add

0d99ae1f · silencealiang · c271aaae · 0d99ae1f · 0d99ae1f · 0d99ae1f
Commit 0d99ae1f authored Mar 14, 2025 by silencealiang
20 changed files
--- a/megatron/core/datasets/masked_dataset.py
+++ b/megatron/core/datasets/masked_dataset.py
--- a/megatron/core/datasets/megatron_dataset.py
+++ b/megatron/core/datasets/megatron_dataset.py
--- a/megatron/core/datasets/megatron_tokenizer.py
+++ b/megatron/core/datasets/megatron_tokenizer.py
--- a/megatron/core/datasets/multimodal_dataset.py
+++ b/megatron/core/datasets/multimodal_dataset.py
--- a/megatron/core/datasets/readme.md
+++ b/megatron/core/datasets/readme.md
--- a/megatron/core/datasets/retro/__init__.py
+++ b/megatron/core/datasets/retro/__init__.py
--- a/megatron/core/datasets/retro/config/__init__.py
+++ b/megatron/core/datasets/retro/config/__init__.py
--- a/megatron/core/datasets/retro/config/bert_embedders.py
+++ b/megatron/core/datasets/retro/config/bert_embedders.py
--- a/megatron/core/datasets/retro/config/config.py
+++ b/megatron/core/datasets/retro/config/config.py
--- a/megatron/core/datasets/retro/config/gpt_chunk_datasets.py
+++ b/megatron/core/datasets/retro/config/gpt_chunk_datasets.py
--- a/megatron/core/datasets/retro/config/tokenizers.py
+++ b/megatron/core/datasets/retro/config/tokenizers.py
--- a/megatron/core/datasets/retro/db/__init__.py
+++ b/megatron/core/datasets/retro/db/__init__.py
--- a/megatron/core/datasets/retro/db/build.py
+++ b/megatron/core/datasets/retro/db/build.py
--- a/megatron/core/datasets/retro/db/dataset.py
+++ b/megatron/core/datasets/retro/db/dataset.py
--- a/megatron/core/datasets/retro/db/utils.py
+++ b/megatron/core/datasets/retro/db/utils.py
--- a/megatron/core/datasets/retro/external_libs.py
+++ b/megatron/core/datasets/retro/external_libs.py
--- a/megatron/core/datasets/retro/index/__init__.py
+++ b/megatron/core/datasets/retro/index/__init__.py
--- a/megatron/core/datasets/retro/index/build.py
+++ b/megatron/core/datasets/retro/index/build.py
--- a/megatron/core/datasets/retro/index/factory.py
+++ b/megatron/core/datasets/retro/index/factory.py
--- a/megatron/core/datasets/retro/index/index.py
+++ b/megatron/core/datasets/retro/index/index.py