Add init files

app.py

@@ -343,4 +343,5 @@ with demo:
 scheduler = BackgroundScheduler()
 scheduler.add_job(restart_space, "interval", seconds=1800)
 scheduler.start()
-demo.queue(default_concurrency_limit=40).launch()
+# demo.queue(default_concurrency_limit=40).launch()
+demo.queue().launch()

eval-queue/leaderboard/aya.json

@@ -0,0 +1 @@
+{"model": "aya", "base_model": "", "revision": "main", "private": false, "precision": "float16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 0.1, "license": "custom"}

eval-queue/leaderboard/demo-leaderboard_gpt2-demo_eval_request_False_bfloat16_Original.json

@@ -1 +0,0 @@
-{"model": "demo-leaderboard/gpt2-demo", "base_model": "", "revision": "main", "private": false, "precision": "float16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 0.1, "license": "custom"}

eval-queue/leaderboard/gpt35.json

@@ -0,0 +1 @@
+{"model": "gpt35", "base_model": "", "revision": "main", "private": false, "precision": "float16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 0.1, "license": "custom"}

eval-queue/leaderboard/gpt4.json

@@ -0,0 +1 @@
+{"model": "gpt4", "base_model": "", "revision": "main", "private": false, "precision": "float16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 0.1, "license": "custom"}

eval-queue/leaderboard/haiku.json

@@ -0,0 +1 @@
+{"model": "haiku", "base_model": "", "revision": "main", "private": false, "precision": "float16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 0.1, "license": "custom"}

eval-queue/leaderboard/human.json

@@ -0,0 +1 @@
+{"model": "human", "base_model": "", "revision": "main", "private": false, "precision": "float16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 0.1, "license": "custom"}

eval-queue/leaderboard/mgpt.json

@@ -0,0 +1 @@
+{"model": "mgpt", "base_model": "", "revision": "main", "private": false, "precision": "float16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 0.1, "license": "custom"}

eval-queue/leaderboard/mt0xl.json

@@ -0,0 +1 @@
+{"model": "mt0xl", "base_model": "", "revision": "main", "private": false, "precision": "float16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 0.1, "license": "custom"}

eval-queue/leaderboard/persianmind.json

@@ -0,0 +1 @@
+{"model": "persianmind", "base_model": "", "revision": "main", "private": false, "precision": "float16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 0.1, "license": "custom"}

eval-queue/leaderboard/random.json

@@ -0,0 +1 @@
+{"model": "random", "base_model": "", "revision": "main", "private": false, "precision": "float16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 0.1, "license": "custom"}

eval-queue/leaderboard/xverse13b.json

@@ -0,0 +1 @@
+{"model": "xverse13b", "base_model": "", "revision": "main", "private": false, "precision": "float16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 0.1, "license": "custom"}

eval-queue/leaderboard/xverse7b.json

@@ -0,0 +1 @@
+{"model": "xverse7b", "base_model": "", "revision": "main", "private": false, "precision": "float16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 0.1, "license": "custom"}

