As expected, Meta today announced the Llama 3.1 family of AI models. The Llama 3.1 family includes three models: Llama 3.1 8B, Llama 3.1 70B, and Llama 3.1 405B. All three models now come with an improved 128K context length. Also, Meta now allows developers to use the outputs from Llama models to improve other models.
Meta evaluated the performance of the Llama 3.1 family of models on over 150 benchmark datasets. Meta also conducted several human evaluations to compare these models with other competing models in real-world scenarios. According to the results, Llama 3.1 405B is competitive with leading foundation models, including GPT-4, GPT-4o, and Claude 3.5 Sonnet. Hence, Meta now claims that Llama 3.1 405B is the world"s largest and most capable openly available foundation model. Also, the smaller Llama 3.1 models are competitive with both closed and open models that are similar in size.
Benchmarks comparison of Llama 3.1 405B with other leading models:
Benchmarks comparison of Llama 3.1 8B and Llama 3.1 70B with other leading models:
The new Llama 3.1 family of models can now be used by developers via AWS, NVIDIA, Databricks, Groq, Dell, Azure, and Google Cloud. The Llama 3.1 405B is available via Azure AI"s Models-as-a-Service as a serverless API endpoint. Also, the latest fine-tuned versions of Llama 3.1 8B and Llama 3.1 70B are now available on the Azure AI Model Catalog. You can read more about it here. You can read more about it here.
Mark Zuckerberg, Founder and CEO of Meta, wrote the following regarding the Llama 3.1 release:
"Today, several tech companies are developing leading closed models. But open source is quickly closing the gap. Last year, Llama 2 was only comparable to an older generation of models behind the frontier. This year, Llama 3 is competitive with the most advanced models and leading in some areas. Starting next year, we expect future Llama models to become the most advanced in the industry. But even before that, Llama is already leading on openness, modifiability, and cost efficiency."
Meta"s Llama 3.1 release marks a significant milestone in the open-source AI industry. With performance rivaling leading closed models and a commitment to accessibility, Meta is democratizing AI capabilities, fostering innovation, and setting a new standard for collaboration and transparency.
Source: Meta