Lists (6)
Sort Name ascending (A-Z)
Stars
An opinionated Scala style guide meant to focus reader and writer on the business domain
Code for training and evaluating T5 on Portuguese data.
notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references und…
CardioBERTpt - Portuguese Transformer-based Models for Clinical Language Representation in Cardiology
SemClinBr - a multi-institutional and multi-specialty semantically annotated corpus for Portuguese clinical NLP tasks
Biomedical and Clinical BERT for Portuguese Language
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
A fast, local first, reactive Database for JavaScript Applications https://rxdb.info/
A flexible distributed key-value datastore that is optimized for caching and other realtime workloads.
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.
Tool provides a better way to ocr pdfs that contain structured data. Will use GPT4 Vision to structured data as Json. Each page will be extracted to a Json file...
Stanford NLP Python library for understanding and improving PyTorch models via interventions
Automate browser-based workflows with LLMs and Computer Vision
A one stop repository for generative AI research updates, interview resources, notebooks and much more!
Sharding and location transparency for Scala
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
Artificial Intelligence Infrastructure-as-Code Generator.
ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)
DSPy: The framework for programming—not prompting—language models
A collection of scripts to flash Tuya IoT devices to alternative firmwares
My configuration for Home Assistant on Hass.io
Your favorite language gets closer to bare metal.
Source code for ACL-IJCNLP 2021 findings paper: SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction
EMNLP 2021 "Pre-train or Annotate? Domain Adaptation with a Constrained Budget".