eval-results/leaderboard/aya/aya.json

@@ -0,0 +1 @@
+{"config": {"model_dtype": "", "model_name": "aya", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.29}, "Calculus USS": {"Acc": 0.26}, "Chemistry USS": {"Acc": 0.3}, "Discrete Mathematics USS": {"Acc": 0.24}, "Economy USS": {"Acc": 0.47}, "Geography USS": {"Acc": 0.36}, "Geology USS": {"Acc": 0.36}, "Geometry USS": {"Acc": 0.28}, "History USS": {"Acc": 0.33}, "Logic USS": {"Acc": 0.29}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.29}, "Mathematics LPS": {"Acc": 0.31}, "Mathematics LSS": {"Acc": 0.31}, "Mathematics UPS": {"Acc": 0.29}, "Mathematics USS": {"Acc": 0.27}, "Mathematics and Statistics USS": {"Acc": 0.27}, "Natural Sciences LPS": {"Acc": 0.5}, "Natural Sciences LSS": {"Acc": 0.33}, "Natural Sciences UPS": {"Acc": 0.43}, "Persian Literature LPS": {"Acc": 0.41}, "Persian Literature LSS": {"Acc": 0.3}, "Persian Literature UPS": {"Acc": 0.31}, "Persian Literature USS": {"Acc": 0.29}, "Philosophy USS": {"Acc": 0.36}, "Physics USS": {"Acc": 0.27}, "Probability and Statistics USS": {"Acc": 0.25}, "Psychology USS": {"Acc": 0.4}, "Social Studies LPS": {"Acc": 0.62}, "Social Studies LSS": {"Acc": 0.39}, "Social Studies UPS": {"Acc": 0.46}, "Sociology USS": {"Acc": 0.34}, "Speed and Accuracy UPS": {"Acc": 0.27}, "Theology LPS": {"Acc": 0.54}, "Theology LSS": {"Acc": 0.46}, "Theology UPS": {"Acc": 0.49}, "Theology USS": {"Acc": 0.37}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.36}, "\u200cBiology USS": {"Acc": 0.29}, "Avg on all tasks": {"Acc": 0.35}, "Avg on all questions": {"Acc": 0.34}}}

eval-results/leaderboard/gpt2-demo/demo-leaderboard_gpt2-demo_results_2023-11-21T18-10-08.json

@@ -1,15 +0,0 @@
-{
-    "config": {
-        "model_dtype": "torch.float16", 
-        "model_name": "demo-leaderboard/gpt2-demo",
-        "model_sha": "ac3299b02780836378b9e1e68c6eead546e89f90"
-    },
-    "results": {
-        "task_name1": {
-            "metric_name": 0
-        },
-        "task_name2": {
-            "metric_name": 0.90
-        }
-    }
-}

eval-results/leaderboard/gpt35/gpt35.json

@@ -0,0 +1 @@
+{"config": {"model_dtype": "", "model_name": "gpt35", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.36}, "Calculus USS": {"Acc": 0.26}, "Chemistry USS": {"Acc": 0.31}, "Discrete Mathematics USS": {"Acc": 0.22}, "Economy USS": {"Acc": 0.4}, "Geography USS": {"Acc": 0.38}, "Geology USS": {"Acc": 0.39}, "Geometry USS": {"Acc": 0.3}, "History USS": {"Acc": 0.37}, "Logic USS": {"Acc": 0.31}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.26}, "Mathematics LPS": {"Acc": 0.39}, "Mathematics LSS": {"Acc": 0.32}, "Mathematics UPS": {"Acc": 0.35}, "Mathematics USS": {"Acc": 0.31}, "Mathematics and Statistics USS": {"Acc": 0.34}, "Natural Sciences LPS": {"Acc": 0.61}, "Natural Sciences LSS": {"Acc": 0.39}, "Natural Sciences UPS": {"Acc": 0.5}, "Persian Literature LPS": {"Acc": 0.42}, "Persian Literature LSS": {"Acc": 0.34}, "Persian Literature UPS": {"Acc": 0.38}, "Persian Literature USS": {"Acc": 0.27}, "Philosophy USS": {"Acc": 0.39}, "Physics USS": {"Acc": 0.29}, "Probability and Statistics USS": {"Acc": 0.31}, "Psychology USS": {"Acc": 0.4}, "Social Studies LPS": {"Acc": 0.67}, "Social Studies LSS": {"Acc": 0.43}, "Social Studies UPS": {"Acc": 0.52}, "Sociology USS": {"Acc": 0.33}, "Speed and Accuracy UPS": {"Acc": 0.36}, "Theology LPS": {"Acc": 0.61}, "Theology LSS": {"Acc": 0.45}, "Theology UPS": {"Acc": 0.54}, "Theology USS": {"Acc": 0.34}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.43}, "\u200cBiology USS": {"Acc": 0.3}, "Avg on all tasks": {"Acc": 0.38}, "Avg on all questions": {"Acc": 0.36}}}

