Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,8 @@ license: apache-2.0
|
|
| 15 |
|
| 16 |
This model `gpt-oss-120b-hallu-miti` is a LoRA adapter based on `gpt-oss-120b` that mitigates hallucinations by fine-tuning with a single data point.
|
| 17 |
|
|
|
|
|
|
|
| 18 |
This model is designed solely to demonstrate fine-tuning techniques with a small amount of data. You should not use this model for production purposes.
|
| 19 |
|
| 20 |
## Evaluation
|
|
|
|
| 15 |
|
| 16 |
This model `gpt-oss-120b-hallu-miti` is a LoRA adapter based on `gpt-oss-120b` that mitigates hallucinations by fine-tuning with a single data point.
|
| 17 |
|
| 18 |
+
This is NOT SFT or RL. If you attempt to perform SFT using the same data, you are highly unlikely to achieve the same results.
|
| 19 |
+
|
| 20 |
This model is designed solely to demonstrate fine-tuning techniques with a small amount of data. You should not use this model for production purposes.
|
| 21 |
|
| 22 |
## Evaluation
|