add resutls

.gitignore

@@ -6,8 +6,4 @@ __pycache__/
 *ipynb
 .vscode/
 
-eval-queue/
-eval-results/
-eval-queue-bk/
-eval-results-bk/
 logs/

eval-queue/CoT/Qwen2.5-7b-Instruct_eval_request_False_float16_Original.json

@@ -0,0 +1,12 @@
+{
+    "model": "CoT/Qwen2.5-7b-Instruct",
+    "revision": "main",
+    "precision": "float16",
+    "weight_type": "Original",
+    "status": "FINISHED",
+    "submitted_time": "2025-09-29T06:00:00.000Z",
+    "model_type": "pretrained",
+    "likes": 8,
+    "params": 7.0,
+    "license": "apache-2.0"
+}

eval-queue/Direct-Inference/Qwen2.5-7b-Instruct_eval_request_False_float16_Original.json

@@ -0,0 +1,12 @@
+{
+    "model": "Direct-Inference/Qwen2.5-7b-Instruct",
+    "revision": "main",
+    "precision": "float16",
+    "weight_type": "Original",
+    "status": "FINISHED",
+    "submitted_time": "2025-09-29T08:00:00.000Z",
+    "model_type": "pretrained",
+    "likes": 12,
+    "params": 7.0,
+    "license": "apache-2.0"
+}

eval-queue/PeterJinGo/Qwen2.5-7b-Instruct_eval_request_False_float16_Original.json

@@ -0,0 +1,13 @@
+{
+    "model": "PeterJinGo/Qwen2.5-7b-Instruct",
+    "revision": "main",
+    "precision": "float16",
+    "weight_type": "Original",
+    "status": "FINISHED",
+    "submitted_time": "2025-09-29T09:00:00.000Z",
+    "model_type": "fine-tuned",
+    "likes": 72,
+    "params": 7.0,
+    "license": "apache-2.0"
+}
+

eval-queue/R1/Qwen2.5-7b-Instruct_eval_request_False_float16_Original.json

@@ -0,0 +1,12 @@
+{
+    "model": "R1/Qwen2.5-7b-Instruct",
+    "revision": "main",
+    "precision": "float16",
+    "weight_type": "Original",
+    "status": "FINISHED",
+    "submitted_time": "2025-09-29T07:00:00.000Z",
+    "model_type": "RL-tuned",
+    "likes": 67,
+    "params": 7.0,
+    "license": "apache-2.0"
+}

eval-queue/RAG/Qwen2.5-7b-Instruct_eval_request_False_float16_Original.json

@@ -0,0 +1,12 @@
+{
+    "model": "RAG/Qwen2.5-7b-Instruct",
+    "revision": "main",
+    "precision": "float16",
+    "weight_type": "Original",
+    "status": "FINISHED",
+    "submitted_time": "2025-09-29T08:30:00.000Z",
+    "model_type": "fine-tuned",
+    "likes": 45,
+    "params": 7.0,
+    "license": "apache-2.0"
+}

eval-queue/ReSeek/Qwen2.5-3b-Instruct_eval_request_False_float16_Original.json

@@ -0,0 +1,12 @@
+{
+    "model": "ReSeek-Qwen2.5-3b-Instruct",
+    "revision": "main",
+    "precision": "float16",
+    "weight_type": "Original",
+    "status": "FINISHED",
+    "submitted_time": "2025-09-29T10:15:00.000Z",
+    "model_type": "fine-tuned",
+    "likes": 156,
+    "params": 3.0,
+    "license": "apache-2.0"
+}

eval-queue/ReSeek/Qwen2.5-7b-Instruct_eval_request_False_float16_Original.json

@@ -0,0 +1,12 @@
+{
+    "model": "ReSeek/Qwen2.5-7b-Instruct",
+    "revision": "main",
+    "precision": "float16",
+    "weight_type": "Original",
+    "status": "FINISHED",
+    "submitted_time": "2025-09-29T10:00:00.000Z",
+    "model_type": "fine-tuned",
+    "likes": 156,
+    "params": 7.0,
+    "license": "apache-2.0"
+}

