Llama 3.2 is here…
Today, we’re releasing Llama 3.2, which includes small and medium-sized vision LLMs (11B and 90B), and lightweight, text-only models (1B and 3B) that fit onto edge and mobile devices, including pre-trained and instruction-tuned versions.
The Llama 3.2 1B and 3B models support context length of 128K tokens and are state-of-the-art in their class for on-device use cases like summarization, instruction following, and rewriting tasks running locally at the edge. These models are enabled on day one for Qualcomm and MediaTek hardware and optimized for Arm processors.
The Llama 3.2 11B and 90B vision models are drop-in replacements for their corresponding text model equivalents, while exceeding on image understanding tasks compared to closed models, such as Claude 3 Haiku. Unlike other open multimodal models, both pre-trained and aligned models are available to be fine-tuned for custom applications using torchtune and deployed locally using torchchat.
We’re sharing the first official Llama Stack distributions, which will greatly simplify the way developers work with Llama models in different environments, including single-node, on-prem, cloud, and on-device, enabling turnkey deployment of retrieval-augmented generation (RAG) and tooling-enabled applications with integrated safety. We’ve been working closely with partners like AWS, Databricks, Dell Technologies, Fireworks, Infosys, and Together AI to build Llama Stack distributions for their downstream enterprise clients. On-device distribution is via PyTorch ExecuTorch, and single-node distribution is via Ollama.
Pointers:
Blog: https://lnkd.in/gzB28z_3
Llama Models GitHub repo: https://lnkd.in/gK4QWDXM
Model Cards & License: https://lnkd.in/gTnBf3M4
Mobile apps built on Executorch: https://lnkd.in/gYvmPU3e
Download at Llama.com or at Hugging Face
On a personal note, this is my last release as part of the Llama team at Meta. I’m very excited to share that I am rejoining my good friends Soumith Chintala, Damien Sereni, Aparna Ramani, Gregory Chanan and many others to help lead PyTorch. The open ecosystem is thriving and I’m excited to be part of the next wave of innovation..
Cheers..