|
Download README.md from umasschemistry/quick-embedding: direct link, hf CLI and curl.
- Browser
- Download file 694 Bytes
-
https://huggingface.co/umasschemistry/quick-embedding/resolve/main/README.md
- Command line
-
hf download hf://umasschemistry/quick-embedding/README.md
-
curl -L -o README.md https://huggingface.co/umasschemistry/quick-embedding/resolve/main/README.md
694 Bytes
| license: mit | |
| tags: | |
| - co-attention | |
| - flash | |
| - lamb | |
| - matching | |
| - mish | |
| - onecycle | |
| - rmsnorm | |
| - swin-t | |
| - xavier | |
| - xlarge | |
| # train.py | |
| ## Model Overview | |
| A **xlarge**-scale implementation of the **swin t** architecture, built for **matching** tasks. | |
| ## Architecture | |
| - **Architecture**: swin t | |
| - **Scale**: xlarge | |
| - **Attention**: flash | |
| - **Fusion strategy**: co attention | |
| - **Task head**: matching | |
| - **Activation**: mish | |
| - **Normalization**: rmsnorm | |
| - **Initialization**: xavier | |
| ## Training | |
| - **Optimizer**: lamb | |
| - **LR scheduler**: onecycle | |
| ## Files | |
| - `train.py` — main artifact of this repository | |
| ## License | |
| See the license field above. | |