NeMo-Megatron-GPT-20B

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 In progress (67%) In progress (67%)

Components with an unspecified license

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

Components with an invalid license

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

Missing components

  • Model architecture
  • Data card

Class II - Open Tooling Model

Class II - Open Tooling Model Class II - Open Tooling Model In progress (50%) In progress (50%)

Included components

  • Training code
  • Inference code
  • Evaluation code

Components with an unspecified license

  • Model parameters (Final)
  • Evaluation data
  • Model card
  • Technical report
  • Evaluation results

Components with an invalid license

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

Missing components

  • Model architecture
  • Data card

Class I - Open Science Model

Class I - Open Science Model Class I - Open Science Model In progress (50%) In progress (50%)

Included components

  • Data preprocessing code
  • Training code
  • Inference code
  • Evaluation code

Components with an unspecified license

  • Model parameters (Final)
  • Datasets
  • Evaluation data
  • Model card
  • Technical report
  • Research paper
  • Evaluation results

Components with an invalid license

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

Missing components

  • Model architecture
  • Model parameters (Intermediate)
  • Data card
Version/Parameters
20B
Organization
NVIDIA
Status
Approved
Architecture
Decoder-only
Base model
NeMo-Megatron-GPT-20B
Last updated