Update README.md
Browse files
README.md
CHANGED
|
@@ -21,4 +21,12 @@ This model is a merged version of two Qwen base models:
|
|
| 21 |
## Notations:
|
| 22 |
- **Evoluation dataset**: `openai/gsm8k` (subset of 100 samples, not trained)
|
| 23 |
- **Generation runs**: 50
|
| 24 |
-
- **Population size**: 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
## Notations:
|
| 22 |
- **Evoluation dataset**: `openai/gsm8k` (subset of 100 samples, not trained)
|
| 23 |
- **Generation runs**: 50
|
| 24 |
+
- **Population size**: 10
|
| 25 |
+
|
| 26 |
+
## Evaluation
|
| 27 |
+
|
| 28 |
+
For my evaluation in agent task is not surpass too much but only 2% with instruct model.
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|