update

cli/analysis-cli.py

@@ -3,6 +3,7 @@
 import os
 import sys
 import json
+import pickle
 
 import numpy as np
 
@@ -27,113 +28,292 @@ def find_json_files(json_path):
     return res
 
 
-my_snapshot_download(repo_id=RESULTS_REPO, revision="main", local_dir=EVAL_RESULTS_PATH_BACKEND, repo_type="dataset", max_workers=60)
-my_snapshot_download(repo_id=QUEUE_REPO, revision="main", local_dir=EVAL_REQUESTS_PATH_BACKEND, repo_type="dataset", max_workers=60)
+def sanitise_metric(name: str) -> str:
+    res = name
+    res = res.replace("prompt_level_strict_acc", "Prompt-Level Accuracy")
+    res = res.replace("acc", "Accuracy")
+    res = res.replace("exact_match", "EM")
+    res = res.replace("avg-selfcheckgpt", "AVG")
+    res = res.replace("max-selfcheckgpt", "MAX")
+    res = res.replace("rouge", "ROUGE-")
+    res = res.replace("bertscore_precision", "BERT-P")
+    res = res.replace("exact", "EM")
+    res = res.replace("HasAns_EM", "HasAns")
+    res = res.replace("NoAns_EM", "NoAns")
+    return res
 
-result_path_lst = find_json_files(EVAL_RESULTS_PATH_BACKEND)
-request_path_lst = find_json_files(EVAL_REQUESTS_PATH_BACKEND)
 
-model_name_to_model_map = {}
+def sanitise_dataset(name: str) -> str:
+    res = name
+    res = res.replace("tqa8", "TriviaQA")
+    res = res.replace("nq8", "NQ")
+    res = res.replace("truthfulqa", "TruthfulQA")
+    res = res.replace("ifeval", "IFEval")
+    res = res.replace("selfcheckgpt", "SelfCheckGPT")
+    res = res.replace("truefalse_cieacf", "True-False")
+    res = res.replace("mc", "MC")
+    res = res.replace("race", "RACE")
+    res = res.replace("squad", "SQuAD")
+    res = res.replace("memo-trap", "MemoTrap")
+    res = res.replace("cnndm", "CNN/DM")
+    res = res.replace("xsum", "XSum")
+    res = res.replace("qa", "QA")
+    res = res.replace("summarization", "Summarization")
+    res = res.replace("dialogue", "Dialog")
+    res = res.replace("halueval", "HaluEval")
+    res = res.replace("_", " ")
+    return res
 
-for path in request_path_lst:
-    with open(path, 'r') as f:
-        data = json.load(f)
-    model_name_to_model_map[data["model"]] = data
 
-model_dataset_metric_to_result_map = {}
-data_map = {}
+cache_file = 'data_map_cache.pkl'
 
-for path in result_path_lst:
-    with open(path, 'r') as f:
-        data = json.load(f)
-    model_name = data["config"]["model_name"]
-    for dataset_name, results_dict in data["results"].items():
-        for metric_name, value in results_dict.items():
 
-            # print(model_name, dataset_name, metric_name, value)
+def load_data_map_from_cache(cache_file):
+    if os.path.exists(cache_file):
+        with open(cache_file, 'rb') as f:
+            return pickle.load(f)
+    else:
+        return None
 
-            if ',' in metric_name and '_stderr' not in metric_name \
-                    and 'f1' not in metric_name \
-                    and model_name_to_model_map[model_name]["likes"] > 256:
 
-                to_add = True
+def save_data_map_to_cache(data_map, cache_file):
+    with open(cache_file, 'wb') as f:
+        pickle.dump(data_map, f)
 
-                if 'selfcheck' in dataset_name:
-                    if 'max' not in metric_name:
-                        to_add = False
 
