Update model size filter intervals

Hello!

We have cloned this leaderboard to run a [Open Korean LLM Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard). We have over 100 models in the past couple of weeks so far!
As discussed with

@clefourrier

, I'm proposing this change to make the model size filter behavior more clear.

Currently the notation like `~13B` means `around 13B` and shows models between 12B and 15B. Although individuals may interpret the notation differently, we thought this could be improved and be more intuitive. Moreover, with `~3B` and `~7B` shows `1.5B~5B` and `6B~11B` respectively, there is no way to filter for models with size between 5B and 6B, such as 5.8B. We actually had a request from one of participants for size 5.8B. (See [discussion](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard/discussions/5))

So the proposal is to change the notation to `1.5~3B` and filter for models with size between 1.5B and 3B.


I hope this makes sense!

app.py

@@ -254,12 +254,13 @@ def select_columns(df: pd.DataFrame, columns: list) -> pd.DataFrame:
 
 NUMERIC_INTERVALS = {
     "Unknown": pd.Interval(-1, 0, closed="right"),
-    "< 1.5B": pd.Interval(0, 1.5, closed="right"),
-    "~3B": pd.Interval(1.5, 5, closed="right"),
-    "~7B": pd.Interval(6, 11, closed="right"),
-    "~13B": pd.Interval(12, 15, closed="right"),
-    "~35B": pd.Interval(16, 55, closed="right"),
-    "60B+": pd.Interval(55, 10000, closed="right"),
+    "0~1.5B": pd.Interval(0, 1.5, closed="right"),
+    "1.5~3B": pd.Interval(1.5, 3, closed="right"),
+    "3~7B": pd.Interval(3, 7, closed="right"),
+    "7~13B": pd.Interval(7, 13, closed="right"),
+    "13~35B": pd.Interval(13, 35, closed="right"),
+    "35~60B": pd.Interval(35, 60, closed="right"),
+    "60B+": pd.Interval(60, 10000, closed="right"),
 }