TYPHOON Logo
TYPHOON
TYPHOON 2

TYPHOON 2

General
Llama
1B
3B
7B
8B
70B

Comprehensive Thai-engineered model lineup from 1B to 70B parameters with 128K context and function-calling capabilities.

Released
January 9, 2025
Context
up to 128K tokens
Input
Text
Output
Text
TYPHOON 2
About this Model

TYPHOON 2 features a comprehensive model lineup spanning from lightweight edge-optimized variants (1B and 3B parameters) to a powerful 70B parameter model, all specifically engineered for Thai language applications. The architecture demonstrates exceptional benchmark performance while supporting extensive context lengths up to 128,000 tokens, incorporating robust safety classification systems and sophisticated function-calling capabilities to enable advanced AI applications.

Key Features
128K Context Window
Enabling processing and generation of longer form content
Function calling capabilities
Support function calling to enable complex workflow.
Available in 5 Sizes
1B, 3B, 7B, 8B, and 70B both pretrained and instruct versions to support various use cases and computational constraints
OpenAI Compatibility
Both TYPHOON API and Together API endpoints are fully compatible with the OpenAI API. If your application is already using OpenAI's client libraries, you can configure it to point to our API servers and start using TYPHOON 2.
Release History
Version 1
January 9, 2025
Initial release