v0.10.1rc1

2025-09-09 09:40:35 +08:00
parent d6f6ef41fe
commit 9149384e03
432 changed files with 84698 additions and 1 deletions
--- a/tests/e2e/models/configs/Qwen3-8B-Base.yaml
+++ b/tests/e2e/models/configs/Qwen3-8B-Base.yaml
@@ -0,0 +1,13 @@
+model_name: "Qwen/Qwen3-8B-Base"
+tasks:
+- name: "gsm8k"
+  metrics:
+  - name: "exact_match,strict-match"
+    value: 0.82
+  - name: "exact_match,flexible-extract"
+    value: 0.83
+- name: "ceval-valid"
+  metrics:
+  - name: "acc,none"
+    value: 0.82
+num_fewshot: 5