In December, @SnowflakeDB AI Research announced SwiftKV, a new approach that reduces inference computation during prompt processing. Today they're making SwiftKV-optimized Llama models available on Cortex AI that reduce inference costs by up to 75%!
@aiatmeta
-
Congratulations on Llama 3.3 RAG Performance Release
By
–
Congratulations on the release! Very exciting to see the impressive RAG performance you're achieving built on Llama 3.3!
-
Meta’s SeamlessM4T Research Published in Nature Journal
By
–
Today we’re excited to share that our work on SeamlessM4T from Meta FAIR was published in the latest issue of @Nature https://
go.fb.me/hmea6y -
Inarix Uses Meta AI Models to Transform Smartphones Into Crop Assessment Tools
By
–
The team at Inarix is using open source AI models from Meta FAIR to turn smartphones into pocket laboratories for farmers. Building a foundational model on top of DINOv2, the platform enables farmers to assess crop value in real time https://
go.fb.me/dov53u -
Meta FAIR Research: Memory Layers Scaled to Modern AI Models
By
–
New research from Meta FAIR — Meta Memory Layers at Scale. This work takes memory layers beyond proof-of-concept, proving their utility at contemporary scale https://
go.fb.me/3lbt4m -
Meta Research on Generative Retrieval for Recommendation Systems
By
–
Newly published research for generative retrieval for recommendations from teams at Meta. – Preference Discerning with LLM-Enhanced Generative Retrieval https://
go.fb.me/evvcu8
– Unifying Generative and Dense Retrieval for Sequential Recommendation https://
go.fb.me/i7l955 -
Byte Latent Transformer: Patches Match Token Performance with Better Efficiency
By
–
New from Meta FAIR — Byte Latent Transformer: Patches Scale Better Than Tokens introduces BLT, which for the first time, matches tokenization-based LLM performance at scale with significant improvements in inference efficiency & robustness. Paper https://
go.fb.me/w23lmz -
Byte Latent Transformer Repository Available on GitHub
By
–
More in the Byte Latent Transformer repo on GitHub
-
SemiKong: First Open Source Semiconductor-Focused LLM Model
By
–
SemiKong, a model built with Llama, is the world's first open source semiconductor-focused LLM. With this work @aitomatic is enabling semiconductor companies to build Domain-Expert Agents to capture and scale their deep domain expertise https://
go.fb.me/9yq4mq -
LinkedIn’s EON-8B Model: 75x More Cost-Effective Than GPT-4
By
–
Through experimentation @LinkedIn found EON-8B, a domain-adapted version of Llama 3.1 8B, to be 75x and 6x cost effective in comparison to GPT-4 and GPT-4o respectively. More on their domain-adapted foundation model work https://
go.fb.me/curuy3