Now compatible with 5.0.0
Browse files
README.md
CHANGED
|
@@ -14,8 +14,6 @@ This model is gpjt/8xa100m40, a trained-from-scratch base model using
|
|
| 14 |
the GPT-2-style architecture from [Sebastian Raschka](https://sebastianraschka.com/)'s book
|
| 15 |
"[Build a Large Language Model (from Scratch)](https://www.manning.com/books/build-a-large-language-model-from-scratch)".
|
| 16 |
|
| 17 |
-
**Note**: this model is not compatible with `transformers` version 5.0.0, please use 4.9.x.
|
| 18 |
-
|
| 19 |
|
| 20 |
## Model Details
|
| 21 |
|
|
|
|
| 14 |
the GPT-2-style architecture from [Sebastian Raschka](https://sebastianraschka.com/)'s book
|
| 15 |
"[Build a Large Language Model (from Scratch)](https://www.manning.com/books/build-a-large-language-model-from-scratch)".
|
| 16 |
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model Details
|
| 19 |
|