Meta, the parent company of Facebook, has launched LLaMA 2, an open-source large language model (LLM) that aims to challenge the restrictive practices of big tech competitors. Unlike proprietary AI systems launched by Google, OpenAI and others, Meta is freely publishing the code and data behind LLaMA 2 so that researchers worldwide can build on and improve the technology. Meta CEO Mark Zuckerberg believes that open-source software drives innovation and improves safety and security. The open-source nature of LLaMA 2 could lead to rapid advances in AI.
See also: Meta: Its open-source AI is being used for sex chatbots
LLaMA 2 is an open challenge to OpenAI's ChatGPT and Google's Bard.
LLaMA 2 is a language model available in three sizes: 7 billion, 13 billion, and 70 billion parameters. It is trained using reinforcement learning with human feedback (RLHF), learning from the preferences and ratings of human AI trainers. This differs from popular alternatives, such as ChatGPT, which used supervised fine-tuning, learning from labeled data provided by human annotators.
How to access and use LLaMA 2
Due to the nature of open source, there are many ways to interact with LLaMA 2. Here you will find some of the easiest ways to access and experiment with LLaMA 2 now:
1. Interact with the Chatbot Demo
The easiest way to use LLaMA 2 is to visit llama2.ai, a demo model chatbot hosted by Andreessen Horowitz. You can ask the model questions about any topic that interests you or request creative content using specific prompts. For example, you can ask “Who is the president of France?” or “Write a poem about love”. You can also change the chat mode between balanced, creative, and precise, depending on your preferences. This is the best way to get started and begin testing the new model.
2. Download the LLaMA 2 code
If you want to run LLaMA 2 on your own machine or modify the code, you can download it directly from Hugging Face, a leading platform for sharing AI models. You will need a Hugging Face account and the required libraries and dependencies to run the code. You can find the installation instructions and documentation in the LLaMA 2 repository.
Proposal: OpenAI may release an open-source AI model
3. Access via Microsoft Azure
Another option to access LLaMA 2 is via Microsoft Azure, a cloud computing service that offers various artificial intelligence solutions. You can find LLaMA 2 in Azure's AI model catalog, where you can browse, deploy, and manage AI models. You will need an Azure account and subscription to use this service. This method is recommended for more advanced users.
4. Access via Amazon SageMaker JumpStart
You can also experiment with and deploy LLaMA 2 via Amazon SageMaker JumpStart, a popular hub for algorithms, models, and solutions. SageMaker JumpStart simplifies the process of creating, training, and deploying machine learning (ML) models with just a few clicks. You will need an Amazon Web Services account and subscription to use this service. This is another method recommended for advanced users and developers.
5. Try a variation on llama.perplexity.ai
The Perplexity.ai is a web crawler that uses ML to generate generic answers to your questions and then offers a series of website links. The Llama.perplexity.ai combines the power of LLaMA 2 and Perplexity.ai to provide you with generic answers and relevant links to queries that use the new model to feed its answers. To use it, visit llama.perplexity.ai and type a query into the search box. You will see a short answer from LLaMA 2 followed by a list of links you can explore further.
Read also: Databricks: Create an open source AI chatbot!
information source:venturebeat.com
