IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license

Hugging Face
Read the full article
IBM has released Granite Time Series PatchTST-FM-r2, a 385M-parameter zero-shot forecasting model with improved architecture and probabilistic forecasting, ranking #2 on the GIFT-Eval benchmark. It supports imputation of missing data and is available under a commercial-friendly open-source license.

More on this story


More in Machine Learning

Machine Learning3 min read

Google ML Drift Accelerates On-Device AI Inference Across Diverse GPUs

InfoQ (AI, ML & Data)
Machine Learning5 min read

Researchers from Stanford and UC Berkeley Introduce TokenGate: Token-Gated Attention Makes Long-Context Prefill Up to 11.3x Faster

MarkTechPost
Machine Learning2 min read

Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend

Covered by 5 sources