初始化项目，由ModelHub XC社区提供模型

Model: seopbo/zerorlvrcode-qwen2.5-1.5b
Source: Original Platform

eval-results/gsm8k/metrics.json

@@ -0,0 +1,11 @@
+{
+  "gsm8k": {
+    "pass@1": {
+      "num_entries": 1319,
+      "avg_tokens": 1586,
+      "gen_seconds": 105,
+      "symbolic_correct": 0.1516300227445034,
+      "no_answer": 5.231235784685368
+    }
+  }
+}

eval-results/hendrycks_math/metrics.json

@@ -0,0 +1,11 @@
+{
+  "hendrycks_math": {
+    "pass@1": {
+      "num_entries": 5000,
+      "avg_tokens": 1118,
+      "gen_seconds": 192,
+      "symbolic_correct": 2.58,
+      "no_answer": 12.28
+    }
+  }
+}

eval-results/human-eval/metrics.json

@@ -0,0 +1,11 @@
+{
+  "human-eval": {
+    "pass@1": {
+      "num_entries": 164,
+      "avg_tokens": 427,
+      "gen_seconds": 34,
+      "passing_base_tests": 28.658536585365855,
+      "passing_plus_tests": 26.21951219512195
+    }
+  }
+}

eval-results/ifbench/metrics.json

@@ -0,0 +1,16 @@
+{
+  "ifbench": {
+    "pass@1": {
+      "num_prompts": 294,
+      "num_instructions": 335,
+      "average_score": 20.91912884556808,
+      "prompt_strict_accuracy": 18.70748299319728,
+      "instruction_strict_accuracy": 20.8955223880597,
+      "prompt_loose_accuracy": 21.08843537414966,
+      "instruction_loose_accuracy": 22.98507462686567,
+      "num_entries": 294,
+      "avg_tokens": 1612,
+      "gen_seconds": 37
+    }
+  }
+}

eval-results/ifeval/metrics.json

@@ -0,0 +1,16 @@
+{
+  "ifeval": {
+    "pass@1": {
+      "num_prompts": 541,
+      "num_instructions": 834,
+      "average_score": 27.84218096871855,
+      "prompt_strict_accuracy": 20.51756007393715,
+      "instruction_strict_accuracy": 32.49400479616307,
+      "prompt_loose_accuracy": 23.10536044362292,
+      "instruction_loose_accuracy": 35.25179856115108,
+      "num_entries": 541,
+      "avg_tokens": 1555,
+      "gen_seconds": 77
+    }
+  }
+}

eval-results/mbpp/metrics.json

@@ -0,0 +1,11 @@
+{
+  "mbpp": {
+    "pass@1": {
+      "num_entries": 378,
+      "avg_tokens": 150,
+      "gen_seconds": 35,
+      "passing_base_tests": 59.78835978835979,
+      "passing_plus_tests": 52.116402116402114
+    }
+  }
+}

eval-results/minerva_math/metrics.json

@@ -0,0 +1,11 @@
+{
+  "minerva_math": {
+    "pass@1": {
+      "num_entries": 272,
+      "avg_tokens": 1813,
+      "gen_seconds": 64,
+      "symbolic_correct": 0.0,
+      "no_answer": 10.661764705882353
+    }
+  }
+}