初始化项目，由ModelHub XC社区提供模型

Model: SeongryongJung/qwen2.5-0.5b-ifeval-mixed-kd-alpha05
Source: Original Platform

README.md

@@ -0,0 +1,26 @@
+---
+language:
+- en
+library_name: transformers
+tags:
+- qwen
+- distillation
+- ifeval
+- retaining-by-doing
+---
+
+# Qwen2.5-0.5B Instruct IFEval Mixed KD (alpha=0.5)
+
+This checkpoint was distilled from a half-epoch `Qwen2.5-1.5B-Instruct` teacher trained on `IFEvalSFTDataset`.
+
+Distillation setup:
+- student: `Qwen2.5-0.5B-Instruct`
+- teacher: half-epoch `Qwen2.5-1.5B-Instruct`
+- `num_train_datapoints=4064`
+- `num_epochs=1`
+- `distill_alpha=0.5`
+- `distill_temperature=2.0`
+- effective loss mix: `CE 0.5 / KD 0.5`
+
+Observed local IFEval accuracy:
+- `0.4137577002`