SiliconRepublic16d
Meta releases compact versions of Llama 3.2 AI models
Meta has released compact versions of its lightweight Llama 3.2 1B and 3B models that are small enough to run effectively on mobile devices. The Facebook owner, in an announcement yesterday (24 ...
the-decoder23d
Nvidia improves Meta's Llama model with new training approach
The company achieved this through a special training procedure combining evaluation and preference models. The new model, called Llama-3.1-Nemotron-70B-Instruct, is based on Meta's open-source Llama 3 ...
lablab26d
Building a Multimodal Edge Application with Llama 3.2 and Llama Guard
The evolution of artificial intelligence has been nothing short of remarkable, and one of the most exciting developments I've encountered recently is Meta's release of Llama 3.2 and Llama Guard. These ...
Mint1mon
GPT, Claude, Llama? How to tell which AI model is best
When Meta, the parent company of Facebook, announced its latest open-source large language model (LLM) on July 23rd, it claimed that the most powerful version of Llama 3.1 had “state-of-the-art ...
Beebom1mon
Meta Releases Llama 3.2 Models with Vision Capability For the First Time
Meta has released Llama 3.2 family models, which include smaller text-only models Llama 3.2 1B and 3B for on-device tasks on phones and laptops. The other two models are Llama 3.2 11B and 90B, which ...
GitHub2mon
Issues: ggerganov/llama.cpp
Bug: Certain RPC Servers cause major slowdown to Host machine bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable) ...
GitHub9mon
Distributed Llama
Distributed Llama allows you to run huge LLMs in-house. The project uses TCP sockets to synchronize the state. You can easily configure your AI cluster by using a home router. TinyLlama 1.1B 3T Q40 ...