Update README.md
Browse files
README.md
CHANGED
|
@@ -70,6 +70,9 @@ We trained models using datasets of different sizes (200,000, 600,000, and 1,000
|
|
| 70 |
|
| 71 |
## Use model
|
| 72 |
BELLE can be easily loaded with AutoModelForCausalLM.
|
|
|
|
|
|
|
|
|
|
| 73 |
``` python
|
| 74 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 75 |
import sys
|
|
|
|
| 70 |
|
| 71 |
## Use model
|
| 72 |
BELLE can be easily loaded with AutoModelForCausalLM.
|
| 73 |
+
|
| 74 |
+
Please note that the input should be formatted as `Human: {input} \n\nAssistant:` in both training and inference.
|
| 75 |
+
|
| 76 |
``` python
|
| 77 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 78 |
import sys
|