eval-results/leaderboard/gpt4/gpt4.json

@@ -0,0 +1 @@
+{"config": {"model_dtype": "", "model_name": "gpt4", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.53}, "Calculus USS": {"Acc": 0.34}, "Chemistry USS": {"Acc": 0.36}, "Discrete Mathematics USS": {"Acc": 0.29}, "Economy USS": {"Acc": 0.62}, "Geography USS": {"Acc": 0.56}, "Geology USS": {"Acc": 0.56}, "Geometry USS": {"Acc": 0.34}, "History USS": {"Acc": 0.55}, "Logic USS": {"Acc": 0.43}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.45}, "Mathematics LPS": {"Acc": 0.56}, "Mathematics LSS": {"Acc": 0.4}, "Mathematics UPS": {"Acc": 0.49}, "Mathematics USS": {"Acc": 0.34}, "Mathematics and Statistics USS": {"Acc": 0.42}, "Natural Sciences LPS": {"Acc": 0.79}, "Natural Sciences LSS": {"Acc": 0.59}, "Natural Sciences UPS": {"Acc": 0.74}, "Persian Literature LPS": {"Acc": 0.66}, "Persian Literature LSS": {"Acc": 0.51}, "Persian Literature UPS": {"Acc": 0.57}, "Persian Literature USS": {"Acc": 0.35}, "Philosophy USS": {"Acc": 0.54}, "Physics USS": {"Acc": 0.39}, "Probability and Statistics USS": {"Acc": 0.39}, "Psychology USS": {"Acc": 0.63}, "Social Studies LPS": {"Acc": 0.85}, "Social Studies LSS": {"Acc": 0.67}, "Social Studies UPS": {"Acc": 0.73}, "Sociology USS": {"Acc": 0.48}, "Speed and Accuracy UPS": {"Acc": 0.38}, "Theology LPS": {"Acc": 0.84}, "Theology LSS": {"Acc": 0.69}, "Theology UPS": {"Acc": 0.79}, "Theology USS": {"Acc": 0.53}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.55}, "\u200cBiology USS": {"Acc": 0.32}, "Avg on all tasks": {"Acc": 0.53}, "Avg on all questions": {"Acc": 0.5}}}

eval-results/leaderboard/haiku/haiku.json

@@ -0,0 +1 @@
+{"config": {"model_dtype": "", "model_name": "haiku", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.39}, "Calculus USS": {"Acc": 0.29}, "Chemistry USS": {"Acc": 0.3}, "Discrete Mathematics USS": {"Acc": 0.27}, "Economy USS": {"Acc": 0.51}, "Geography USS": {"Acc": 0.5}, "Geology USS": {"Acc": 0.52}, "Geometry USS": {"Acc": 0.32}, "History USS": {"Acc": 0.47}, "Logic USS": {"Acc": 0.4}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.28}, "Mathematics LPS": {"Acc": 0.38}, "Mathematics LSS": {"Acc": 0.36}, "Mathematics UPS": {"Acc": 0.35}, "Mathematics USS": {"Acc": 0.29}, "Mathematics and Statistics USS": {"Acc": 0.36}, "Natural Sciences LPS": {"Acc": 0.71}, "Natural Sciences LSS": {"Acc": 0.46}, "Natural Sciences UPS": {"Acc": 0.63}, "Persian Literature LPS": {"Acc": 0.55}, "Persian Literature LSS": {"Acc": 0.46}, "Persian Literature UPS": {"Acc": 0.53}, "Persian Literature USS": {"Acc": 0.32}, "Philosophy USS": {"Acc": 0.51}, "Physics USS": {"Acc": 0.32}, "Probability and Statistics USS": {"Acc": 0.35}, "Psychology USS": {"Acc": 0.5}, "Social Studies LPS": {"Acc": 0.77}, "Social Studies LSS": {"Acc": 0.57}, "Social Studies UPS": {"Acc": 0.7}, "Sociology USS": {"Acc": 0.44}, "Speed and Accuracy UPS": {"Acc": 0.32}, "Theology LPS": {"Acc": 0.71}, "Theology LSS": {"Acc": 0.61}, "Theology UPS": {"Acc": 0.68}, "Theology USS": {"Acc": 0.45}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.49}, "\u200cBiology USS": {"Acc": 0.27}, "Avg on all tasks": {"Acc": 0.46}, "Avg on all questions": {"Acc": 0.43}}}