eval-queue/SFT/Qwen2.5-7b-Instruct_eval_request_False_float16_Original.json

@@ -0,0 +1,12 @@
+{
+    "model": "SFT/Qwen2.5-7b-Instruct",
+    "revision": "main",
+    "precision": "float16",
+    "weight_type": "Original",
+    "status": "FINISHED",
+    "submitted_time": "2025-09-29T06:30:00.000Z",
+    "model_type": "fine-tuned",
+    "likes": 23,
+    "params": 7.0,
+    "license": "apache-2.0"
+}

eval-queue/Search-R1/Qwen2.5-3b-Instruct_eval_request_False_float16_Original.json

@@ -0,0 +1,12 @@
+{
+    "model": "Search-R1-Qwen2.5-3b-Instruct",
+    "revision": "main",
+    "precision": "float16",
+    "weight_type": "Original",
+    "status": "FINISHED",
+    "submitted_time": "2025-09-29T09:15:00.000Z",
+    "model_type": "fine-tuned",
+    "likes": 72,
+    "params": 3.0,
+    "license": "apache-2.0"
+}

eval-queue/Search-o1/Qwen2.5-7b-Instruct_eval_request_False_float16_Original.json

@@ -0,0 +1,12 @@
+{
+    "model": "Search-o1/Qwen2.5-7b-Instruct",
+    "revision": "main",
+    "precision": "float16",
+    "weight_type": "Original",
+    "status": "FINISHED",
+    "submitted_time": "2025-09-29T07:30:00.000Z",
+    "model_type": "fine-tuned",
+    "likes": 98,
+    "params": 7.0,
+    "license": "apache-2.0"
+}

eval-queue/ZeroSearch/Qwen2.5-3b-Instruct_eval_request_False_float16_Original.json

@@ -0,0 +1,12 @@
+{
+    "model": "ZeroSearch-Qwen2.5-3b-Instruct",
+    "revision": "main",
+    "precision": "float16",
+    "weight_type": "Original",
+    "status": "FINISHED",
+    "submitted_time": "2025-09-29T09:45:00.000Z",
+    "model_type": "fine-tuned",
+    "likes": 89,
+    "params": 3.0,
+    "license": "apache-2.0"
+}

eval-queue/ZeroSearch/Qwen2.5-7b-Instruct_eval_request_False_float16_Original.json

@@ -0,0 +1,12 @@
+{
+    "model": "ZeroSearch/Qwen2.5-7b-Instruct",
+    "revision": "main", 
+    "precision": "float16",
+    "weight_type": "Original",
+    "status": "FINISHED",
+    "submitted_time": "2025-09-29T09:30:00.000Z",
+    "model_type": "fine-tuned",
+    "likes": 89,
+    "params": 7.0,
+    "license": "apache-2.0"
+}

eval-queue/pending_eval_request.json

@@ -0,0 +1,12 @@
+{
+    "model": "DeepResearcher/Qwen2.5-7b-Instruct",
+    "revision": "main",
+    "precision": "float16",
+    "weight_type": "Original",
+    "status": "PENDING",
+    "submitted_time": "2025-09-29T10:00:00.000Z",
+    "model_type": "fine-tuned",
+    "likes": 42,
+    "params": 7.0,
+    "license": "apache-2.0"
+}

eval-results/CoT_Qwen2.5-7b-Instruct.json

@@ -0,0 +1,33 @@
+{
+    "config": {
+        "model_dtype": "torch.float16",
+        "model_name": "CoT-Qwen2.5-7b-Instruct",
+        "model_sha": "main"
+    },
+    "results": {
+        "nq": {
+            "exact_match": 0.048
+        },
+        "triviaqa": {
+            "exact_match": 0.185
+        },
+        "popqa": {
+            "exact_match": 0.054
+        },
+        "hotpotqa": {
+            "exact_match": 0.092
+        },
+        "2wiki": {
+            "exact_match": 0.111
+        },
+        "musique": {
+            "exact_match": 0.022
+        },
+        "bamboogle": {
+            "exact_match": 0.232
+        },
+        "fictionalhot": {
+            "exact_match": 0.001
+        }
+    }
+}

