IDEFICS-9B

Parameters

9B

Published

Aug 22, 2023

IDEFICS-9B is an AI model developed by Hugging Face (United States), first published in August 2023. It works in the multimodal, language and vision domain, on tasks such as language modeling, image captioning and visual question answering.

Epoch AI has no training-compute estimate for this model. The model has 9,000,000,000 parameters. It was trained on roughly 262B datapoints. Training ran on 128 NVIDIA A100 for about 350 hours.

Access: Open weights (non-commercial). Its weights are openly available. It is built on top of CLIP ViT-H/14 - LAION-2B,LLaMA-7B. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Hugging Face
Country of organization: United States
Domain: Multimodal, Language, Vision
Task: Language modeling, Image captioning, Visual question answering
Compute estimation method: Operation counting, Hardware
Parameters: 9,000,000,000
Dataset size: 262B
Training hardware: NVIDIA A100
Chips used: 128
Training time: 350 h
Training power draw: 101.8 kW
Numerical format: BF16
Model accessibility: Open weights (non-commercial)
Open weights: Yes
Base model: CLIP ViT-H/14 - LAION-2B, LLaMA-7B
Epoch confidence: Confident