Instructions to use peach-lab/privacy-comparator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use peach-lab/privacy-comparator with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct") model = PeftModel.from_pretrained(base_model, "peach-lab/privacy-comparator") - Notebooks
- Google Colab
- Kaggle
Gigi commited on
Commit ·
60710c8
1
Parent(s): faedd41
Fix base_model_name_or_path format and README SAME meaning
Browse files- README.md +3 -3
- adapter_config.json +1 -1
README.md
CHANGED
|
@@ -26,9 +26,9 @@ B: message
|
|
| 26 |
the model outputs:
|
| 27 |
|
| 28 |
```
|
| 29 |
-
A
|
| 30 |
-
B
|
| 31 |
-
SAME
|
| 32 |
```
|
| 33 |
|
| 34 |
The model performs **relative privacy comparison** and can be applied to arbitrary message pairs, regardless of how they were generated.
|
|
|
|
| 26 |
the model outputs:
|
| 27 |
|
| 28 |
```
|
| 29 |
+
A message A is more privacy-preserving
|
| 30 |
+
B message B is more privacy-preserving
|
| 31 |
+
SAME messages offer the same level of privacy protection
|
| 32 |
```
|
| 33 |
|
| 34 |
The model performs **relative privacy comparison** and can be applied to arbitrary message pairs, regardless of how they were generated.
|
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path":
|
| 5 |
"bias": "none",
|
| 6 |
"corda_config": null,
|
| 7 |
"eva_config": null,
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
| 5 |
"bias": "none",
|
| 6 |
"corda_config": null,
|
| 7 |
"eva_config": null,
|