eval-results/Direct_Inference_Qwen2.5-7b-Instruct.json

@@ -0,0 +1,33 @@
+{
+    "config": {
+        "model_dtype": "torch.float16",
+        "model_name": "Direct-Inference-Qwen2.5-7b-Instruct",
+        "model_sha": "main"
+    },
+    "results": {
+        "nq": {
+            "exact_match": 0.134
+        },
+        "triviaqa": {
+            "exact_match": 0.408
+        },
+        "popqa": {
+            "exact_match": 0.140
+        },
+        "hotpotqa": {
+            "exact_match": 0.183
+        },
+        "2wiki": {
+            "exact_match": 0.250
+        },
+        "musique": {
+            "exact_match": 0.031
+        },
+        "bamboogle": {
+            "exact_match": 0.120
+        },
+        "fictionalhot": {
+            "exact_match": 0.001
+        }
+    }
+}

eval-results/R1_Qwen2.5-7b-Instruct.json

@@ -0,0 +1,33 @@
+{
+    "config": {
+        "model_dtype": "torch.float16",
+        "model_name": "R1-Qwen2.5-7b-Instruct",
+        "model_sha": "main"
+    },
+    "results": {
+        "nq": {
+            "exact_match": 0.270
+        },
+        "triviaqa": {
+            "exact_match": 0.537
+        },
+        "popqa": {
+            "exact_match": 0.199
+        },
+        "hotpotqa": {
+            "exact_match": 0.237
+        },
+        "2wiki": {
+            "exact_match": 0.292
+        },
+        "musique": {
+            "exact_match": 0.072
+        },
+        "bamboogle": {
+            "exact_match": 0.293
+        },
+        "fictionalhot": {
+            "exact_match": 0.003
+        }
+    }
+}

eval-results/RAG_Qwen2.5-7b-Instruct.json

@@ -0,0 +1,33 @@
+{
+    "config": {
+        "model_dtype": "torch.float16",
+        "model_name": "RAG-Qwen2.5-7b-Instruct",
+        "model_sha": "main"
+    },
+    "results": {
+        "nq": {
+            "exact_match": 0.349
+        },
+        "triviaqa": {
+            "exact_match": 0.585
+        },
+        "popqa": {
+            "exact_match": 0.392
+        },
+        "hotpotqa": {
+            "exact_match": 0.299
+        },
+        "2wiki": {
+            "exact_match": 0.235
+        },
+        "musique": {
+            "exact_match": 0.058
+        },
+        "bamboogle": {
+            "exact_match": 0.208
+        },
+        "fictionalhot": {
+            "exact_match": 0.012
+        }
+    }
+}

eval-results/ReSeek_Qwen2.5-3b-Instruct.json

@@ -0,0 +1,33 @@
+{
+    "config": {
+        "model_dtype": "torch.float16",
+        "model_name": "ReSeek-Qwen2.5-3b-Instruct",
+        "model_sha": "main"
+    },
+    "results": {
+        "nq": {
+            "exact_match": 0.415
+        },
+        "triviaqa": {
+            "exact_match": 0.553
+        },
+        "popqa": {
+            "exact_match": 0.434
+        },
+        "hotpotqa": {
+            "exact_match": 0.328
+        },
+        "2wiki": {
+            "exact_match": 0.298
+        },
+        "musique": {
+            "exact_match": 0.103
+        },
+        "bamboogle": {
+            "exact_match": 0.304
+        },
+        "fictionalhot": {
+            "exact_match": 0.059
+        }
+    }
+}

