This container houses Llama3.1-Typhoon2-8B-Instruct, an 8B LLM by SCB 10X based on Meta's Llama3.1, tuned for conversational tasks in Thai and English, marking a significant advance for Thai Natural Language Processing.
Llama3.1-Typhoon2-8b-Instruct Overview
Description:
This container houses the Llama3.1-Typhoon2-8Bb-Instruct, which is an instruction-tuned large language model with 8 billion parameters, primarily designed for the Thai language and also proficient in English. This model, based on Meta's Llama3.1-8B, is engineered to comprehend and execute user commands in a conversational manner, making it suitable for a wide array of applications including, but not limited to, question answering, content generation, and summarization. Developed by SCB 10X, it represents a significant advancement in Thai natural language processing.
The container components are ready for commercial/non-commercial use.
Third-Party Community Consideration
This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party's requirements for this application and use case; see link to Non-NVIDIA [scb10x/llama3.1-typhoon2-8b-instruct]
(scb10x/llama3.1-typhoon2-8b-instruct · Hugging Face).
License/Terms of Use:
GOVERNING TERMS: The NIM container is governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products. The model is governed by the NVIDIA Community Model License Agreement;
ADDITIONAL INFORMATION: Llama 3.1 Community Model License. Built with Llama.
Deployment Geography:
Global
Release Date:
Huggingface 03/31/2025 via
scb10x/llama3.1-typhoon2-8b-instruct · Hugging Face
NGC 06/10/2025
Llama3.1-Typhoon2-8b-Instruct
Llama3.1-Typhoon2-8b-Instruct Container includes the following model:
| Model Name & Link | Use Case | How to Pull the Model |
|---|---|---|
| Llama3.1-Typhoon2-8b-Instruct | A Thai-English bilingual instruction-tuned large language model for tasks such as question answering, content creation, and general chat applications. | Automatic |
Deployment Details:
Visit the NIM Container LLM page for release documentation, deployment guides, and more.
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
Reference(s):
N/A
Container Version(s):
nvcr.io/nvstaging/nim/llama3.1-typhoon2-8b-instruct:1.8.5-31055025
Ethical Considerations:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal developer team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
Please report security vulnerabilities or NVIDIA AI Concerns here.
You are responsible for ensuring that your use of NVIDIA AI Foundation Models complies with all applicable laws.