初始化项目，由ModelHub XC社区提供模型

Model: North-ML1/willow-alpha-base Source: Original Platform
2026-06-10 16:46:17 +08:00
commit 24ece0645e
9 changed files with 81672 additions and 0 deletions
--- a/eval_results.json
+++ b/eval_results.json
@@ -0,0 +1,164 @@
+[
+  {
+    "task": "hellaswag",
+    "benchmark": "HellaSwag",
+    "metric": "acc_norm",
+    "score": 0.26707827126070505,
+    "shots": 0,
+    "runtime_sec": 318.67,
+    "status": "success"
+  },
+  {
+    "task": "piqa",
+    "benchmark": "PIQA",
+    "metric": "acc_norm",
+    "score": 0.5386289445048966,
+    "shots": 0,
+    "runtime_sec": 38.85,
+    "status": "success"
+  },
+  {
+    "task": "winogrande",
+    "benchmark": "WinoGrande",
+    "metric": "acc",
+    "score": 0.5067087608524072,
+    "shots": 0,
+    "runtime_sec": 23.73,
+    "status": "success"
+  },
+  {
+    "task": "boolq",
+    "benchmark": "BoolQ",
+    "metric": "acc",
+    "score": 0.40214067278287463,
+    "shots": 0,
+    "runtime_sec": 144.8,
+    "status": "success"
+  },
+  {
+    "task": "arc_easy",
+    "benchmark": "ARC-Easy",
+    "metric": "acc_norm",
+    "score": 0.3468013468013468,
+    "shots": 0,
+    "runtime_sec": 51.41,
+    "status": "success"
+  },
+  {
+    "task": "arc_challenge",
+    "benchmark": "ARC-Challenge",
+    "metric": "acc_norm",
+    "score": 0.25597269624573377,
+    "shots": 0,
+    "runtime_sec": 37.69,
+    "status": "success"
+  },
+  {
+    "task": "openbookqa",
+    "benchmark": "OpenBookQA",
+    "metric": "acc_norm",
+    "score": 0.25,
+    "shots": 0,
+    "runtime_sec": 21.14,
+    "status": "success"
+  },
+  {
+    "task": "commonsense_qa",
+    "benchmark": "CommonsenseQA",
+    "metric": "acc",
+    "score": 0.2031122031122031,
+    "shots": 0,
+    "runtime_sec": 27.66,
+    "status": "success"
+  },
+  {
+    "task": "lambada_openai",
+    "benchmark": "LAMBADA",
+    "metric": "acc",
+    "score": 0.0023287405394915583,
+    "shots": 0,
+    "runtime_sec": 96.28,
+    "status": "success"
+  },
+  {
+    "task": "blimp",
+    "benchmark": "BLiMP",
+    "metric": "acc",
+    "score": 0.5923432835820895,
+    "shots": 0,
+    "runtime_sec": 354.79,
+    "status": "success"
+  },
+  {
+    "task": "mmlu",
+    "benchmark": "MMLU",
+    "metric": "acc",
+    "score": 0.23892607890613873,
+    "shots": 0,
+    "runtime_sec": 388.62,
+    "status": "success"
+  },
+  {
+    "task": "wikitext",
+    "benchmark": "WikiText-2",
+    "metric": "word_perplexity",
+    "score": 12524.42105099034,
+    "shots": 0,
+    "runtime_sec": 182.89,
+    "status": "success"
+  },
+  {
+    "task": "wikitext",
+    "benchmark": "WikiText-2",
+    "metric": "byte_perplexity",
+    "score": 5.838498405241562,
+    "shots": 0,
+    "runtime_sec": 181.42,
+    "status": "success"
+  },
+  {
+    "task": "sciq",
+    "benchmark": "SciQ",
+    "metric": "acc_norm",
+    "score": 0.356,
+    "shots": 0,
+    "runtime_sec": 87.15,
+    "status": "success"
+  },
+  {
+    "task": "copa",
+    "benchmark": "COPA",
+    "metric": "acc",
+    "score": 0.64,
+    "shots": 0,
+    "runtime_sec": 17.21,
+    "status": "success"
+  },
+  {
+    "task": "race",
+    "benchmark": "RACE",
+    "metric": "acc",
+    "score": 0.23157894736842105,
+    "shots": 0,
+    "runtime_sec": 334.7,
+    "status": "success"
+  },
+  {
+    "task": "swag",
+    "benchmark": "SWAG",
+    "metric": "acc_norm",
+    "score": 0.2912626212136359,
+    "shots": 0,
+    "runtime_sec": 252.0,
+    "status": "success"
+  },
+  {
+    "task": "truthfulqa_mc2",
+    "benchmark": "TruthfulQA MC2",
+    "metric": "acc",
+    "score": 0.48740972804833826,
+    "shots": 0,
+    "runtime_sec": 126.29,
+    "status": "success"
+  }
+]