Update README.md (#3)

- Update README.md (528313623b85c1efe4470dd55ea55956e6380112)


Co-authored-by: Hailey LIM <[email protected]>

README.md

@@ -72,8 +72,7 @@ print(decoded)
 
 ## Training Dataset
 
-The model was trained on approximately 100k high-quality Korean instruction examples. The dataset was curated to cover a wide range of Korean language contexts and tasks, with a focus on aligning model outputs with user intent and natural language generation, and is currently undisclosed.
-
+The model was trained on high-quality Korean instructional data. The dataset was curated to cover a broad range of Korean language contexts and task types, with a focus on aligning model outputs with user intent and natural language generation. It is currently not publicly available.
 
 ## Evaluation
 
@@ -97,7 +96,7 @@ The table below contains a description of the Korean LLM evaluation benchmark da
 
 |         | **davidkim205<br>Hunminai<br>-1.0-27b** | google<br>gemma-3<br>-27b-it | unsloth<br>gemma-3<br>-27b-it | google<br>gemma-2<br>-27b-it |
 |---------|----------------------------------------:|-----------------------------:|------------------------------:|-----------------------------:|
-| Avg.    |                                **8.53** |                         8.31 |                          8.03 |                         7.49 |
+| Avg.    |                                **8.51** |                         8.32 |                          8.03 |                         7.49 |
 | bench   |                                    8.26 |                         8.06 |                      **8.27** |                         7.59 |
 | ged     |                                **9.19** |                         9.02 |                          9.03 |                         8.38 |
 | ged:E   |                                    9.86 |                         9.86 |                      **9.93** |                         9.51 |
@@ -105,5 +104,5 @@ The table below contains a description of the Korean LLM evaluation benchmark da
 | ged:H   |                                **9.60** |                         9.52 |                          9.52 |                         9.32 |
 | gpqa    |                                **4.55** |                         3.69 |                          3.38 |                         3.54 |
 | math500 |                                **8.56** |                         8.38 |                          6.26 |                         5.00 |
-| ifeval  |                                         |                              |                      **8.10** |                              |
+| ifeval  |                                **8.41** |                         8.37 |                          8.10 |                              |