Jan 1, 07:15 PM

Microsoft Paper Reveals GPT-4o-Mini Size at 8B Parameters; GPT-4 at 1.76T, Claude 3.5 Sonnet at 175B

A recent paper from Microsoft has revealed the sizes of various large language models (LLMs), indicating that the GPT-4o-mini is approximately an 8 billion parameter model. Other models noted in the paper include Claude 3.5 Sonnet at 175 billion parameters, GPT-4 at 1.76 trillion parameters, GPT-4o at 200 billion parameters, o1-preview at 300 billion parameters, and o1-mini also at 200 billion parameters. The findings suggest that distillation techniques at OpenAI are effective, as evidenced by the reduced size of the GPT-4o-mini compared to its larger counterparts.

#Microsoft

Written with ChatGPT (GPT-4o mini).