llmreference
Hyperbolic AI Inference

Using Llama 3 70B Instruct on Hyperbolic AI Inference

Implementation guide · Llama 3 · AI at Meta

ServerlessOpen Source

Quick Start

  1. 1
    Create an account at Hyperbolic AI Inference and generate an API key.
  2. 2
    Use the Hyperbolic AI Inference SDK or REST API to call llama3-70b-instruct — see the documentation for request format.
  3. 3
    You'll be billed $0.40/1M input, $0.40/1M output tokens. See full pricing.

Code Examples

See Hyperbolic AI Inference documentation for integration details.

About Hyperbolic AI Inference

Hyperbolic's AI platform offers an open-access cloud service that democratizes advanced AI computing resources. At its core is Hyper-dOS, a decentralized orchestration layer that efficiently manages global GPU infrastructure with auto-scaling and self-healing capabilities. The platform supports a wide range of AI functionalities, including real-time inference services, model training and fine-tuning, and performance evaluation. Users can access various AI models, such as large language models for text generation and image generation models like Stable Diffusion. The platform also incorporates a vector database for managing high-dimensional data and utilizes retrieval-augmented generation (RAG) techniques, enhancing the overall performance and flexibility of AI applications. The platform provides cost-effective access to high-performance GPUs, potentially reducing operational expenses by up to 80% compared to traditional cloud providers. It allows users to monetize idle GPU resources, fostering a collaborative ecosystem where contributions are rewarded. The platform ensures data privacy and integrity through advanced cryptographic techniques and a verification layer developed in collaboration with academic institutions. This combination of features enhances the scalability and reliability of AI applications, empowering users to innovate and develop AI solutions without the constraints of high costs or limited access to computing power.

Hyperbolic is building an open-access AI cloud platform that provides affordable inference and compute resources for AI applications. Their platform enables developers, researchers, and individuals to build AI applications without relying on centralized infrastructures. Hyperbolic aims to create an open AI ecosystem and economy where contributors are rewarded for their participation. The platform offers access to state-of-the-art AI models, including Llama 3.1 405B and FLUX.1 for image generation, with features such as extended context lengths and optimized performance. Hyperbolic's mission is to democratize AI development by providing a decentralized alternative to traditional Web2 platforms, fostering innovation in the AI space.

Pricing on Hyperbolic AI Inference

TypePrice (per 1M)
Input tokens$0.40
Output tokens$0.40

Capabilities

Structured Outputs

About Llama 3 70B Instruct

The Llama 3 70B Instruct model is a large language model with 70 billion parameters, released by Meta on April 18, 2024. It's an instruction-tuned variant optimized for conversational applications, utilizing an advanced auto-regressive transformer architecture. The model excels in following instructions and engaging in dialogue, having been trained on over 15 trillion tokens with a December 2023 knowledge cutoff. It demonstrates superior performance on industry benchmarks, scoring 82.0 on the MMLU (5-shot) test. The model incorporates extensive safety measures and optimizations, including RLHF, to enhance helpfulness and reduce harmful content generation. For more details, visit the model's Hugging Face page [1].

Model Specs

Released2024-04-18
Parameters70B
Context8K
ArchitectureDecoder Only
Knowledge cutoff2023-12

Provider

Hyperbolic AI Inference
Hyperbolic AI Inference

Hyperbolic

Irvine, California, United States