US Edition
Trillion Labs Unveils Inference-Specialized Llm 'Tree-21b'... "Improving Low-Resource Language Learning Problems"
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.2 Articles
2 Articles
Trillion Labs Releases Its Proprietary LLM ‘Tri-21B’ as Open Source
(Photo courtesy of Trillion Labs) South Korean artificial intelligence startup Trillion Labs has released its proprietary large language model (LLM), "Tri-21B," as open source. Developed entirely from scratch using a pre-training approach, the model features more than triple the number of parameters compared to its predecessor, while maintaining a lightweight structure that allows it to run on a single GPU. According to Trillion Labs, Tri-21B is…
[Digital Daily Reporter Lee Geon-han] Trillion Labs announced on the 23rd that it has released its next-generation LLM (Large Language Model) 'Tri-21B' as open source. Tri-21B has significantly improved performance by expanding the number of parameters by more than three times compared to its predecessor, the Trillion-7B model, to 21 billion. At the same time, it is characterized by being lightweight and efficient enough to operate smoothly eve…
Coverage Details
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
