5/ Augmenting LLMs with Databases – combines an LLM with a set of SQL databases, enabling a symbolic memory framework; completes tasks via LLM generating SQL instructions that manipulate the DB autonomously.
LLMS
-
Sparse-Quantized Representation enables 4.75-bit LLM inference
By
–
3/ Sparse-Quantized Representation – a new compressed format and quantization technique that enables near-lossless compression of LLMs across model scales; “allows LLM inference at 4.75 bits with a 15% speedup”.
-
Top ML Papers Week: AlphaDev, MusicGen, RLHF Advances
By
–
Top ML Papers of the Week (June 5-11): – AlphaDev
– MusicGen
– Fine-Grained RLHF
– Humor in ChatGPT
– Concept Scrubbing in LLM
– Augmenting LLMs with Databases
… -
Free Workshop: Create Custom Chat Data LLMs
By
–
A FREE hands-on workshop to learn how to create custom chat & data LLMs. June 22 | 9 am PST The 2-hour workshop teaches you to create state-of-the-art custom LLMs on your knowledge base & create AI agents to perform various tasks. You can register now http://
eventbrite.com/e/free-hands-o
n-workshop-create-custom-chat-data-llms-tickets-650105110887
… -
System Converting LLM Output into Checkable Queries
By
–
Sure, a system that could systematically and reliably turn LLM output (or other text) into checkable queries like that would be useful.
-
Fine-tuning SD and LLaMA: compute, data, use cases matter most
By
–
It’s trivial to build a fine tune on top of SD/LLaMA these days. Access to compute, access to data, and a kick ass use case are the hardest parts.
-
MusicGen, BAAI LLM, LIMA Dataset, Llama Falcon Variants
By
–
MusicGen, BAAI’s new LLM, LIMA dataset launch, a billion new variants of Llama/ Falcon & much more.
— Vaibhav (VB) Srivastav (@reach_vb) 11 juin 2023
You were missed hehe! 🤗 pic.twitter.com/rg2mF0hk7UMusicGen, BAAI’s new LLM, LIMA dataset launch, a billion new variants of Llama/ Falcon & much more. You were missed hehe!
-
Google Launches Generative AI Platform for Universal Access
By
–
Google’s Generative AI Platform Is Now Available To Everyone. #generativeAI #OpenAI #technology #Google #ChatGPT #AI #NLP #ArtificialIntelligence #LanguageModeling #MachineLearning #Tech #Innovation #FutureTech #ML #IoT #Programming https://
bit.ly/43DAepV -
LLM Hallucinations: Algorithm Problem Not Data Quality Issue
By
–
Even with perfect data LLMs would hallucinate. when an LLM tells you Elon Musk died a car crash, it’s not a problem with the data, it’s a problem w the algorithm, and its inherent lack of proper database records and proper methods for validating against formal knowledge stores.