eval-results/leaderboard/human/human.json

@@ -0,0 +1 @@
+{"config": {"model_dtype": "", "model_name": "human", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.59}, "Calculus USS": {"Acc": 0.85}, "Chemistry USS": {"Acc": 0.73}, "Discrete Mathematics USS": {"Acc": 0.78}, "Economy USS": {"Acc": 0.69}, "Geography USS": {"Acc": 0.85}, "Geology USS": {"Acc": 0.89}, "Geometry USS": {"Acc": 0.83}, "History USS": {"Acc": 0.85}, "Logic USS": {"Acc": 0.58}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.44}, "Mathematics LPS": {"Acc": 0.77}, "Mathematics LSS": {"Acc": 0.77}, "Mathematics UPS": {"Acc": 0.66}, "Mathematics USS": {"Acc": 0.84}, "Mathematics and Statistics USS": {"Acc": 0.63}, "Natural Sciences LPS": {"Acc": 0.85}, "Natural Sciences LSS": {"Acc": 0.72}, "Natural Sciences UPS": {"Acc": 0.82}, "Persian Literature LPS": {"Acc": 0.83}, "Persian Literature LSS": {"Acc": 0.77}, "Persian Literature UPS": {"Acc": 0.8}, "Persian Literature USS": {"Acc": 0.59}, "Philosophy USS": {"Acc": 0.61}, "Physics USS": {"Acc": 0.83}, "Probability and Statistics USS": {"Acc": 0.77}, "Psychology USS": {"Acc": 0.79}, "Social Studies LPS": {"Acc": 0.94}, "Social Studies LSS": {"Acc": 0.86}, "Social Studies UPS": {"Acc": 0.89}, "Sociology USS": {"Acc": 0.82}, "Speed and Accuracy UPS": {"Acc": 0.84}, "Theology LPS": {"Acc": 0.88}, "Theology LSS": {"Acc": 0.88}, "Theology UPS": {"Acc": 0.9}, "Theology USS": {"Acc": 0.8}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.63}, "\u200cBiology USS": {"Acc": 0.73}, "Avg on all tasks": {"Acc": 0.77}, "Avg on all questions": {"Acc": 0.77}}}

eval-results/leaderboard/mgpt/mgpt.json

@@ -0,0 +1 @@
+{"config": {"model_dtype": "", "model_name": "mgpt", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.28}, "Calculus USS": {"Acc": 0.27}, "Chemistry USS": {"Acc": 0.26}, "Discrete Mathematics USS": {"Acc": 0.27}, "Economy USS": {"Acc": 0.25}, "Geography USS": {"Acc": 0.26}, "Geology USS": {"Acc": 0.25}, "Geometry USS": {"Acc": 0.23}, "History USS": {"Acc": 0.25}, "Logic USS": {"Acc": 0.21}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.28}, "Mathematics LPS": {"Acc": 0.25}, "Mathematics LSS": {"Acc": 0.25}, "Mathematics UPS": {"Acc": 0.27}, "Mathematics USS": {"Acc": 0.25}, "Mathematics and Statistics USS": {"Acc": 0.27}, "Natural Sciences LPS": {"Acc": 0.28}, "Natural Sciences LSS": {"Acc": 0.25}, "Natural Sciences UPS": {"Acc": 0.24}, "Persian Literature LPS": {"Acc": 0.29}, "Persian Literature LSS": {"Acc": 0.24}, "Persian Literature UPS": {"Acc": 0.26}, "Persian Literature USS": {"Acc": 0.25}, "Philosophy USS": {"Acc": 0.27}, "Physics USS": {"Acc": 0.25}, "Probability and Statistics USS": {"Acc": 0.23}, "Psychology USS": {"Acc": 0.22}, "Social Studies LPS": {"Acc": 0.25}, "Social Studies LSS": {"Acc": 0.23}, "Social Studies UPS": {"Acc": 0.26}, "Sociology USS": {"Acc": 0.27}, "Speed and Accuracy UPS": {"Acc": 0.26}, "Theology LPS": {"Acc": 0.21}, "Theology LSS": {"Acc": 0.26}, "Theology UPS": {"Acc": 0.25}, "Theology USS": {"Acc": 0.24}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.33}, "\u200cBiology USS": {"Acc": 0.22}, "Avg on all tasks": {"Acc": 0.25}, "Avg on all questions": {"Acc": 0.25}}}

