Good question! On average: LoRA: 21.33 tokens/sec; Memory used: 14.59 GB
Adapter: 26.22 tokens/sec; Memory used: 14.59 GB
AI
-
LoRA vs Adapter: Performance and Memory Usage Comparison
By
–
-
LLM Adoption Across Sequoia Portfolio Companies
By
–
Quick one – when you say “Nearly every company in the Sequoia network is building language models into their products.” Do you refer to the entire Sequoia portfolio or the 33 companies you selected to sample, which I assume are those most likely to be in a spot where LLMs are
-
Memory reduction: Full finetuning vs Adapter vs LoRA comparison
By
–
Btw, it's also a big reduction in memory: 16 gigs instead of 6 x 40 GB. Due to the reduced parameter counts in the backward pass: Full finetuning: 7,217,189,760
Adapter: 1,365,330
Adapter v2: 3,839,186
LoRA: 3,506,176 (I used LoRA rank of 16 to match Adapter v2 above.) -
GPT Engineer Setup Guide and Demo
By
–
GPT Engineer is pretty crazy… Here's how you set it up: https://t.co/DhAPQSE14i pic.twitter.com/d5N9ITvaYJ
— Dave Ebbelaar (@daveebbelaar) 15 juin 2023GPT Engineer is pretty crazy… Here's how you set it up: https://
youtu.be/gWy-pJ2ofEM -
Efficient Falcon Finetuning with LoRA on Single GPU
By
–
Have been heads-down porting LoRA (low-rank-adaptation) to finetune Falcon more efficiently and ran some performance benchmarks. My longer write-up here: https://
lightning.ai/pages/communit
y/finetuning-falcon-efficiently/
… Long story short: you can finetune Falcon in 1 h on a 52k dataset using a single GPU with 16 GB RAM. -
ChatGPT versus Raphaël Enthoven: Media Experiment Fairness Questioned
By
–
Cette expérience est une escroquerie médiatique
— Docteur Laurent Alexandre (@dr_l_alexandre) 15 juin 2023
ChatGPT a eu 90 secondes
Raphael Enthoven a eu 90 minutes
J’aime beaucoup Raphaël malgré tout 😂 https://t.co/OuK0URIusgCette expérience est une escroquerie médiatique ChatGPT a eu 90 secondes Raphael Enthoven a eu 90 minutes J’aime beaucoup Raphaël malgré tout
-
AI Anthology: 20 Essays on Beneficial AI Applications
By
–
"I am honored to present the AI Anthology, a compilation of 20 inspiring essays authored by distinguished scholars and professionals from various disciplines. The anthology explores the diverse ways in which AI can be channeled to benefit humanity" https://
bit.ly/3N9m3Si -
EU Considers Forcing Google to Divest Adtech Business
By
–
Saying “behavioral remedy” would be ineffective, EU officials say it might be necessary to force Google to divest of part of its adtech biz if found to be in violation of EU law. My story from yesterday about the new antitrust case against the tech giant: https://
tinyurl.com/5h48wyxm -
LLaMA-Adapter Compatible with Falcon Models
By
–
(And yes, that's not a typo, you can use LLaMA-Adapter for Falcon :P)
-
Gmail’s New AI Feature Helps Write Emails on iOS Android
By
–
Article: https://
bgr.com/tech/gmails-ne
w-ai-feature-is-ready-to-help-you-write-emails-on-ios-and-android/
…