-                if 'nq_open' in dataset_name or 'triviaqa' in dataset_name:
-                    to_add = False
-                    # pass
+# Try to load the data_map from the cache file
+data_map = load_data_map_from_cache(cache_file)
+
+
+if data_map is None:
+    my_snapshot_download(repo_id=RESULTS_REPO, revision="main", local_dir=EVAL_RESULTS_PATH_BACKEND, repo_type="dataset", max_workers=60)
+    my_snapshot_download(repo_id=QUEUE_REPO, revision="main", local_dir=EVAL_REQUESTS_PATH_BACKEND, repo_type="dataset", max_workers=60)
+
+    result_path_lst = find_json_files(EVAL_RESULTS_PATH_BACKEND)
+    request_path_lst = find_json_files(EVAL_REQUESTS_PATH_BACKEND)
 
-                # breakpoint()
+    model_name_to_model_map = {}
 
-                if 'bertscore' in metric_name:
-                    if 'precision' not in metric_name:
+    for path in request_path_lst:
+        with open(path, 'r') as f:
+            data = json.load(f)
+        model_name_to_model_map[data["model"]] = data
+
+    model_dataset_metric_to_result_map = {}
+
+    # data_map[model_name][(dataset_name, sanitised_metric_name)] = value
+    data_map = {}
+
+    for path in result_path_lst:
+        with open(path, 'r') as f:
+            data = json.load(f)
+        model_name = data["config"]["model_name"]
+        for dataset_name, results_dict in data["results"].items():
+            for metric_name, value in results_dict.items():
+
+                # print(model_name, dataset_name, metric_name, value)
+
+                if ',' in metric_name and '_stderr' not in metric_name \
+                        and 'f1' not in metric_name \
+                        and model_name_to_model_map[model_name]["likes"] > 128:
+
+                    to_add = True
+
+                    if 'memo-trap_v2' in dataset_name:
                         to_add = False
 
-                if 'correctness,' in metric_name or 'em,' in metric_name:
-                    to_add = False
+                    if 'selfcheck' in dataset_name:
+                        # if 'max' in metric_name:
+                        #     to_add = False
+                        pass
 
-                if 'rouge' in metric_name:
-                    if 'rougeL' not in metric_name:
+                    if 'faithdial' in dataset_name:
                         to_add = False
 
-                if 'ifeval' in dataset_name:
-                    if 'prompt_level_strict_acc' not in metric_name:
+                    if 'nq_open' in dataset_name or 'triviaqa' in dataset_name:
                         to_add = False
 
-                if 'squad' in dataset_name:
-                    to_add = False
+                    if 'truthfulqa_gen' in dataset_name:
+                        to_add = False
 
-                if 'fever' in dataset_name:
-                    to_add = False
+                    if 'bertscore' in metric_name:
+                        if 'precision' not in metric_name:
+                            to_add = False
+
+                    if 'correctness,' in metric_name or 'em,' in metric_name:
+                        to_add = False
 
-                if 'rouge' in metric_name:
-                    value /= 100.0
+                    if 'rouge' in metric_name:
+                        pass
+                        # if 'rougeL' not in metric_name:
+                        #     to_add = False
 
-                if to_add:
-                    sanitised_metric_name = metric_name.split(',')[0]
-                    model_dataset_metric_to_result_map[(model_name, dataset_name, sanitised_metric_name)] = value
+                    if 'ifeval' in dataset_name:
+                        if 'prompt_level_strict_acc' not in metric_name:
+                            to_add = False
 
-                    # if (model_name, dataset_name) not in data_map:
-                    #     data_map[(model_name, dataset_name)] = {}
-                    # data_map[(model_name, dataset_name)][metric_name] = value
+                    if 'squad' in dataset_name:
+                        # to_add = False
+                        if 'best_exact' in metric_name:
+                            to_add = False
 
-                    if model_name not in data_map:
-                        data_map[model_name] = {}
-                    data_map[model_name][(dataset_name, sanitised_metric_name)] = value
+                    if 'fever' in dataset_name:
+                        to_add = False
 
