├── .gitignore ├── LICENSE ├── README.md ├── cs336_spring2025_assignment1_basics.pdf ├── modules ├── __init__.py └── modules.py ├── pyproject.toml ├── test ├── __init__.py ├── test_my_lm.py └── val_my_lm.py ├── test_logs ├── 模型结构对训练的影响.pdf └── 超参数对训练的影响.pdf ├── train ├── __init__.py ├── config.py ├── tokenize_corpus.py ├── train_my_bpe.py └── train_my_lm.py └── uv.lock /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/README.md -------------------------------------------------------------------------------- /cs336_spring2025_assignment1_basics.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/cs336_spring2025_assignment1_basics.pdf -------------------------------------------------------------------------------- /modules/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /modules/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/modules/modules.py -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/pyproject.toml -------------------------------------------------------------------------------- /test/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /test/test_my_lm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/test/test_my_lm.py -------------------------------------------------------------------------------- /test/val_my_lm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/test/val_my_lm.py -------------------------------------------------------------------------------- /test_logs/模型结构对训练的影响.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/test_logs/模型结构对训练的影响.pdf -------------------------------------------------------------------------------- /test_logs/超参数对训练的影响.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/test_logs/超参数对训练的影响.pdf -------------------------------------------------------------------------------- /train/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /train/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/train/config.py -------------------------------------------------------------------------------- /train/tokenize_corpus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/train/tokenize_corpus.py -------------------------------------------------------------------------------- /train/train_my_bpe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/train/train_my_bpe.py -------------------------------------------------------------------------------- /train/train_my_lm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/train/train_my_lm.py -------------------------------------------------------------------------------- /uv.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sherlock1956/TransformerFromScratch/HEAD/uv.lock --------------------------------------------------------------------------------