raphaelsty / LeNLPLinks
NLP with Rust for Python π¦π
β64Updated 3 months ago
Alternatives and similar repositories for LeNLP
Users that are interested in LeNLP are comparing it to the libraries listed below
Sorting:
- β68Updated 2 months ago
- Pre-train Static Word Embeddingsβ85Updated this week
- An introduction to LLM Samplingβ80Updated 8 months ago
- Tree-based indexes for neural-searchβ32Updated last year
- minimal pytorch implementation of bm25 (with sparse tensors)β104Updated last year
- π Reference-Free automatic summarization evaluation with potential hallucination detectionβ103Updated last year
- Trully flash implementation of DeBERTa disentangled attention mechanism.β63Updated last week
- Python library to use Pleias-RAG modelsβ61Updated 4 months ago
- PyLate efficient inference engineβ64Updated last month
- The Batched API provides a flexible and efficient way to process multiple requests in a batch, with a primary focus on dynamic batching oβ¦β146Updated last month
- β49Updated 7 months ago
- Efficient BM25 with DuckDB π¦β55Updated 8 months ago
- High-Performance Engine for Multi-Vector Searchβ155Updated this week
- β28Updated 2 months ago
- Tools to make language models a bit easier to useβ54Updated last month
- β40Updated 2 months ago
- Generalist and Lightweight Model for Text Classificationβ156Updated 2 months ago
- lossily compress representation vectors using product quantizationβ59Updated 4 months ago
- Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and teβ¦β42Updated last year
- Small python package to measure OCR quality and other related metrics.β25Updated last year
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).β80Updated last year
- Training code for Sparse Autoencoders on Embedding modelsβ38Updated 6 months ago
- Command Line Interface for Hugging Face Inference Endpointsβ66Updated last year
- β31Updated 9 months ago
- Optimus is a flexible and scalable framework built to train language models efficiently across diverse hardware configurations, includingβ¦β67Updated 2 months ago
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, impβ¦β189Updated last year
- utilities for loading and running text embeddings with onnxβ44Updated 3 weeks ago
- XTR/WARP (SIGIR'25) is an extremely fast and accurate retrieval engine based on Stanford's ColBERTv2/PLAID and Google DeepMind's XTR.β163Updated 4 months ago
- Efficient few-shot learning with cross-encoders.β58Updated last year
- β58Updated 4 months ago