Update README.md
Browse files
README.md
CHANGED
@@ -87,7 +87,7 @@ tokenizer.decode(summary_ids[0], skip_special_tokens=True, clean_up_tokenization
|
|
87 |
```
|
88 |
#### Hardware
|
89 |
|
90 |
-
The model was trained continuously on a single A10G GPU in an AWS instance for 133 hours with each epoch taking 45 hours.
|
91 |
|
92 |
#### Authors:
|
93 |
|
|
|
87 |
```
|
88 |
#### Hardware
|
89 |
|
90 |
+
The model was trained continuously on a single A10G GPU in an AWS instance for 133 hours with each epoch taking 45 hours using bf16 quantization.
|
91 |
|
92 |
#### Authors:
|
93 |
|