LLMS - AI Dynamics

Extending LLM Context Windows to 32K with Minimal Fine-tuning

By

–

02 July 2023 16h06

2/ Extending Context Window of LLMs – extends the context window of LLMs like LLaMA to up to 32K with minimal fine-tuning (within 1000 steps); attains good performance on several tasks while being more efficient and cost-effective.

→ View original post on X — @dair_ai

2 July 2023

Top Machine Learning Papers: LeanDojo, DragDiffusion, LLM Context

By

@dair_ai

–

02 July 2023 16h06

Top ML Papers of the Week (June 26 – July 2): – LeanDojo
– DragDiffusion
– Scaling MLPs
– Visual Navigation Transformer
– GPT-4 for Programming Education
– Extending Context Window of LLMs
…

→ View original post on X — @dair_ai

2 July 2023

Daily AI and Machine Learning Content: Python, NLP, Computer Vision

By

@akshay_pachaar

–

02 July 2023 14h30

That's a wrap! If you interested in: – Python – Data Science – Machine Learning – Maths for ML – MLOps – NLP – Computer Vision – LLMs I'm sharing daily content over here, follow me → @akshay_pachaarif you haven't already!! Cheers!!

→ View original post on X — @akshay_pachaar

2 July 2023

Free Conference on AI Agents, Custom LLMs and Generative AI

By

@akshay_pachaar

–

02 July 2023 14h30

Participating in high-quality conferences help you to stay abreast of the latest advancements in tech. Here's Free Conference by @abacusai ! You'll Learn about: – AI agents
– Building custom LLMs
– Future of Generative AI. Reserve FREE spot!

→ View original post on X — @akshay_pachaar

2 July 2023

Different Development Paths of Large Language Models

By

@miketamir

–

02 July 2023 3h01

Different development paths of LLMs https://
bit.ly/440No00 #AI #MachineLearning #DeepLearning #LLMs #DataScience

→ View original post on X — @miketamir

2 July 2023

LakehouseIQ: Natural Language Data Querying with AI

By

@databricks

–

01 July 2023 22h03

Search, understand & query data with words instead of code! #LakehouseIQ uses info about your data, usage patterns & org chart to understand your business’s jargon & unique data environment – giving significantly better answers than naive use LLMs: https://
dbricks.co/3PEDL3g

→ View original post on X — @databricks

1 July 2023

Replit Prioritizes Product Quality Over AI Benchmarks

By

@replit

–

01 July 2023 22h00

At Replit we’re not interested in hitting benchmarks and training LLMS to look good, we’re interested in building good products.

To learn more watch the full AI panel with @MosaicML’s Chief Scientist @jefrankle in conversation with Replit’s @amasad and @pirroh pic.twitter.com/OdFeWLdUdk
— Replit ⠕ (@Replit) 1 juillet 2023

At Replit we’re not interested in hitting benchmarks and training LLMS to look good, we’re interested in building good products. To learn more watch the full AI panel with @MosaicML
’s Chief Scientist @jefrankle in conversation with Replit’s @amasad and @pirroh

→ View original post on X — @replit

1 July 2023

vLLM Paged Attention Improves Text Generation Inference Performance

By

@thom_wolf

–

01 July 2023 18h19

Though these benchmarks are already out-of-date since vLLM’s paged attention landed in Text-Generation-Inference yesterday https://
github.com/huggingface/te
xt-generation-inference/pull/516
… https://
github.com/huggingface/te
xt-generation-inference/issues/478
…

→ View original post on X — @thom_wolf

1 July 2023

Whisper for efficient, professional email responses

By

@aibreakfast

–

01 July 2023 17h48

I often use Whisper (the OpenAI speech-to-text model available on the ChatGPT iOS app) to ad lib long email responses, and follow it up with a prompt to rewrite the email in a professional, courteous tone. Saves me probably an hour per day.

→ View original post on X — @aibreakfast

1 July 2023