DeepSeek-MoE-145B

Primary tabs

Disclaimer

This is beta software containing preliminary data which is incomplete and may be inaccurate. If you experience errors with the tool or discover inaccurate information, please open an Issue or Pull Request on the MOF GitHub repository. Thank you.
Download JSONDownload YAML

Class III - Open Model

Class III - Open Model Class III - Open Model Qualified Qualified

Components with an unspecified license

  • Model architecture
  • Model parameters (Final)
  • Model card
  • Data card
  • Technical report
  • Evaluation results

Components with an invalid license

  • Model architecture
  • Model parameters (Final)
  • Model card
  • Data card
  • Technical report
  • Evaluation results

Class II - Open Tooling Model

Class II - Open Tooling Model Class II - Open Tooling Model Qualified Qualified

Components with an unspecified license

  • Model architecture
  • Training code
  • Inference code
  • Evaluation code
  • Model parameters (Final)
  • Evaluation data
  • Model card
  • Data card
  • Technical report
  • Evaluation results

Components with an invalid license

  • Model architecture
  • Training code
  • Inference code
  • Evaluation code
  • Model parameters (Final)
  • Evaluation data
  • Model card
  • Data card
  • Technical report
  • Evaluation results

Class I - Open Science Model

Class I - Open Science Model Class I - Open Science Model In progress (93%) In progress (93%)

Included components

  • Research paper

Components with an unspecified license

  • Model architecture
  • Data preprocessing code
  • Training code
  • Inference code
  • Evaluation code
  • Model parameters (Final)
  • Model parameters (Intermediate)
  • Datasets
  • Evaluation data
  • Model card
  • Data card
  • Technical report
  • Evaluation results

Components with an invalid license

  • Model architecture
  • Data preprocessing code
  • Training code
  • Inference code
  • Evaluation code
  • Model parameters (Final)
  • Model parameters (Intermediate)
  • Datasets
  • Evaluation data
  • Model card
  • Data card
  • Technical report
  • Research paper
  • Evaluation results
Description
-
Version/Parameters
145B
Organization
DeepSeek AI
Type
Language model
Status
Approved
Base model
DeepSeek-MoE-16B
Last updated