Update README.md
Browse files
README.md
CHANGED
|
@@ -45,10 +45,6 @@ Quantization and FP16 Conversion
|
|
| 45 |
|
| 46 |
To improve inference efficiency, models were converted to FP16:
|
| 47 |
|
| 48 |
-
import torch
|
| 49 |
-
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
|
| 50 |
-
|
| 51 |
-
|
| 52 |
|
| 53 |
# Inference Example
|
| 54 |
```
|
|
|
|
| 45 |
|
| 46 |
To improve inference efficiency, models were converted to FP16:
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
|
| 49 |
# Inference Example
|
| 50 |
```
|