Loading...
Market
Will Pixtral 12B be mentioned in a major tech conference keynote by June 30, 2025?
2
Resolution / Starting Odds
Yes, at CES 2025 • 25%
Yes, at Google I/O 2025 • 25%
Yes, at Microsoft Build 2025 • 25%
No • 25%
Official agendas and recordings of major tech conferences
Story
Mistral AI Releases 25.38 GB Pixtral 12B Multimodal AI Model with 400M Parameters
Sep 11, 2024, 07:31 AM
Mistral AI has released a new multimodal AI model called Pixtral 12B. This model integrates both language and vision processing capabilities, marking a significant advancement in multimodal AI technology. The Pixtral 12B model features a text backbone based on Mistral Nemo 12B and includes a vision adapter with 400 million parameters. The model architecture consists of 40 layers, a hidden dimension of 14,336, a dimension of 5120, a head dimension of 128, 32 heads, and 8 kv-heads. It also has a vocabulary size of 131,072. Additionally, the vision adapter uses GeLU and 2D RoPE, and the tokenizer includes three new special tokens. The model is available for download via a torrent magnet link and has a size of approximately 25.38 GB.
View original story
Similar markets
Yes • 50%
No • 50%
Yes • 50%
No • 50%
Yes • 50%
No • 50%
Yes • 50%
No • 50%
Yes • 50%
No • 50%
Yes • 50%
No • 50%
0-10 • 25%
11-20 • 25%
21-30 • 25%
31+ • 25%
Language Processing • 25%
Vision Processing • 25%
Integration of Language and Vision • 25%
Ease of Use • 25%
Healthcare • 25%
Finance • 25%
Retail • 25%
Entertainment • 25%