Meta on Tuesday launched its newest and largest synthetic intelligence (AI) mannequin to the general public. Known as Meta Llama 3.1 405B, the corporate says the open-source mannequin outperforms main closed AI fashions comparable to GPT-4, GPT-4o, and Claude 3.5 Sonnet throughout a number of benchmarks. The beforehand released Llama 3 8B and 70B AI fashions have additionally been upgraded. The newer variations have been distilling from the 405B mannequin and now supply a 1,28,000 tokens context window. Meta claims each of those fashions at the moment are the main open-source giant language fashions (LLMs) for his or her sizes.
Saying the brand new AI mannequin in a weblog post, the expertise conglomerate mentioned, “Llama 3.1 405B is the primary brazenly accessible mannequin that rivals the highest AI fashions relating to state-of-the-art capabilities basically data, steerability, math, instrument use, and multilingual translation.”
Notably, 405B right here refers to 405 billion parameters, which could be understood because the LLM’s variety of data nodes. The upper the parameter measurement, the more proficient an AI mannequin is in dealing with advanced queries. The context window of the mannequin is 128,000 tokens. It helps English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai languages.
The corporate claims the Llama 3.1 405B was evaluated on greater than 150 benchmark checks throughout a number of experience. Based mostly on the information shared within the submit, Meta’s AI mannequin scored 96.8 within the Grade College Math 8K (GSM8K) GPT-4’s 94.2, GPT-4o’s 96.1, and Claude 3.5 Sonnet’s 96.4. It additionally outperformed these fashions within the AI2’s Reasoning Problem (ARC) benchmark for science proficiency, Nexus for instrument use, and the Multilingual Grade College Math (MGSM) benchmark.
Meta’s largest AI mannequin was skilled on greater than 15 trillion tokens with greater than 16 thousand Nvidia H100 GPUs. One of many main introductions within the Llama 3.1 405B is the official help for tool-calling which can enable builders to make use of Courageous Seek for net searches, Wolfram Alpha to carry out advanced mathematical calculations, and Code Interpreter to generate Python code.
For the reason that Meta Llama 3.1 405B is obtainable in open supply, people can entry it from both the corporate’s website or from its Hugging Face listing. Nonetheless, being a big mannequin, it requires roughly 750GB of disk space for storing to run. For inferencing, two nodes on Mannequin Parallel 16 (MP16) may also be needed. Mannequin Parallelism 16 is a particular implementation of mannequin parallelism the place a big neural community is separated into 16 units or processors.
Other than being accessible publicly, the mannequin can also be accessible on main AI platforms by AWS, Nvidia, Databricks, Groq, Dell, Azure, Google Cloud, Snowflake, and extra. The corporate says a complete of 25 such platforms can be powered by Llama 3.1 405B. For security and safety, the corporate has used Llama Guard 3 and Immediate Guards, two new instruments that safeguard the LLM from potential hurt and abuse.
