Remove columns from eval

.gitignore

@@ -11,3 +11,4 @@ eval-results/
 eval-queue-bk/
 eval-results-bk/
 logs/
+results/*

src/display/utils.py

@@ -5,6 +5,7 @@ import pandas as pd
 
 from src.about import Tasks
 
+
 def fields(raw_class):
     return [v for k, v in raw_class.__dict__.items() if k[:2] != "__" and k[-2:] != "__"]
 
@@ -20,52 +21,59 @@ class ColumnContent:
     hidden: bool = False
     never_hidden: bool = False
 
-## Leaderboard columns
+
+# Leaderboard columns
 auto_eval_column_dict = []
 # Init
-auto_eval_column_dict.append(["model_type_symbol", ColumnContent, ColumnContent("T", "str", True, never_hidden=True)])
-auto_eval_column_dict.append(["model", ColumnContent, ColumnContent("Model", "markdown", True, never_hidden=True)])
-#Scores
+auto_eval_column_dict.append(["model_type_symbol", ColumnContent, ColumnContent(
+    "T", "str", True, never_hidden=True)])
+auto_eval_column_dict.append(["model", ColumnContent, ColumnContent(
+    "Model", "markdown", True, never_hidden=True)])
+# Scores
 # auto_eval_column_dict.append(["average", ColumnContent, ColumnContent("Average ⬆️", "number", True)])
 for task in Tasks:
-    auto_eval_column_dict.append([task.name, ColumnContent, ColumnContent(task.value.col_name, "number", True)])
+    auto_eval_column_dict.append(
+        [task.name, ColumnContent, ColumnContent(task.value.col_name, "number", True)])
 # Model information
-auto_eval_column_dict.append(["model_type", ColumnContent, ColumnContent("Type", "str", False)])
-auto_eval_column_dict.append(["architecture", ColumnContent, ColumnContent("Architecture", "str", False)])
-auto_eval_column_dict.append(["weight_type", ColumnContent, ColumnContent("Weight type", "str", False, True)])
-auto_eval_column_dict.append(["precision", ColumnContent, ColumnContent("Precision", "str", False)])
-auto_eval_column_dict.append(["license", ColumnContent, ColumnContent("Hub License", "str", False)])
-auto_eval_column_dict.append(["params", ColumnContent, ColumnContent("#Params (B)", "number", False)])
-auto_eval_column_dict.append(["likes", ColumnContent, ColumnContent("Hub ❤️", "number", False)])
-auto_eval_column_dict.append(["still_on_hub", ColumnContent, ColumnContent("Available on the hub", "bool", False)])
-auto_eval_column_dict.append(["revision", ColumnContent, ColumnContent("Model sha", "str", False, False)])
+auto_eval_column_dict.append(
+    ["model_type", ColumnContent, ColumnContent("Type", "str", False)])
+auto_eval_column_dict.append(
+    ["architecture", ColumnContent, ColumnContent("Architecture", "str", False)])
+auto_eval_column_dict.append(
+    ["precision", ColumnContent, ColumnContent("Precision", "str", False)])
+auto_eval_column_dict.append(
+    ["params", ColumnContent, ColumnContent("#Params (B)", "number", False)])
+auto_eval_column_dict.append(
+    ["revision", ColumnContent, ColumnContent("Model sha", "str", False, False)])
 
 # We use make dataclass to dynamically fill the scores from Tasks
-AutoEvalColumn = make_dataclass("AutoEvalColumn", auto_eval_column_dict, frozen=True)
+AutoEvalColumn = make_dataclass(
+    "AutoEvalColumn", auto_eval_column_dict, frozen=True)
+
+# For the queue columns in the submission tab
+
 
-## For the queue columns in the submission tab
 @dataclass(frozen=True)
 class EvalQueueColumn:  # Queue column
     model = ColumnContent("model", "markdown", True)
     revision = ColumnContent("revision", "str", True)
     private = ColumnContent("private", "bool", True)
     precision = ColumnContent("precision", "str", True)
-    weight_type = ColumnContent("weight_type", "str", "Original")
     status = ColumnContent("status", "str", True)
 
-## All the model information that we might need
+# All the model information that we might need
+
+
 @dataclass
 class ModelDetails:
     name: str
     display_name: str = ""
-    symbol: str = "" # emoji
+    symbol: str = ""  # emoji
 
 
 class ModelType(Enum):
-    PT = ModelDetails(name="pretrained", symbol="🟢")
-    FT = ModelDetails(name="fine-tuned", symbol="🔶")
-    IFT = ModelDetails(name="instruction-tuned", symbol="⭕")
-    RL = ModelDetails(name="RL-tuned", symbol="🟦")
+    OP = ModelDetails(name="pretrained", symbol="🟢")
+    CL = ModelDetails(name="instruction-tuned", symbol="⭕")
     Unknown = ModelDetails(name="", symbol="?")
 
     def to_str(self, separator=" "):
@@ -73,20 +81,12 @@ class ModelType(Enum):
 
     @staticmethod
     def from_str(type):
-        if "fine-tuned" in type or "🔶" in type:
-            return ModelType.FT
-        if "pretrained" in type or "🟢" in type:
-            return ModelType.PT
-        if "RL-tuned" in type or "🟦" in type:
-            return ModelType.RL
-        if "instruction-tuned" in type or "⭕" in type:
-            return ModelType.IFT
+        if "open" in type or "🟢" in type:
+            return ModelType.OP
+        if "closed" in type or "⭕" in type:
+            return ModelType.CL
         return ModelType.Unknown
 
-class WeightType(Enum):
-    Adapter = ModelDetails("Adapter")
-    Original = ModelDetails("Original")
-    Delta = ModelDetails("Delta")
 
 class Precision(Enum):
     float16 = ModelDetails("float16")
@@ -100,6 +100,7 @@ class Precision(Enum):
             return Precision.bfloat16
         return Precision.Unknown
 
+
 # Column selection
 COLS = [c.name for c in fields(AutoEvalColumn) if not c.hidden]
 
@@ -107,4 +108,3 @@ EVAL_COLS = [c.name for c in fields(EvalQueueColumn)]
 EVAL_TYPES = [c.type for c in fields(EvalQueueColumn)]
 
 BENCHMARK_COLS = [t.value.col_name for t in Tasks]
-