Issue #28: A new big LLM in the market

01.AI releases a new LLM

Welcome to Issue #28 of One Minute AI, your daily AI news companion. This issue discusses a new LLM released by 01.AI.

---

01.AI releases a new LLM

01.AI has introduced the Yi-1.5-34B model, an advanced version of its predecessor, leveraging a high-quality corpus of 500 billion tokens and fine-tuning with 3 million diverse samples. This model bridges the gap between Llama 3's 8B and 70B models, and its key features include:

• Balanced architecture: Combines computational efficiency and broad capabilities.

• High performance: Excels in multimodal tasks, logical reasoning, and code generation.

• Extended context handling: Manages long contexts up to 200,000 tokens.

• Fine-tuning process: Utilizes 3.1 trillion tokens and a robust data verification pipeline for enhanced precision.

Yi-1.5 delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension.

---

Want to help?

If you liked this issue, help spread the word and share One Minute AI with your peers and community.

You can also share feedback with us, as well as news from the AI world that you’d like to see featured by joining our chat on Substack.