Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,8 @@ This llama model was trained 2x faster with Unsloth and Huggingface's TRL librar
|
|
| 21 |
|
| 22 |
Here I fine-tuned Llama3_8B to perform the matching task in my Scholara Virtual assistant. It matches the given student information with the provided scholarships list (which comes from my Vector DB and my AI Web agent), and then shows the student the most suitable scholarships based on their information and desires.
|
| 23 |
|
|
|
|
|
|
|
| 24 |
## Example Usage
|
| 25 |
|
| 26 |
The following example demonstrates how to use the model. It requires at least 1xL4 GPU to make the inference.
|
|
|
|
| 21 |
|
| 22 |
Here I fine-tuned Llama3_8B to perform the matching task in my Scholara Virtual assistant. It matches the given student information with the provided scholarships list (which comes from my Vector DB and my AI Web agent), and then shows the student the most suitable scholarships based on their information and desires.
|
| 23 |
|
| 24 |
+
|
| 25 |
+
- context window is 4k
|
| 26 |
## Example Usage
|
| 27 |
|
| 28 |
The following example demonstrates how to use the model. It requires at least 1xL4 GPU to make the inference.
|