Transformers from scratch
Project description
rawformer
Transformers from scratch.
This library implements transformer architectures from pure PyTorch. It's not production ready, more so for my personal use and understanding.
Supported architectures:
- ViT
Supported positional encodings:
- Learned
- RoPE (1D and 2D)
Installation
pip install rawformer
This library uses runtime checks to validate itself and throw better error messages early. NOTE: Beartype is incompatible with torch.compile.
- Turn off runtime type checking with env var:
BEARTYPE=0 - Turn off python interpreter's assert statements with env var:
PYTHONOPTIMIZE=1
Developer install
uv sync --extra cpu
uv sync --extra cuda
pre-commit install
pre-commit run --all-files
uv pip install -e .
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file rawformer-0.2.0.tar.gz.
File metadata
- Download URL: rawformer-0.2.0.tar.gz
- Upload date:
- Size: 7.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.9.30 {"installer":{"name":"uv","version":"0.9.30","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"NixOS","version":"25.11","id":"xantusia","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b504c7f9d55a256cadcbfe7a3930bcb4c7435d1f10a132206c394ac7f882a9a2
|
|
| MD5 |
b69b21c538a2b4fea8813cfdbbb6f999
|
|
| BLAKE2b-256 |
27a013c62639068e2dd371b641a7541e65956d4233bba3007288bd24e27a61d9
|
File details
Details for the file rawformer-0.2.0-py3-none-any.whl.
File metadata
- Download URL: rawformer-0.2.0-py3-none-any.whl
- Upload date:
- Size: 10.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.9.30 {"installer":{"name":"uv","version":"0.9.30","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"NixOS","version":"25.11","id":"xantusia","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d135d9ba167863297c65d92c80d5725aebfffe1fe6def3fe4116ab51ba314246
|
|
| MD5 |
f5fd481016ac5640a849677dba9cf900
|
|
| BLAKE2b-256 |
cf2e7f83633f40ca521fd8e0af9787a38e77eef3245ef9160071371bfd064bcb
|
