mariagrandury
Follow
Lists (5)
Stars
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
A course on aligning smol models.
Machine Learning Engineering Open Book
A framework for few-shot evaluation of language models
A 4-hour coding workshop to understand how LLMs are implemented and used
Diapositivas, notebooks y material de charlas, talleres y el grupo de estudio
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
A curated list of awesome responsible machine learning resources.
Automatically evaluate your LLMs in Google Colab
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
๐ธ๐ฌ - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
๐ฆ ๐๐ฒ๐ฎ๐ฟ๐ป about ๐๐๐ ๐, ๐๐๐ ๐ข๐ฝ๐, and ๐๐ฒ๐ฐ๐๐ผ๐ฟ ๐๐๐ for free by designing, training, and deploying a real-time financial advisor LLM system ~ ๐ด๐ฐ๐ถ๐ณ๐ค๐ฆ ๐ค๐ฐ๐ฅ๐ฆ + ๐ท๐ช๐ฅ๐ฆ๐ฐ & ๐ณ๐ฆ๐ข๐ฅ๐ช๐ฏ๐จ ๐ฎ๐ข๐ต๐ฆ๐ณ๐ช๐ข๐ญ๐ด
Understanding Deep Learning - Simon J.D. Prince
Robust recipes to align language models with human and AI preferences
This repository contains demos I made with the Transformers library by HuggingFace.
21 Lessons, Get Started Building with Generative AI ๐ https://microsoft.github.io/generative-ai-for-beginners/
๐ฅHighlighting the top ML papers every week.
Stanford CRFM's initiative to assess potential compliance with the draft EU AI Act
Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image โฆ
Lista de corpus de PLN en espaรฑol โจ #Somos600M: Ayuda a desarrollar IA inclusiva que entienda las diferentes variedades de nuestras lenguas โจ English-speaking contributors welcome!
๐ A list of open LLMs available for commercial use.
A Python package to compute HONEST, a score to measure hurtful sentence completions in language models. Published at NAACL 2021.
A Python multilingual toolkit for Sentiment Analysis and Social NLP tasks
A language for constraint-guided and efficient LLM programming.