DeepSeek Open-Sources V4 Model With 1.6 Trillion Parameters

robot
Abstract generation in progress

DeepSeek released a preview of its V4 open-source model series under the MIT license, including a V4-Pro model with about 1.6 trillion parameters. DeepSeek said model weights are available on Hugging Face and ModelScope, and both V4 models support a 1 million token context window.

This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin