llmreference
IBM watsonx

Using Llama 3 8B Instruct on IBM watsonx

Implementation guide · Llama 3 · AI at Meta

ServerlessOpen Source

Quick Start

  1. 1
    Create an account at IBM watsonx and generate an API key.
  2. 2
    Use the IBM watsonx SDK or REST API to call llama3-8b-instruct — see the documentation for request format.
  3. 3
    You'll be billed $0.60/1M input, $0.60/1M output tokens. See full pricing.

Code Examples

See IBM watsonx documentation for integration details.

About IBM watsonx

The IBM watsonx AI platform is a comprehensive solution that integrates generative AI capabilities with traditional machine learning. It offers users access to a wide range of foundation models, including both IBM-developed and third-party options. The platform features a user-friendly studio for model building, a robust data management system based on an open lakehouse architecture, and governance tools to ensure compliance and ethical AI practices. Watsonx supports hybrid cloud deployments, enabling seamless integration of AI workloads into existing infrastructures, which enhances operational efficiency and scalability. This AI platform empowers organizations to leverage artificial intelligence for data-driven decision-making and innovation across multiple sectors, including healthcare, finance, and customer service. It offers advanced analytics, natural language processing, and automated workflows, aiding in tasks such as predictive analytics, content generation, and customer engagement. By streamlining processes and providing actionable insights, the platform helps businesses improve productivity and gain a competitive advantage, making it a crucial tool for those looking to harness the full potential of AI in their operations.

IBM offers a comprehensive AI platform that includes IBM watsonx, a next-generation enterprise AI and data platform. The platform integrates various AI technologies and services, including natural language processing, machine learning, and data analytics. IBM's AI solutions are designed to help businesses across industries leverage artificial intelligence for improved decision-making, automation, and innovation. The company's focus on AI extends to areas such as cloud computing, quantum computing, and industry-specific applications, making it a leader in enterprise AI solutions.

Pricing on IBM watsonx

TypePrice (per 1M)
Input tokens$0.60
Output tokens$0.60

Capabilities

Structured Outputs

About Llama 3 8B Instruct

The Llama 3 8B Instruct model, released on April 18, 2024, is Meta's latest instruction-following language model with 8 billion parameters. It utilizes an auto-regressive transformer architecture with Grouped-Query Attention for improved scalability. Trained on over 15 trillion tokens and fine-tuned with 10 million human-annotated examples, it excels in dialogue and conversational tasks. The model outperforms its predecessors on industry benchmarks, scoring 68.4 on MMLU (5-shot). Designed for commercial and research applications, it prioritizes safety and helpfulness, making it suitable for chatbots, virtual assistants, and other interactive AI applications. For more details, visit the Hugging Face page [1].

Model Specs

Released2024-04-18
Parameters8B
Context8K
ArchitectureDecoder Only
Knowledge cutoff2023-03

Provider

IBM watsonx
IBM watsonx

IBM

Armonk, New York, United States