main
YaLM-100B
Repository badge with A rating
View on GitHub
Grade
Name
Complexity
Churn
Issues
A
megatron_lm\curriculum_learning\ds_pretrain_gpt2.sh
 1 1
A
megatron_lm\megatron\mpu\mappings.py
23 1 -
A
megatron_lm\megatron\deprecated_data_utils\lazy_loader.py
37 1 1
A
megatron_lm\megatron\mpu\tests\commons.py
7 1 -
A
megatron_lm\examples\pretrain_gpt2.sh
 1 -
A
megatron_lm\megatron\mpu\tests\test_data.py
8 1 -
A
megatron_lm\megatron\deprecated_data_utils\scripts\presplit_sentences_json.py
 1 -
A
megatron_lm\megatron\mpu\tests\test_layers.py
24 1 -
A
docker\Dockerfile
 1 7
A
megatron_lm\megatron\mpu\utils.py
7 1 -
A
megatron_lm\megatron\deprecated_data_utils\scripts\split_json.py
19 1 5
A
megatron_lm\megatron\text_generation_utils.py
62 1 4
A
megatron_lm\megatron\__init__.py
3 1 1
A
megatron_lm\megatron\tokenizer\gpt2_tokenization.py
69 1 -
A
megatron_lm\megatron\deprecated_data_utils\tokenization.py
244 1 1
A
docker\pull.sh
 1 -
A
examples\generate_conditional_sampling.sh
 1 -
A
megatron_lm\examples\evaluate_zeroshot_gpt2.sh
 1 -
F
megatron_lm\megatron\data\helpers.cpp
19 1 18
A
megatron_lm\megatron\fused_kernels\scaled_upper_triang_masked_softmax_cuda.cu
 1 -