Update README.md
Browse files
README.md
CHANGED
|
@@ -26,7 +26,8 @@ This model is a merged version of two Qwen base models:
|
|
| 26 |
- **Evoluation dataset**: `openai/gsm8k` (subset of 100 samples, not trained)
|
| 27 |
- **Generation runs**: 50
|
| 28 |
- **Population size**: 10
|
| 29 |
-
- This model design for instruct model not reasoning model
|
|
|
|
| 30 |
|
| 31 |
## Evaluation
|
| 32 |
|
|
|
|
| 26 |
- **Evoluation dataset**: `openai/gsm8k` (subset of 100 samples, not trained)
|
| 27 |
- **Generation runs**: 50
|
| 28 |
- **Population size**: 10
|
| 29 |
+
- This model design for instruct model not reasoning model with same function like Qwen3-Instruct-2507
|
| 30 |
+
- **A good start for SFT or GRPO training.**
|
| 31 |
|
| 32 |
## Evaluation
|
| 33 |
|