Using Llama 2 70B Chat on OCI Generative AI
Implementation guide · Llama 2 · AI at Meta
Quick Start
- 1
- 2Use the OCI Generative AI SDK or REST API to call
llama2-70b-chat— see the documentation for request format.
Code Examples
About OCI Generative AI
Oracle Cloud Infrastructure (OCI) provides a comprehensive AI platform that seamlessly integrates various artificial intelligence and machine learning capabilities into its cloud services. The platform offers a suite of prebuilt services, including OCI Vision for image recognition, OCI Language for advanced text analysis, OCI Speech for speech-to-text and text-to-speech functionalities, and OCI Document Understanding for extracting data from documents. These services are designed to simplify AI integration into applications, allowing developers to enhance their solutions without requiring extensive machine learning expertise. Additionally, the platform includes OCI Digital Assistant, which provides conversational AI capabilities, enabling businesses to deploy chatbots for efficient customer inquiry handling. Beyond prebuilt services, the AI platform supports advanced machine learning functionalities through tools like the Oracle AI Platform Cloud Service. This fully managed environment facilitates building, training, and deploying machine learning models, offering features such as AutoML, integrated Jupyter Notebooks, and collaborative workspaces for data science teams. The platform also includes specialized offerings aimed at enhancing customer experience, such as predictive analytics for sales and marketing, automated content generation for customer interactions, and intelligent automation for service requests. These capabilities not only improve operational efficiency but also enable organizations to deliver personalized and timely responses to customer needs, ultimately enhancing overall engagement and satisfaction.
OCI Generative AI is Oracle Cloud's managed foundation-model service, providing API access to Cohere and Meta Llama models for text generation, summarization, and embedding workloads within Oracle's secure cloud infrastructure.
Pricing on OCI Generative AI
Capabilities
About Llama 2 70B Chat
Llama 2 70B Chat is a large-scale language model with 70 billion parameters, designed for conversational AI applications. Released on July 18, 2023, it's part of Meta's Llama 2 family, featuring advanced transformer architecture optimized through supervised fine-tuning and reinforcement learning with human feedback. The model excels in generating human-like responses, outperforming many open-source alternatives and rivaling closed-source models like ChatGPT. Trained on 2 trillion tokens from diverse public sources, it's suitable for commercial and research applications in English, particularly for assistant-like functionalities. The model is available on Hugging Face for further exploration and implementation .