tmp save
Showing
- draw_diff.py 16 additions, 7 deletionsdraw_diff.py
- finetune/__init__.py 0 additions, 0 deletionsfinetune/__init__.py
- fp16/__init__.py 0 additions, 30 deletionsfp16/__init__.py
- fp16/fp16.py 0 additions, 629 deletionsfp16/fp16.py
- fp16/fp16util.py 0 additions, 204 deletionsfp16/fp16util.py
- fp16/loss_scaler.py 0 additions, 237 deletionsfp16/loss_scaler.py
- generate_samples.py 0 additions, 2 deletionsgenerate_samples.py
- model/__init__.py 0 additions, 1 deletionmodel/__init__.py
- model/base_model.py 54 additions, 0 deletionsmodel/base_model.py
- model/distributed.py 0 additions, 121 deletionsmodel/distributed.py
- model/gpt2.py 17 additions, 0 deletionsmodel/gpt2.py
- model/gpt2_modeling.py 0 additions, 126 deletionsmodel/gpt2_modeling.py
- model/mixins.py 69 additions, 0 deletionsmodel/mixins.py
- mpu/__init__.py 2 additions, 4 deletionsmpu/__init__.py
- mpu/grads.py 0 additions, 74 deletionsmpu/grads.py
- mpu/sparse_transformer.py 0 additions, 729 deletionsmpu/sparse_transformer.py
- mpu/transformer.py 412 additions, 0 deletionsmpu/transformer.py
- mpu/utils.py 25 additions, 11 deletionsmpu/utils.py
- pretrain_gpt2.py 63 additions, 93 deletionspretrain_gpt2.py
- utils.py 0 additions, 22 deletionsutils.py
Loading
Please register or sign in to comment