Update README.md
Browse files
README.md
CHANGED
|
@@ -49,3 +49,15 @@ This model is fine-tuned from the meta-llama/Meta-Llama-3.1-8B base model to enh
|
|
| 49 |
- Token Limitations: With a max token limit of 512, the model might not handle very long queries or contexts effectively.
|
| 50 |
- Training Data Limitations: The model’s performance is contingent on the quality and coverage of the fine-tuning dataset, which may affect its generalizability to different contexts or medications not covered in the dataset.
|
| 51 |
- Potential Biases: As with any model fine-tuned on specific data, there may be biases based on the dataset used for training.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
- Token Limitations: With a max token limit of 512, the model might not handle very long queries or contexts effectively.
|
| 50 |
- Training Data Limitations: The model’s performance is contingent on the quality and coverage of the fine-tuning dataset, which may affect its generalizability to different contexts or medications not covered in the dataset.
|
| 51 |
- Potential Biases: As with any model fine-tuned on specific data, there may be biases based on the dataset used for training.
|
| 52 |
+
|
| 53 |
+
---
|
| 54 |
+
# Model Performace Evaluation:
|
| 55 |
+
- Evaluation on 1000 Questions based on dataset (to evaluate the finetuned knowledge base)
|
| 56 |
+
- Correct Responses: %
|
| 57 |
+
- Incorrect Responses: %
|
| 58 |
+
|
| 59 |
+
<p align="center">
|
| 60 |
+
<img src="" width="20%" style="display:inline-block;"/>
|
| 61 |
+
<img src="" width="35%" style="display:inline-block;"/>
|
| 62 |
+
<img src="" width="35%" style="display:inline-block;"/>
|
| 63 |
+
</p>
|