-                    print('model_name', model_name, 'dataset_name', dataset_name, 'metric_name', metric_name, 'value', value)
+                    if 'xsum' in dataset_name:
+                        # to_add = False
+                        pass
 
-model_name_lst = [m for m in data_map.keys()]
-for m in model_name_lst:
-    if len(data_map[m]) < 8:
-        del data_map[m]
+                    if 'rouge' in metric_name:
+                        value /= 100.0
 
-df = pd.DataFrame.from_dict(data_map, orient='index')
-o_df = df.copy(deep=True)
+                    if 'squad' in dataset_name:
+                        value /= 100.0
 
-print(df)
+                    if to_add:
+                        sanitised_metric_name = sanitise_metric(metric_name.split(',')[0])
+                        sanitised_dataset_name = sanitise_dataset(dataset_name)
 
-# Check for NaN or infinite values and replace them
-df.replace([np.inf, -np.inf], np.nan, inplace=True)  # Replace infinities with NaN
-df.fillna(0, inplace=True)  # Replace NaN with 0 (or use another imputation strategy)
+                        model_dataset_metric_to_result_map[(model_name, sanitised_dataset_name, sanitised_metric_name)] = value
 
-from sklearn.preprocessing import MinMaxScaler
+                        if model_name not in data_map:
+                            data_map[model_name] = {}
+                        data_map[model_name][(sanitised_dataset_name, sanitised_metric_name)] = value
 
-# scaler = MinMaxScaler()
-# df = pd.DataFrame(scaler.fit_transform(df), index=df.index, columns=df.columns)
+                        print('model_name', model_name, 'dataset_name', sanitised_dataset_name, 'metric_name', sanitised_metric_name, 'value', value)
 
-sns.set_context("notebook", font_scale=1.0)
+    save_data_map_to_cache(data_map, cache_file)
 
-# fig = sns.clustermap(df, method='average', metric='cosine', cmap='coolwarm', figsize=(16, 12), annot=True)
-fig = sns.clustermap(df, method='ward', metric='euclidean', cmap='coolwarm', figsize=(16, 12), annot=True, mask=o_df.isnull())
+model_name_lst = [m for m in data_map.keys()]
 
-# Adjust the size of the cells (less wide)
-plt.setp(fig.ax_heatmap.get_yticklabels(), rotation=0)
-plt.setp(fig.ax_heatmap.get_xticklabels(), rotation=90)
+for model_name in model_name_lst:
+    if len(data_map[model_name]) < 14:
+        del data_map[model_name]
 
