Update README with license attribution
Browse files
README.md
CHANGED
|
@@ -7,7 +7,7 @@ license: mit
|
|
| 7 |
|
| 8 |
# crate-d12-base
|
| 9 |
|
| 10 |
-
A CRATE (Coding
|
| 11 |
trained with [nanochat](https://github.com/karpathy/nanochat).
|
| 12 |
|
| 13 |
## Model Details
|
|
@@ -43,3 +43,12 @@ from nanochat.checkpoint_manager import build_model
|
|
| 43 |
|
| 44 |
model, tokenizer, meta = build_model("path/to/downloaded/dir", step=20000, device=torch.device("cuda"), phase="eval")
|
| 45 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
|
| 8 |
# crate-d12-base
|
| 9 |
|
| 10 |
+
A CRATE (Coding RAte reduction TransformEr) language model
|
| 11 |
trained with [nanochat](https://github.com/karpathy/nanochat).
|
| 12 |
|
| 13 |
## Model Details
|
|
|
|
| 43 |
|
| 44 |
model, tokenizer, meta = build_model("path/to/downloaded/dir", step=20000, device=torch.device("cuda"), phase="eval")
|
| 45 |
```
|
| 46 |
+
|
| 47 |
+
## License
|
| 48 |
+
|
| 49 |
+
This model is released under the **MIT License**.
|
| 50 |
+
|
| 51 |
+
Built on:
|
| 52 |
+
- [nanochat](https://github.com/karpathy/nanochat) by Andrej Karpathy -- MIT License, Copyright (c) 2025
|
| 53 |
+
- [CRATE](https://github.com/Ma-Lab-Berkeley/CRATE) (White-Box Transformers via Sparse Rate Reduction) by Ma-Lab-Berkeley -- MIT License, Copyright (c) 2023
|
| 54 |
+
- [CRATE-alpha](https://github.com/UCSC-VLAA/CRATE-alpha) (Scaling White-Box Transformers for Vision) by UCSC-VLAA
|