DeepSeek-Math/train at 2b3c49c9cb387883749459b75f89e8d070af8f2e - DeepSeek-Math - Gitea: Git with a cup of tea

DeepSeek/DeepSeek-Math

mirror of https://github.com/deepseek-ai/DeepSeek-Math synced 2025-06-26 18:16:20 +00:00

Files

History

jayeshthk 2b3c49c9cb Add commented options for output attentions and hidden states in DeepSeekMathConfig

2025-06-19 17:46:50 +05:30

..

model.py

Add commented options for output attentions and hidden states in DeepSeekMathConfig

2025-06-19 17:46:50 +05:30

train.py

Implement DeepSeek-Math model and training pipeline with dataset handling and distributed training support

2025-06-19 17:27:05 +05:30