Commit
•
7dce2a2
1
Parent(s):
4dedaba
Update README.md
Browse files
README.md
CHANGED
|
@@ -41,7 +41,7 @@ The model was fine-tuned on a synthetic dataset derived from GPT-4 (for user que
|
|
| 41 |
|
| 42 |
### Performance Metrics
|
| 43 |
- **Training Loss:** Final loss of 1.3721 after 3 epochs
|
| 44 |
-
- **Real-world Use** Seems to struggle with maintaining conversational context.
|
| 45 |
|
| 46 |
### Limitations and Current Shortcomings
|
| 47 |
- The model's knowledge is limited to its training data and cut-off date.
|
|
|
|
| 41 |
|
| 42 |
### Performance Metrics
|
| 43 |
- **Training Loss:** Final loss of 1.3721 after 3 epochs
|
| 44 |
+
- **Real-world Use** Seems to struggle with maintaining conversational context on CUDA? CPU produces much more coherent results compared to CUDA.
|
| 45 |
|
| 46 |
### Limitations and Current Shortcomings
|
| 47 |
- The model's knowledge is limited to its training data and cut-off date.
|