Stars
Weighs the soul of incoming HTTP requests to stop AI crawlers
Bringing BERT into modernity via both architecture changes and scaling
Plaintext files with Latin texts from the Tesserae Project
Training sets and tokenizer for the Latin language, for use with CLTK
A more sophisticated implementation of Whitaker's WORDS program written for Python
A simple module to collect video, text, and metadata from Tiktok.
A high-throughput and memory-efficient inference and serving engine for LLMs
State-of-the-art paired encoder and decoder models (17M-1B params)
DSPy: The framework for programming—not prompting—language models
Fast and memory-efficient exact attention
Causal depthwise conv1d in CUDA, with a PyTorch interface
convert a saved pytorch model to gguf and generate as much corresponding ggml c code as possible
A library for efficient similarity search and clustering of dense vectors.
List of papers on hallucination detection in LLMs.
The 4CAT Capture and Analysis Toolkit provides modular data capture & analysis for a variety of social media platforms.
A browser extension to collect social media data with.
A Dataset for Direct Quotation Extraction and Attribution in News Articles.
Deep universal probabilistic programming with Python and PyTorch
Spam Apple Proximity Messages via an ESP32
A Simple ESP32 Bluetooth A2DP Library (to implement a Music Receiver or Sender) that supports Arduino, PlatformIO and Espressif IDF
released code for our EMNLP22 paper: UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction
PyTorch code for SpERT: Span-based Entity and Relation Transformer