2/ Survey on Instruction Tuning for LLMs – new survey paper on instruction tuning LLM, including a systematic review of the literature, methodologies, dataset construction, training models, applications, and more.
MACHINE LEARNING
-
SeamlessM4T: Unified Multilingual Multimodal Machine Translation System
By
–
3/ SeamlessM4T – a unified multilingual and multimodal machine translation system that supports ASR, text-to-text translation, speech-to-text translation, text-to-speech translation, and speech-to-speech translation.
-
Weights compatibility and numerical stability in LoRA fine-tuning
By
–
Yes, I think that's either maybe so that (1) people with older cards can use these weights as well and (2) we maybe have more stability when finetuning with LoRA etc (in case numbers become large)
It's interesting for sure -
Hugging Face Learning Resources: Start Your AI Journey
By
–
The best places to start learning about the Hugging Face ecosystem are our courses: https://
huggingface.co/learn and the tasks page: https://
huggingface.co/tasks -
ECMWF Leads AI Methods for Weather Forecasting Research
By
–
Excited to see @ECMWF take the lead in exploring #AI methods for weather forecasting building on our research efforts at @nvidia Earth-2 as well as from other labs https://
x.com/PDueben/status
/PDueben/status/1690336752181895168
… -
Multiple Imputation by Chained Equations Implementation Guide
By
–
Cameron Patrick – Dirty imputation done dirt cheap: implementing Multiple Imputation by Chained Equations in one blog post https://
bit.ly/3Qw76NF #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Artificial Intelligence Saving Lives in Hospital Settings
By
–
How artificial intelligence is saving lives in our hospitals
#AI #AIio #BigData #ML #NLU #Futureofwork @TunstallAsc @StrategyFintech @TamaraMcCleary @TerenceLeungSF @psb_dc @thomaspower @vinod1975 @ylecun http://
ow.ly/Jtbk30swTtL -
RAG Technique: Solving Modern LLM Limitations Without Fine-Tuning
By
–
Let’s dive in to one of the most-talked about AI techniques—retrieval augmented generation (RAG)— that developers are using as a precursor to fine-tuning. It helps solve the recent issue of modern LLMs while being not-really-that-hard to implement.
-
RAG Emerges as Developer Priority for Model Performance Optimization
By
–
Among all the developers, experts, and sources I talk to, no subject comes up more than RAG. Developers are increasingly working with it as a precursor to fine-tuning to squeeze more performance out of less-powerful models.
