Update hallucination_detection_lora/README.md
Browse files
hallucination_detection_lora/README.md
CHANGED
|
@@ -96,7 +96,7 @@ As explained above, it is highly recommended to use the LoRA adapter through [gr
|
|
| 96 |
|
| 97 |
|
| 98 |
|
| 99 |
-
However, if you prefer to invoke the LoRA adapter directly, you can use the following code.
|
| 100 |
|
| 101 |
```
|
| 102 |
import torch
|
|
@@ -106,7 +106,7 @@ from nltk import tokenize
|
|
| 106 |
import json
|
| 107 |
|
| 108 |
BASE_NAME = "ibm-granite/granite-3.3-8b-instruct"
|
| 109 |
-
LORA_NAME = "
|
| 110 |
|
| 111 |
def get_device():
|
| 112 |
"""
|
|
|
|
| 96 |
|
| 97 |
|
| 98 |
|
| 99 |
+
However, if you prefer to invoke the LoRA adapter directly, you can use the following code. Before running the script, set the `LORA_NAME` parameter to the path of the directory that you downloaded the LoRA adapter. The download process is explained [here](https://huggingface.co/ibm-granite/granite-3.3-8b-rag-agent-lib#quickstart-example).
|
| 100 |
|
| 101 |
```
|
| 102 |
import torch
|
|
|
|
| 106 |
import json
|
| 107 |
|
| 108 |
BASE_NAME = "ibm-granite/granite-3.3-8b-instruct"
|
| 109 |
+
LORA_NAME = "PATH_TO_DOWNLOADED_DIRECTORY"
|
| 110 |
|
| 111 |
def get_device():
|
| 112 |
"""
|