Simplify model card usage notes
Browse files
README.md
CHANGED
|
@@ -71,10 +71,6 @@ These scores show clear progress over the project’s earlier checkpoints, but t
|
|
| 71 |
|
| 72 |
This repository is a native safetensors export rather than a Transformers `AutoModel` package. It includes the minimal `tiny_english` inference module.
|
| 73 |
|
| 74 |
-
## Weights
|
| 75 |
-
|
| 76 |
-
`model.safetensors` contains the single BF16 release (624 MB; SHA-256 `fce44c1f7fc64a51a775d8802cfa75277dc68a34ef5d2908f541caa21fad66c2`). It requires a BF16-capable CUDA GPU, such as the RTX 3060 Ti used for training. The bundled inference command defaults to CUDA.
|
| 77 |
-
|
| 78 |
```bash
|
| 79 |
pip install -r requirements.txt
|
| 80 |
python -m tiny_english.generate --model-dir . --device cuda --prompt "The invention of the printing press changed" --max-new-tokens 128 --temperature 0.7 --top-k 40 --seed 42
|
|
|
|
| 71 |
|
| 72 |
This repository is a native safetensors export rather than a Transformers `AutoModel` package. It includes the minimal `tiny_english` inference module.
|
| 73 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
```bash
|
| 75 |
pip install -r requirements.txt
|
| 76 |
python -m tiny_english.generate --model-dir . --device cuda --prompt "The invention of the printing press changed" --max-new-tokens 128 --temperature 0.7 --top-k 40 --seed 42
|