Update README.md
Browse files
README.md
CHANGED
|
@@ -133,7 +133,7 @@ This allows the model to encode information about these concepts in their indivi
|
|
| 133 |
|
| 134 |
## Model Architecture and Objective
|
| 135 |
|
| 136 |
-
|
| 137 |
|
| 138 |
| | |
|
| 139 |
| ----------- | ----- |
|
|
|
|
| 133 |
|
| 134 |
## Model Architecture and Objective
|
| 135 |
|
| 136 |
+
BioMedLM 2.7B is a standard GPT-2 implementation (trained with Flash Attention) with the following hyperparameters:
|
| 137 |
|
| 138 |
| | |
|
| 139 |
| ----------- | ----- |
|