eval-results/ReSeek_Qwen2.5-7b-Instruct.json

@@ -0,0 +1,33 @@
+{
+    "config": {
+        "model_dtype": "torch.float16",
+        "model_name": "ReSeek-Qwen2.5-7b-Instruct",
+        "model_sha": "main"
+    },
+    "results": {
+        "nq": {
+            "exact_match": 0.469
+        },
+        "triviaqa": {
+            "exact_match": 0.640
+        },
+        "popqa": {
+            "exact_match": 0.501
+        },
+        "hotpotqa": {
+            "exact_match": 0.389
+        },
+        "2wiki": {
+            "exact_match": 0.382
+        },
+        "musique": {
+            "exact_match": 0.185
+        },
+        "bamboogle": {
+            "exact_match": 0.392
+        },
+        "fictionalhot": {
+            "exact_match": 0.061
+        }
+    }
+}

eval-results/SFT_Qwen2.5-7b-Instruct.json

@@ -0,0 +1,33 @@
+{
+    "config": {
+        "model_dtype": "torch.float16",
+        "model_name": "SFT-Qwen2.5-7b-Instruct",
+        "model_sha": "main"
+    },
+    "results": {
+        "nq": {
+            "exact_match": 0.318
+        },
+        "triviaqa": {
+            "exact_match": 0.354
+        },
+        "popqa": {
+            "exact_match": 0.121
+        },
+        "hotpotqa": {
+            "exact_match": 0.217
+        },
+        "2wiki": {
+            "exact_match": 0.259
+        },
+        "musique": {
+            "exact_match": 0.066
+        },
+        "bamboogle": {
+            "exact_match": 0.112
+        },
+        "fictionalhot": {
+            "exact_match": 0.003
+        }
+    }
+}

eval-results/Search-R1_Qwen2.5-3b-Instruct.json

@@ -0,0 +1,33 @@
+{
+    "config": {
+        "model_dtype": "torch.float16",
+        "model_name": "Search-R1-Qwen2.5-3b-Instruct",
+        "model_sha": "main"
+    },
+    "results": {
+        "nq": {
+            "exact_match": 0.341
+        },
+        "triviaqa": {
+            "exact_match": 0.545
+        },
+        "popqa": {
+            "exact_match": 0.378
+        },
+        "hotpotqa": {
+            "exact_match": 0.324
+        },
+        "2wiki": {
+            "exact_match": 0.319
+        },
+        "musique": {
+            "exact_match": 0.103
+        },
+        "bamboogle": {
+            "exact_match": 0.264
+        },
+        "fictionalhot": {
+            "exact_match": 0.037
+        }
+    }
+}

eval-results/Search-R1_Qwen2.5-7b-Instruct.json

@@ -0,0 +1,33 @@
+{
+    "config": {
+        "model_dtype": "torch.float16",
+        "model_name": "Search-R1-Qwen2.5-7b-Instruct",
+        "model_sha": "main"
+    },
+    "results": {
+        "nq": {
+            "exact_match": 0.393
+        },
+        "triviaqa": {
+            "exact_match": 0.610
+        },
+        "popqa": {
+            "exact_match": 0.397
+        },
+        "hotpotqa": {
+            "exact_match": 0.370
+        },
+        "2wiki": {
+            "exact_match": 0.414
+        },
+        "musique": {
+            "exact_match": 0.146
+        },
+        "bamboogle": {
+            "exact_match": 0.368
+        },
+        "fictionalhot": {
+            "exact_match": 0.034
+        }
+    }
+}

eval-results/Search-o1_Qwen2.5-7b-Instruct.json

@@ -0,0 +1,33 @@
+{
+    "config": {
+        "model_dtype": "torch.float16",
+        "model_name": "Search-o1-Qwen2.5-7b-Instruct",
+        "model_sha": "main"
+    },
+    "results": {
+        "nq": {
+            "exact_match": 0.151
+        },
+        "triviaqa": {
+            "exact_match": 0.443
+        },
+        "popqa": {
+            "exact_match": 0.131
+        },
+        "hotpotqa": {
+            "exact_match": 0.187
+        },
+        "2wiki": {
+            "exact_match": 0.176
+        },
+        "musique": {
+            "exact_match": 0.058
+        },
+        "bamboogle": {
+            "exact_match": 0.296
+        },
+        "fictionalhot": {
+            "exact_match": 0.020
+        }
+    }
+}

