初始化项目，由ModelHub XC社区提供模型

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

eval-results/gsm8k/metrics.json

@@ -0,0 +1,11 @@
+{
+  "gsm8k": {
+    "pass@1": {
+      "num_entries": 1319,
+      "avg_tokens": 57,
+      "gen_seconds": 49,
+      "symbolic_correct": 9.476876421531463,
+      "no_answer": 4.321455648218347
+    }
+  }
+}

eval-results/hendrycks_math/metrics.json

@@ -0,0 +1,11 @@
+{
+  "hendrycks_math": {
+    "pass@1": {
+      "num_entries": 5000,
+      "avg_tokens": 454,
+      "gen_seconds": 136,
+      "symbolic_correct": 11.86,
+      "no_answer": 18.66
+    }
+  }
+}

eval-results/human-eval/metrics.json

@@ -0,0 +1,11 @@
+{
+  "human-eval": {
+    "pass@1": {
+      "num_entries": 164,
+      "avg_tokens": 904,
+      "gen_seconds": 35,
+      "passing_base_tests": 11.585365853658537,
+      "passing_plus_tests": 10.365853658536585
+    }
+  }
+}

eval-results/ifbench/metrics.json

@@ -0,0 +1,16 @@
+{
+  "ifbench": {
+    "pass@1": {
+      "num_prompts": 294,
+      "num_instructions": 335,
+      "average_score": 24.357041323992284,
+      "prompt_strict_accuracy": 22.108843537414966,
+      "instruction_strict_accuracy": 23.582089552238806,
+      "prompt_loose_accuracy": 25.170068027210885,
+      "instruction_loose_accuracy": 26.56716417910448,
+      "num_entries": 294,
+      "avg_tokens": 1242,
+      "gen_seconds": 36
+    }
+  }
+}

eval-results/ifeval/metrics.json

@@ -0,0 +1,16 @@
+{
+  "ifeval": {
+    "pass@1": {
+      "num_prompts": 541,
+      "num_instructions": 834,
+      "average_score": 41.75820157182941,
+      "prompt_strict_accuracy": 34.56561922365989,
+      "instruction_strict_accuracy": 47.00239808153477,
+      "prompt_loose_accuracy": 36.78373382624769,
+      "instruction_loose_accuracy": 48.6810551558753,
+      "num_entries": 541,
+      "avg_tokens": 883,
+      "gen_seconds": 41
+    }
+  }
+}

eval-results/mbpp/metrics.json

@@ -0,0 +1,11 @@
+{
+  "mbpp": {
+    "pass@1": {
+      "num_entries": 378,
+      "avg_tokens": 781,
+      "gen_seconds": 36,
+      "passing_base_tests": 12.433862433862434,
+      "passing_plus_tests": 10.846560846560847
+    }
+  }
+}

eval-results/minerva_math/metrics.json

@@ -0,0 +1,11 @@
+{
+  "minerva_math": {
+    "pass@1": {
+      "num_entries": 272,
+      "avg_tokens": 884,
+      "gen_seconds": 37,
+      "symbolic_correct": 3.676470588235294,
+      "no_answer": 16.176470588235293
+    }
+  }
+}