ROSCOE is a first-of-its-kind suite of metrics for scoring step-by-step reasoning. We hope this work provides a foundation that enables scalable systematic evaluation and benchmarking of new language models. Read the paper https://
bit.ly/3XxYAgU
RESEARCH
-
ROSCOE: New Metrics Suite for Evaluating Step-by-Step Reasoning
By
–
-
Chatbots Hallucinate: December Story Resurfaced
By
–
Seems like a good time to resurface this December story pointing out that chatbots hallucinate:
-
Genome-Scale Language Models Learn SARS-CoV-2 Evolution
By
–
Join us for a guest presentation! @argonne
's Arvind Ramanathan will share how his team built genome-scale language models that can learn the evolutionary landscape of SARS-CoV-2 genomes. This research won the 2022 ACM Gordon Bell Special Prize. Register: https://
hubs.li/Q01CkjLt0 -
Mapping Planetary Reliefs with Deep Learning
By
–
Mapping planetary reliefs using deep learning https://actuia.com/actualite/cartographier-les-reliefs-planetaires-grace-au-deep-learning/
… #AI #artificialintelligence #research -
OpenCV Kickstarter for Stable Diffusion AI Art Contest
By
–
Joao, Basavaraja #opencvkickstarter4stablediffusion #aiartcontest #aiart #midjourney #dalle2 #stablediffusion #computervision #ai #deeplearning #machinelearning #artificialintelligence
-
OpenCV Kickstarter for Stable Diffusion AI Art Contest
By
–
Suzana, Ad K, Amar, Alex #opencvkickstarter4stablediffusion #aiartcontest #aiart #midjourney #dalle2 #stablediffusion #computervision #ai #deeplearning #machinelearning #artificialintelligence
-
Meta Launches Toolformer: An Autonomous Model Using External Tools
By
–
Meta introduces Toolformer, a language model that has independently learned to use external tools https://actuia.com/actualite/meta-presente-toolformer-un-modele-de-langage-ayant-appris-par-lui-meme-a-utiliser-des-outils-externes/
… #AI #artificialintelligence
@Meta -
Interesting Use Cases of PEFT Parameter Efficient Fine-Tuning
By
–
Some of the interesting usecases of PEFT are: 1. Stable Diffusion Dreambooth training.
2. Finetuning the `bigscience/T0_3B` model which has around 3 Billion Parameters. Checkout them here: https://
github.com/huggingface/pe
ft#use-cases
… 3/5 -
PEFT: Fine-tuning Large Models on Low-End Hardware
By
–
But fine-tuning large models on low-end hardware is a real challenge PEFT solves this by fine-tuning a small number of model parameters while freezing most parameters of the pre-trained LLMs. This reduces the computational and storage costs 2/5 https://
github.com/huggingface/pe
ft
… -
Fine-tuning: Faster Model Adaptation for Specific Tasks
By
–
In simple words fine-tuning is taking a pre-trained machine learning model and adjusting it for a specific task Fine-tuning is much faster than training a model from scratch and also reduces the amount of data, compute required for training and lot of other benefits 1/5