eval-results/leaderboard/mt0xl/mt0xl.json

@@ -0,0 +1 @@
+{"config": {"model_dtype": "", "model_name": "mt0xl", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.28}, "Calculus USS": {"Acc": 0.25}, "Chemistry USS": {"Acc": 0.28}, "Discrete Mathematics USS": {"Acc": 0.26}, "Economy USS": {"Acc": 0.31}, "Geography USS": {"Acc": 0.28}, "Geology USS": {"Acc": 0.25}, "Geometry USS": {"Acc": 0.25}, "History USS": {"Acc": 0.27}, "Logic USS": {"Acc": 0.22}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.21}, "Mathematics LPS": {"Acc": 0.27}, "Mathematics LSS": {"Acc": 0.25}, "Mathematics UPS": {"Acc": 0.27}, "Mathematics USS": {"Acc": 0.25}, "Mathematics and Statistics USS": {"Acc": 0.27}, "Natural Sciences LPS": {"Acc": 0.38}, "Natural Sciences LSS": {"Acc": 0.28}, "Natural Sciences UPS": {"Acc": 0.3}, "Persian Literature LPS": {"Acc": 0.33}, "Persian Literature LSS": {"Acc": 0.3}, "Persian Literature UPS": {"Acc": 0.31}, "Persian Literature USS": {"Acc": 0.26}, "Philosophy USS": {"Acc": 0.33}, "Physics USS": {"Acc": 0.27}, "Probability and Statistics USS": {"Acc": 0.23}, "Psychology USS": {"Acc": 0.35}, "Social Studies LPS": {"Acc": 0.38}, "Social Studies LSS": {"Acc": 0.31}, "Social Studies UPS": {"Acc": 0.36}, "Sociology USS": {"Acc": 0.26}, "Speed and Accuracy UPS": {"Acc": 0.28}, "Theology LPS": {"Acc": 0.51}, "Theology LSS": {"Acc": 0.35}, "Theology UPS": {"Acc": 0.35}, "Theology USS": {"Acc": 0.3}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.31}, "\u200cBiology USS": {"Acc": 0.26}, "Avg on all tasks": {"Acc": 0.29}, "Avg on all questions": {"Acc": 0.29}}}

eval-results/leaderboard/persianmind/persianmind.json

@@ -0,0 +1 @@
+{"config": {"model_dtype": "", "model_name": "persianmind", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.27}, "Calculus USS": {"Acc": 0.21}, "Chemistry USS": {"Acc": 0.26}, "Discrete Mathematics USS": {"Acc": 0.29}, "Economy USS": {"Acc": 0.28}, "Geography USS": {"Acc": 0.3}, "Geology USS": {"Acc": 0.27}, "Geometry USS": {"Acc": 0.28}, "History USS": {"Acc": 0.31}, "Logic USS": {"Acc": 0.31}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.24}, "Mathematics LPS": {"Acc": 0.22}, "Mathematics LSS": {"Acc": 0.29}, "Mathematics UPS": {"Acc": 0.26}, "Mathematics USS": {"Acc": 0.27}, "Mathematics and Statistics USS": {"Acc": 0.28}, "Natural Sciences LPS": {"Acc": 0.33}, "Natural Sciences LSS": {"Acc": 0.3}, "Natural Sciences UPS": {"Acc": 0.29}, "Persian Literature LPS": {"Acc": 0.29}, "Persian Literature LSS": {"Acc": 0.26}, "Persian Literature UPS": {"Acc": 0.26}, "Persian Literature USS": {"Acc": 0.26}, "Philosophy USS": {"Acc": 0.31}, "Physics USS": {"Acc": 0.27}, "Probability and Statistics USS": {"Acc": 0.2}, "Psychology USS": {"Acc": 0.32}, "Social Studies LPS": {"Acc": 0.45}, "Social Studies LSS": {"Acc": 0.29}, "Social Studies UPS": {"Acc": 0.38}, "Sociology USS": {"Acc": 0.27}, "Speed and Accuracy UPS": {"Acc": 0.26}, "Theology LPS": {"Acc": 0.34}, "Theology LSS": {"Acc": 0.31}, "Theology UPS": {"Acc": 0.34}, "Theology USS": {"Acc": 0.26}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.28}, "\u200cBiology USS": {"Acc": 0.3}, "Avg on all tasks": {"Acc": 0.29}, "Avg on all questions": {"Acc": 0.28}}}

