upload results

app.py

@@ -57,137 +57,38 @@ LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS,
     pending_eval_queue_df,
 ) = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)
 
-def init_leaderboard(dataframe):
-    if dataframe is None or dataframe.empty:
-        raise ValueError("Leaderboard DataFrame is empty or None.")
-    return Leaderboard(
-        value=dataframe,
-        datatype=[c.type for c in fields(AutoEvalColumn)],
-        select_columns=SelectColumns(
-            default_selection=[c.name for c in fields(AutoEvalColumn) if c.displayed_by_default],
-            cant_deselect=[c.name for c in fields(AutoEvalColumn) if c.never_hidden],
-            label="Select Columns to Display:",
-        ),
-        search_columns=[AutoEvalColumn.model.name, AutoEvalColumn.license.name],
-        hide_columns=[c.name for c in fields(AutoEvalColumn) if c.hidden],
-        filter_columns=[
-            ColumnFilter(AutoEvalColumn.model_type.name, type="checkboxgroup", label="Model types"),
-            ColumnFilter(AutoEvalColumn.precision.name, type="checkboxgroup", label="Precision"),
-            ColumnFilter(
-                AutoEvalColumn.params.name,
-                type="slider",
-                min=0.01,
-                max=150,
-                label="Select the number of parameters (B)",
-            ),
-            ColumnFilter(
-                AutoEvalColumn.still_on_hub.name, type="boolean", label="Deleted/incomplete", default=True
-            ),
-        ],
-        bool_checkboxgroup_label="Hide models",
-        interactive=False,
-    )
 
+def load_data():
+    import pandas as pd
+    # load results.csv
+    results_df = pd.read_csv("results.csv")
+    return results_df
 
 demo = gr.Blocks(css=custom_css)
 with demo:
     gr.HTML(TITLE)
     gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
 
-    with gr.Tabs(elem_classes="tab-buttons") as tabs:
-        with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
-            leaderboard = init_leaderboard(LEADERBOARD_DF)
-
-        with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
-            gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
-
-        with gr.TabItem("🚀 Submit here! ", elem_id="llm-benchmark-tab-table", id=3):
-            with gr.Column():
-                with gr.Row():
-                    gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
-
-                with gr.Column():
-                    with gr.Accordion(
-                        f"✅ Finished Evaluations ({len(finished_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            finished_eval_table = gr.components.Dataframe(
-                                value=finished_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
-                    with gr.Accordion(
-                        f"🔄 Running Evaluation Queue ({len(running_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            running_eval_table = gr.components.Dataframe(
-                                value=running_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
-
-                    with gr.Accordion(
-                        f"⏳ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            pending_eval_table = gr.components.Dataframe(
-                                value=pending_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
+    with gr.Tabs():
+        with gr.TabItem("Leaderboard"):
             with gr.Row():
-                gr.Markdown("# ✉️✨ Submit your model here!", elem_classes="markdown-text")
-
-            with gr.Row():
-                with gr.Column():
-                    model_name_textbox = gr.Textbox(label="Model name")
-                    revision_name_textbox = gr.Textbox(label="Revision commit", placeholder="main")
-                    model_type = gr.Dropdown(
-                        choices=[t.to_str(" : ") for t in ModelType if t != ModelType.Unknown],
-                        label="Model type",
-                        multiselect=False,
-                        value=None,
-                        interactive=True,
-                    )
-
-                with gr.Column():
-                    precision = gr.Dropdown(
-                        choices=[i.value.name for i in Precision if i != Precision.Unknown],
-                        label="Precision",
-                        multiselect=False,
-                        value="float16",
-                        interactive=True,
-                    )
-                    weight_type = gr.Dropdown(
-                        choices=[i.value.name for i in WeightType],
-                        label="Weights type",
-                        multiselect=False,
-                        value="Original",
-                        interactive=True,
-                    )
-                    base_model_name_textbox = gr.Textbox(label="Base model (for delta or adapter weights)")
-
-            submit_button = gr.Button("Submit Eval")
-            submission_result = gr.Markdown()
-            submit_button.click(
-                add_new_eval,
-                [
-                    model_name_textbox,
-                    base_model_name_textbox,
-                    revision_name_textbox,
-                    precision,
-                    weight_type,
-                    model_type,
-                ],
-                submission_result,
+                version_dropdown = gr.Dropdown(
+                    choices=["All"],
+                    label="🔄 Select Models",
+                    value="All",
+                )
+                model_dropdown = gr.Dropdown(
+                    choices=["All"],
+                    label="🔄 Select Inference Method",
+                    value="All",
+                )
+
+            leaderboard_table = gr.components.Dataframe(
+                value=load_data(),
+                interactive=True,
+                visible=True,
             )
-
+    
     with gr.Row():
         with gr.Accordion("📙 Citation", open=False):
             citation_button = gr.Textbox(

