The 11B and 90B currently support multimodal tasks and text-only function calls.
MULTIMODAL AI
-
AI2 Releases Multimodal Open-Source Models
By
–
congrats to AI2 for also releasing (what look like) great multimodal open-source models today!!! https://t.co/hgcVwy4BER
— Soumith Chintala (@soumithchintala) 25 septembre 2024congrats to AI2 for also releasing (what look like) great multimodal open-source models today!!!
-
Anticipating Developer Innovation with New Multimodal Lightweight Models
By
–
We can't wait to see the wave of innovation from developers building on these new multimodal and lightweight models on Bedrock!
-
Llama 3.2 Vision Models Compete with Leading Closed Models
By
–
Evaluating performance on extensive human evaluations and benchmarks, results suggest that Llama 3.2 vision models are competitive with leading closed models on image recognition + a range of visual understanding tasks.
-
New Llama Vision Models Updates and Details Released
By
–
This is just a small slice of what’s new with our Llama vision models. You can find more details in the full model card published on GitHub
-
New Vision Model Architecture for Image Reasoning with Adapter Weights
By
–
Our vision models required an entirely new architecture to support image reasoning. This was accomplished by training a set of adapter weights that integrate the pre-trained image encoder into the pre-trained language model.
-
Llama 3.2 Multimodal Models with Improved Image Understanding
By
–
By training adapter weights without updating the language-model parameters, Llama 3.2 11B & 90B retain their text-only performance while outperforming on image understanding tasks vs closed models. Enabling developers to use these new models as drop-in replacements for Llama 3.1. pic.twitter.com/TQo4IIyqRH
— AI at Meta (@AIatMeta) 25 septembre 2024By training adapter weights without updating the language-model parameters, Llama 3.2 11B & 90B retain their text-only performance while outperforming on image understanding tasks vs closed models. Enabling developers to use these new models as drop-in replacements for Llama 3.1.
-
Technical Insights on New Llama Vision Models Release
By
–
A few technical insights on the new Llama vision models we’re releasing today
-
Llama 3.2 Multimodal Vision Capabilities for Image and Data Analysis
By
–
Llama 3.2 11B & 90B include support for a range of multimodal vision tasks. These capabilities enable scenarios like captioning images for accessibility, providing natural language insights based on data visualizations and more.
-
Inquiry on LLM multimodal capabilities and future model releases
By
–
Can someone clarify if voice will be tts or multimodal too? And should we expect 3.2 405b?