Commit
•
e7a5731
1
Parent(s):
5887ec5
Update README.md
Browse files
README.md
CHANGED
|
@@ -53,6 +53,7 @@ This model is fine-tuned from the meta-llama/Llama-3.2-1B base model to enhance
|
|
| 53 |
---
|
| 54 |
# Model Performace Evaluation:
|
| 55 |
- Evaluation on 1000 Questions based on dataset (to evaluate the finetuned knowledge base)
|
|
|
|
| 56 |
- Correct Responses: 82.23%%
|
| 57 |
- Incorrect Responses: 17.77%
|
| 58 |
|
|
|
|
| 53 |
---
|
| 54 |
# Model Performace Evaluation:
|
| 55 |
- Evaluation on 1000 Questions based on dataset (to evaluate the finetuned knowledge base)
|
| 56 |
+
- At temperature 0.2
|
| 57 |
- Correct Responses: 82.23%%
|
| 58 |
- Incorrect Responses: 17.77%
|
| 59 |
|