results.csv

@@ -0,0 +1,27 @@
+copyright,model,decoding,count_verbatim,count_nonverbatim,count_qa,score_rouge_l,score_rouge_l>=0.8,events_recall,events_recall>=5,char_recall,char_recall>=3,score_f1,verbatim_quality_score,nonverbatim_quality_score
+yes,gpt-35-turbo,greedy,2274,1770,589,0.1840055085,2.022867194,0.5316384181,1.355932203,0.1836158192,1.412429379,36.09021864,3.49648197,4.340112994
+yes,gpt-4-turbo,greedy,2274,1730,589,0.1579340721,0.4397537379,0.8560693642,2.947976879,0.4398843931,4.50867052,41.9088674,3.940193492,4.667052023
+yes,llama2-13b-chat-hf,greedy,2274,1770,589,0.1259847233,0,0.2271186441,0.2259887006,0.106779661,0.5649717514,17.18724202,3.922163588,4.201694915
+yes,llama2-13b-hf,greedy,2274,1770,589,0.1487607591,0.08795074758,0.3169491525,0.3389830508,0.2542372881,2.033898305,20.94628725,2.514951627,3.020903955
+yes,llama2-13b-hf,memfree,2274,1770,589,0.1470236149,0,0.3146892655,0.3389830508,0.2446327684,2.033898305,20.94628725,2.551890941,3.049717514
+yes,llama2-13b-hf,system,2274,1770,589,0.1489617194,0.04397537379,0.3367231638,0.4519774011,0.2423728814,2.033898305,19.79607546,2.576077397,3.123163842
+yes,llama2-13b-vicuna,greedy,2274,1770,589,0.1419072826,0.08795074758,0.4824858757,0.4519774011,0.186440678,1.412429379,16.18073258,3.649956025,4.176271186
+yes,llama2-70b,greedy,2274,1770,589,0.198620695,2.418645558,0.8903954802,4.011299435,0.7485875706,10.33898305,30.1233411,2.803869833,3.346892655
+yes,llama2-70b,memfree,2274,1770,589,0.1751059825,0.3078276165,0.8903954802,3.84180791,0.7519774011,10.9039548,30.1233411,2.76121372,3.341242938
+yes,llama2-70b,system,2274,1770,589,0.2003116714,2.594547054,0.9146892655,4.745762712,0.7734463277,11.52542373,29.9026073,2.750659631,3.355932203
+yes,llama2-70b-chat,greedy,2274,1770,589,0.1468163176,0.1319261214,0.4016949153,0.7344632768,0.1644067797,1.129943503,21.19026512,3.627968338,4.156497175
+yes,llama2-7b,greedy,2274,1770,589,0.1435181828,0.1319261214,0.297740113,0.2259887006,0.213559322,1.694915254,15.34213034,2.380386983,2.85819209
+yes,llama3-70b,greedy,2274,1770,589,0.3042579322,10.51011434,1.176836158,6.892655367,1.076271186,15.59322034,39.98167839,2.708003518,3.206779661
+yes,llama3-70b,memfree,2274,1770,589,0.2223630689,0.6156552331,1.215254237,7.231638418,1.074576271,15.53672316,39.98167839,2.666666667,3.196045198
+yes,llama3-70b,system,2274,1770,589,0.308713149,11.03781882,1.15480226,5.93220339,1.038418079,15.02824859,39.92419107,2.736147757,3.276271186
+yes,llama3-70b-instruct,greedy,2274,1770,589,0.1338709257,0.219876869,0.4344632768,1.242937853,0.4276836158,4.237288136,30.20756187,3.237906772,4.404519774
+yes,llama3-8b,greedy,2274,1770,589,0.1498831988,0.1759014952,0.6531073446,2.316384181,0.3949152542,4.463276836,18.60886463,2.576956904,2.737288136
+yes,mistral-7b,greedy,2274,1770,589,0.1477934219,0.1319261214,0.3576271186,0.395480226,0.2299435028,1.920903955,18.71270589,2.279683377,2.796045198
+yes,mixtral-8x7b,greedy,2274,1770,589,0.1561011593,0.9674582234,0.5344632768,1.299435028,0.5536723164,6.949152542,23.32206589,2.981530343,3.537853107
+yes,mixtral-8x7b-instruct,greedy,2274,1770,589,0.1316051003,0.08795074758,0.7254237288,1.97740113,0.3474576271,2.937853107,21.27583658,3.420844327,4.255932203
+yes,tulu2-13b,greedy,2274,1770,589,0.1306359884,0,0.506779661,0.6214689266,0.2474576271,1.581920904,17.89834888,2.931838171,4.005649718
+yes,tulu2-13b-dpo,greedy,2274,1770,589,0.1383527819,0.08795074758,0.618079096,1.525423729,0.288700565,1.751412429,17.32643669,3.448988566,4.196610169
+yes,tulu2-70b,greedy,2274,1770,589,0.1678018825,1.011433597,0.7706214689,2.824858757,0.4395480226,4.632768362,28.32230484,2.921723835,4.019774011
+yes,tulu2-70b,memfree,2274,1770,589,0.1578867035,0.08795074758,0.7734463277,2.881355932,0.4293785311,4.406779661,28.32230484,2.91292876,4.044632768
+yes,tulu2-70b,system,2274,1770,589,0.1675028708,0.7475813544,0.7559322034,2.033898305,0.3875706215,3.276836158,28.30660473,3.044415128,4.116949153
+yes,tulu2-70b-dpo,greedy,2274,1770,589,0.1738150265,0.3518029903,0.7689265537,2.146892655,0.3672316384,3.389830508,28.836381,3.480650836,4.363276836