eval-results/leaderboard/random/random.json

@@ -0,0 +1 @@
+{"config": {"model_dtype": "", "model_name": "random", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.26}, "Calculus USS": {"Acc": 0.29}, "Chemistry USS": {"Acc": 0.24}, "Discrete Mathematics USS": {"Acc": 0.3}, "Economy USS": {"Acc": 0.29}, "Geography USS": {"Acc": 0.25}, "Geology USS": {"Acc": 0.26}, "Geometry USS": {"Acc": 0.24}, "History USS": {"Acc": 0.24}, "Logic USS": {"Acc": 0.26}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.18}, "Mathematics LPS": {"Acc": 0.26}, "Mathematics LSS": {"Acc": 0.26}, "Mathematics UPS": {"Acc": 0.28}, "Mathematics USS": {"Acc": 0.26}, "Mathematics and Statistics USS": {"Acc": 0.23}, "Natural Sciences LPS": {"Acc": 0.25}, "Natural Sciences LSS": {"Acc": 0.23}, "Natural Sciences UPS": {"Acc": 0.26}, "Persian Literature LPS": {"Acc": 0.25}, "Persian Literature LSS": {"Acc": 0.25}, "Persian Literature UPS": {"Acc": 0.24}, "Persian Literature USS": {"Acc": 0.25}, "Philosophy USS": {"Acc": 0.24}, "Physics USS": {"Acc": 0.26}, "Probability and Statistics USS": {"Acc": 0.23}, "Psychology USS": {"Acc": 0.24}, "Social Studies LPS": {"Acc": 0.23}, "Social Studies LSS": {"Acc": 0.26}, "Social Studies UPS": {"Acc": 0.26}, "Sociology USS": {"Acc": 0.24}, "Speed and Accuracy UPS": {"Acc": 0.17}, "Theology LPS": {"Acc": 0.31}, "Theology LSS": {"Acc": 0.29}, "Theology UPS": {"Acc": 0.28}, "Theology USS": {"Acc": 0.24}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.26}, "\u200cBiology USS": {"Acc": 0.25}, "Avg on all tasks": {"Acc": 0.25}, "Avg on all questions": {"Acc": 0.25}}}

eval-results/leaderboard/xverse13b/xverse13b.json

@@ -0,0 +1 @@
+{"config": {"model_dtype": "", "model_name": "xverse13b", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.29}, "Calculus USS": {"Acc": 0.25}, "Chemistry USS": {"Acc": 0.28}, "Discrete Mathematics USS": {"Acc": 0.24}, "Economy USS": {"Acc": 0.33}, "Geography USS": {"Acc": 0.3}, "Geology USS": {"Acc": 0.32}, "Geometry USS": {"Acc": 0.27}, "History USS": {"Acc": 0.33}, "Logic USS": {"Acc": 0.33}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.22}, "Mathematics LPS": {"Acc": 0.33}, "Mathematics LSS": {"Acc": 0.31}, "Mathematics UPS": {"Acc": 0.27}, "Mathematics USS": {"Acc": 0.24}, "Mathematics and Statistics USS": {"Acc": 0.28}, "Natural Sciences LPS": {"Acc": 0.48}, "Natural Sciences LSS": {"Acc": 0.32}, "Natural Sciences UPS": {"Acc": 0.39}, "Persian Literature LPS": {"Acc": 0.39}, "Persian Literature LSS": {"Acc": 0.29}, "Persian Literature UPS": {"Acc": 0.35}, "Persian Literature USS": {"Acc": 0.25}, "Philosophy USS": {"Acc": 0.31}, "Physics USS": {"Acc": 0.28}, "Probability and Statistics USS": {"Acc": 0.25}, "Psychology USS": {"Acc": 0.32}, "Social Studies LPS": {"Acc": 0.59}, "Social Studies LSS": {"Acc": 0.35}, "Social Studies UPS": {"Acc": 0.36}, "Sociology USS": {"Acc": 0.32}, "Speed and Accuracy UPS": {"Acc": 0.29}, "Theology LPS": {"Acc": 0.48}, "Theology LSS": {"Acc": 0.38}, "Theology UPS": {"Acc": 0.41}, "Theology USS": {"Acc": 0.28}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.37}, "\u200cBiology USS": {"Acc": 0.27}, "Avg on all tasks": {"Acc": 0.32}, "Avg on all questions": {"Acc": 0.31}}}