eval-results/ZeroSearch_Qwen2.5-3b-Instruct.json

@@ -0,0 +1,33 @@
+{
+    "config": {
+        "model_dtype": "torch.float16",
+        "model_name": "ZeroSearch-Qwen2.5-3b-Instruct",
+        "model_sha": "main"
+    },
+    "results": {
+        "nq": {
+            "exact_match": 0.414
+        },
+        "triviaqa": {
+            "exact_match": 0.574
+        },
+        "popqa": {
+            "exact_match": 0.448
+        },
+        "hotpotqa": {
+            "exact_match": 0.274
+        },
+        "2wiki": {
+            "exact_match": 0.300
+        },
+        "musique": {
+            "exact_match": 0.098
+        },
+        "bamboogle": {
+            "exact_match": 0.111
+        },
+        "fictionalhot": {
+            "exact_match": 0.030
+        }
+    }
+}

eval-results/ZeroSearch_Qwen2.5-7b-Instruct.json

@@ -0,0 +1,33 @@
+{
+    "config": {
+        "model_dtype": "torch.float16",
+        "model_name": "ZeroSearch-Qwen2.5-7b-Instruct",
+        "model_sha": "main"
+    },
+    "results": {
+        "nq": {
+            "exact_match": 0.436
+        },
+        "triviaqa": {
+            "exact_match": 0.652
+        },
+        "popqa": {
+            "exact_match": 0.488
+        },
+        "hotpotqa": {
+            "exact_match": 0.346
+        },
+        "2wiki": {
+            "exact_match": 0.352
+        },
+        "musique": {
+            "exact_match": 0.184
+        },
+        "bamboogle": {
+            "exact_match": 0.278
+        },
+        "fictionalhot": {
+            "exact_match": 0.031
+        }
+    }
+}

eval-results/demo-leaderboard/gpt2-demo/results_2023-11-21T18-10-08.json

@@ -0,0 +1,15 @@
+{
+    "config": {
+        "model_dtype": "torch.float16", 
+        "model_name": "demo-leaderboard/gpt2-demo",
+        "model_sha": "ac3299b02780836378b9e1e68c6eead546e89f90"
+    },
+    "results": {
+        "anli_r1": {
+            "acc": 0
+        },
+        "logiqa": {
+            "acc_norm": 0.90
+        }
+    }
+}

eval-results/demo-leaderboard/gpt2-demo/results_2023-11-22 15:46:20.425378.json

@@ -0,0 +1,33 @@
+{
+  "results": {
+    "anli_r1": {
+      "acc": 0.4,
+      "acc_stderr": 0.11239029738980327
+    },
+    "logiqa": {
+      "acc": 0.35,
+      "acc_stderr": 0.10942433098048308,
+      "acc_norm": 0.3,
+      "acc_norm_stderr": 0.10513149660756933
+    }
+  },
+  "versions": {
+    "anli_r1": 0,
+    "logiqa": 0
+  },
+  "config": {
+    "model": "hf-causal-experimental",
+    "model_args": "pretrained=demo-leaderboard/gpt2-demo,revision=main,dtype=bfloat16",
+    "num_fewshot": 0,
+    "batch_size": 1,
+    "batch_sizes": [],
+    "device": "cpu",
+    "no_cache": true,
+    "limit": 20,
+    "bootstrap_iters": 100000,
+    "description_dict": null,
+    "model_dtype": "bfloat16",
+    "model_name": "demo-leaderboard/gpt2-demo",
+    "model_sha": "main"
+  }
+}