luisgasco
Follow
recursos_utiles
Different useful snippets I create while I am a working at BSC
Vector Hub - Library for easy discovery, and consumption of State-of-the-art models to turn data into vectors. (text2vec, image2vec, video2vec, graph2vec, bert, inception, etc)
Simple generic REST service for checking the spelling of words. Incorrect words are returned with any available suggestions.
Generating Candidate Entities with ScispaCy
Zero-shot Entity Linking with blitz start in 3 minutes. Hard negative mining and encoder for all entities are also included in this implementation.
Obsidian plugin which integrates your academic reference manager with the Obsidian editor. Search your references from within Obsidian and automatically create and reference literature notes for pa…
Text normalization in clinical natural language processing includes the task to identify acronyms to obtain their appropriate expanded form. This paper contributes to acronym resolution in Spanish …
A guide book on data science for busy and equally lazy Data Scientists 😄
Curso de análisis de textos con técnicas de aprendizaje automático
🎓 Sharing machine learning course / lecture notes.
A comprehensive reference for all topics related to Natural Language Processing
A curated list of few-shot learning in NLP. :-)
A Unified Library for Parameter-Efficient and Modular Transfer Learning
Collection of NLP model explanations and accompanying analysis tools
Learn how to design, develop, deploy and iterate on production-grade ML applications.
COLING 2022: Baseline model and annotations for MedSecId, Landes et al.
MatScIE: An automated tool for information extraction from Material Science scientific documents.
Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.
The Metadata Platform for your Data and AI Stack
Some recipes for data engineering with Python
The fastest ⚡️ way to build data pipelines. Develop iteratively, deploy anywhere. ☁️
😎 A curated list of awesome MLOps tools
Natural Language Toolkit for Malaysian language, https://malaya.readthedocs.io/
OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
Language model fine-tuning on NER with an easy interface and cross-domain evaluation. "T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition, EACL 2021"