eval-results/leaderboard/xverse7b/xverse7b.json

@@ -0,0 +1 @@
+{"config": {"model_dtype": "", "model_name": "xverse7b", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.32}, "Calculus USS": {"Acc": 0.26}, "Chemistry USS": {"Acc": 0.27}, "Discrete Mathematics USS": {"Acc": 0.23}, "Economy USS": {"Acc": 0.25}, "Geography USS": {"Acc": 0.31}, "Geology USS": {"Acc": 0.23}, "Geometry USS": {"Acc": 0.28}, "History USS": {"Acc": 0.29}, "Logic USS": {"Acc": 0.29}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.22}, "Mathematics LPS": {"Acc": 0.32}, "Mathematics LSS": {"Acc": 0.26}, "Mathematics UPS": {"Acc": 0.27}, "Mathematics USS": {"Acc": 0.25}, "Mathematics and Statistics USS": {"Acc": 0.28}, "Natural Sciences LPS": {"Acc": 0.4}, "Natural Sciences LSS": {"Acc": 0.29}, "Natural Sciences UPS": {"Acc": 0.32}, "Persian Literature LPS": {"Acc": 0.3}, "Persian Literature LSS": {"Acc": 0.28}, "Persian Literature UPS": {"Acc": 0.28}, "Persian Literature USS": {"Acc": 0.26}, "Philosophy USS": {"Acc": 0.26}, "Physics USS": {"Acc": 0.24}, "Probability and Statistics USS": {"Acc": 0.24}, "Psychology USS": {"Acc": 0.35}, "Social Studies LPS": {"Acc": 0.44}, "Social Studies LSS": {"Acc": 0.34}, "Social Studies UPS": {"Acc": 0.36}, "Sociology USS": {"Acc": 0.28}, "Speed and Accuracy UPS": {"Acc": 0.26}, "Theology LPS": {"Acc": 0.44}, "Theology LSS": {"Acc": 0.34}, "Theology UPS": {"Acc": 0.38}, "Theology USS": {"Acc": 0.28}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.27}, "\u200cBiology USS": {"Acc": 0.28}, "Avg on all tasks": {"Acc": 0.3}, "Avg on all questions": {"Acc": 0.29}}}

src/display/about.py

@@ -51,8 +51,8 @@ class Tasks(Enum):
     Theology_USS = Task("Theology USS", "Acc", "Theology USS")
     Verbal_and_Linguistic_Intelligence_UPS = Task("Verbal and Linguistic Intelligence UPS", "Acc", "Verbal and Linguistic Intelligence UPS")
     Biology_USS = Task("‌Biology USS", "Acc", "‌Biology USS")
-    Avg_on_all_tasks = Task("Avg on all tasks", "Acc", "Avg on all tasks")
-    Avg_on_all_questions = Task("Avg on all questions", "Acc", "Avg on all questions")
+    # Avg_on_all_tasks = Task("Avg on all tasks", "Acc", "Avg on all tasks")
+    # Avg_on_all_questions = Task("Avg on all questions", "Acc", "Avg on all questions")
 
 
 # Your leaderboard name