25 (with sparse tensors)☆104Updated last month
- Implementation of "Efficient Multi-vector Dense Retrieval with Bit Vectors", ECIR 2024☆66Updated last month
- Supercharge huggingface transformers with model parallelism.☆77Updated 4 months ago
- ☆39Updated last year
- Mixing Language Models with Self-Verification and Meta-Verification☆110Updated 11 months ago
- Experiments for efforts to train a new and improved t5☆76Updated last year
- Tree-based indexes for neural-search☆31Updated last year
- NLP with Rust for Python 🦀🐍☆70Updated 6 months ago
- NeurIPS 2023 - Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer☆44Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated last year
- PostText is a QA system for querying your text data. When appropriate structured views are in place, PostText is good at answering querie…☆31Updated 2 years ago
- Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE …☆115Updated last year
- Make triton easier☆49Updated last year
- A library for squeakily cleaning and filtering language datasets.☆49Updated 2 years ago
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆226Updated 2 months ago
- ☆12Updated last year
- Latent Large Language Models☆19Updated last year
- ☆86Updated 5 months ago
- Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and te…☆44Updated last year
- Using FlexAttention to compute attention with different masking patterns☆47Updated last year
- Simple GRPO scripts and configurations.☆59Updated 10 months ago
- Truly flash T5 realization!☆71Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆87Updated 3 years ago
- ☆52Updated 9 months ago