Some setup notes (cc @EthanJPerez
) – We used the exact 2-shot prompt for Quote Repetition, which is already U-shaped for Gopher/Chinchilla – We used fewer shots for Hindsight – We did few-shot instead of 0-shot for Negation QA – We also showed inverse scaling up to PaLM 62B
LLMS
-
Few-shot Prompt Setup Notes for Scaling Law Experiments
By
–
-
U-shaped Scaling and the Limitations of Inverse Scaling Tasks
By
–
Implications: 1. U-shaped scaling means that inverse scaling may not hold when extrapolated to larger models. 2. The term “inverse scaling task” is underspecified. A task can be inverse scaling for one type of prompting and positive or U-shaped for another type of prompting.
-
CoT Prompting Defends Against Inverse Scaling in Math Tasks
By
–
Second, we show that CoT prompting can defend against inverse scaling. For instance, CoT prompting achieves 100% on 7 out of 8 subtasks for Redefine Math.
-
U-shaped Scaling Behavior Emerges at Higher Computational Budgets
By
–
Our results first confirm inverse scaling behavior seen on prior models trained up to 500 zettaFLOPs. But at 2K zettaFLOPs, it becomes U-shaped. U-scaling has also been shown in prior work, such as BIG-Bench.
-
Inverse Scaling Becomes U-Shaped with Larger Language Models
By
–
New preprint!
— Jason Wei (@_jasonwei) 4 novembre 2022
By evaluating 5x larger language models, inverse scaling can become “U-shaped scaling”, which means that performance increases sharply after decreasing.
https://t.co/bZQndKqlB6
These two tasks here are Third Prize winners from the Inverse Scaling Prize. pic.twitter.com/8d3pu8DDrkNew preprint! By evaluating 5x larger language models, inverse scaling can become “U-shaped scaling”, which means that performance increases sharply after decreasing. https://
arxiv.org/abs/2211.02011 These two tasks here are Third Prize winners from the Inverse Scaling Prize. -
Meta AI Creates Largest Protein Language Model with 15B Parameters
By
–
Meta AI researchers trained a language model to fill in protein sequence gaps across millions of diverse proteins & scaled up to 15B parameters, creating the largest language model of proteins to date. More on our latest breakthrough in protein folding https://
bit.ly/3WoWcK2 -
Machine Learning GPT3 Website Free for Content Creators
By
–
Machine learning for deep thought: a GPT3-based website that every content creator should jump on while it’s free… https://
qburst.co -
Inverse Scaling Observed Up to 62B Model Parameters
By
–
We also showed inverse scaling up to 62B on our model / prompt setup
-
Model Available in Lean VSCode Plugin for Researchers
By
–
We’ve made our model available through the Lean VSCode plugin to allow researchers to explore the capabilities within the Lean environment. We hope you’ll build on this work as part of our shared pursuit of rapid progress in this exciting field.
-
AI21 Labs at IL Cloud Summit: Large Language Models and AI Fortune Teller
By
–
Come visit us at the upcoming IL Cloud Summit on November 9th!
— AI21 Labs (@AI21Labs) 3 novembre 2022
We'll be discussing a topic that has been gaining plenty of traction – large language models.
Be sure to stop by our booth as well to experience the magic of our AI fortune teller 🔮✨ pic.twitter.com/OqM3ldylKZCome visit us at the upcoming IL Cloud Summit on November 9th! We'll be discussing a topic that has been gaining plenty of traction – large language models. Be sure to stop by our booth as well to experience the magic of our AI fortune teller