-# Save the clustermap to file
-fig.savefig('plots/clustermap.pdf')
-fig.savefig('plots/clustermap.png')
+plot_type_lst = ['all', 'summ', 'qa', 'instr', 'detect', 'rc']
+
+for plot_type in plot_type_lst:
+
+    data_map_v2 = {}
+    for model_name in data_map.keys():
+        for dataset_metric in data_map[model_name].keys():
+            if dataset_metric not in data_map_v2:
+                data_map_v2[dataset_metric] = {}
+
+            if plot_type in {'all'}:
+                to_add = True
+                if 'ROUGE' in dataset_metric[1] and 'ROUGE-L' not in dataset_metric[1]:
+                    to_add = False
+                if 'SQuAD' in dataset_metric[0] and 'EM' not in dataset_metric[1]:
+                    to_add = False
+                if 'SelfCheckGPT' in dataset_metric[0] and 'MAX' not in dataset_metric[1]:
+                    to_add = False
+                if to_add is True:
+                    data_map_v2[dataset_metric][model_name] = data_map[model_name][dataset_metric]
+            elif plot_type in {'summ'}:
+                if 'CNN' in dataset_metric[0] or 'XSum' in dataset_metric[0]:
+                    data_map_v2[dataset_metric][model_name] = data_map[model_name][dataset_metric]
+            elif plot_type in {'qa'}:
+                if 'TriviaQA' in dataset_metric[0] or 'NQ' in dataset_metric[0] or 'TruthfulQA' in dataset_metric[0]:
+                    data_map_v2[dataset_metric][model_name] = data_map[model_name][dataset_metric]
+            elif plot_type in {'instr'}:
+                if 'MemoTrap' in dataset_metric[0] or 'IFEval' in dataset_metric[0]:
+                    data_map_v2[dataset_metric][model_name] = data_map[model_name][dataset_metric]
+            elif plot_type in {'detect'}:
+                if 'HaluEval' in dataset_metric[0] or 'SelfCheck' in dataset_metric[0]:
+                    data_map_v2[dataset_metric][model_name] = data_map[model_name][dataset_metric]
+            elif plot_type in {'rc'}:
+                if 'RACE' in dataset_metric[0] or 'SQuAD' in dataset_metric[0]:
+                    data_map_v2[dataset_metric][model_name] = data_map[model_name][dataset_metric]
+            else:
+                assert False, f"Unknown plot type: {plot_type}"
+
+    # df = pd.DataFrame.from_dict(data_map, orient='index')   # Invert the y-axis (rows)
+    df = pd.DataFrame.from_dict(data_map_v2, orient='index')   # Invert the y-axis (rows)
+    df.index = [', '.join(map(str, idx)) for idx in df.index]
+
+    o_df = df.copy(deep=True)
+
+    # breakpoint()
+
+    print(df)
+
+    # Check for NaN or infinite values and replace them
+    df.replace([np.inf, -np.inf], np.nan, inplace=True)  # Replace infinities with NaN
+    df.fillna(0, inplace=True)  # Replace NaN with 0 (or use another imputation strategy)
+
+    from sklearn.preprocessing import MinMaxScaler
+
+    # scaler = MinMaxScaler()
+    # df = pd.DataFrame(scaler.fit_transform(df), index=df.index, columns=df.columns)
+
+    # Calculate dimensions based on the DataFrame size
+    cell_height = 1.0  # Height of each cell in inches
+    cell_width = 1.0   # Width of each cell in inches
+
+    n_rows = len(df.index)  # Datasets and Metrics
+    n_cols = len(df.columns)  # Models
+
+    # Calculate figure size dynamically
+    fig_width = cell_width * n_cols + 0
+    fig_height = cell_height * n_rows + 0
+
+    col_cluster = True
+    row_cluster = True
+
+    sns.set_context("notebook", font_scale=1.3)
+
+    dendrogram_ratio = (.1, .1)
+
+    if plot_type in {'detect'}:
+        fig_width = cell_width * n_cols - 2
+        fig_height = cell_height * n_rows + 5.2
+        dendrogram_ratio = (.1, .2)
+
+    if plot_type in {'instr'}:
+        fig_width = cell_width * n_cols - 2
+        fig_height = cell_height * n_rows + 5.2
+        dendrogram_ratio = (.1, .4)
+
+    if plot_type in {'qa'}:
+        fig_width = cell_width * n_cols - 2
+        fig_height = cell_height * n_rows + 4
+        dendrogram_ratio = (.1, .2)
+
+    if plot_type in {'summ'}:
+        fig_width = cell_width * n_cols - 2
+        fig_height = cell_height * n_rows + 2.0
+        dendrogram_ratio = (.1, .1)
+        row_cluster = False
+
+    if plot_type in {'rc'}:
+        fig_width = cell_width * n_cols - 2
+        fig_height = cell_height * n_rows + 5.2
+        dendrogram_ratio = (.1, .4)
+
+    print('figsize', (fig_width, fig_height))
+
+    print(f'Generating clustermap for {plot_type}')
+
+    # fig = sns.clustermap(df, method='average', metric='cosine', cmap='coolwarm', figsize=(16, 12), annot=True)
+    fig = sns.clustermap(df,
+                         method='ward',
+                         metric='euclidean',
+                         cmap='coolwarm',
+                         figsize=(fig_width, fig_height),  # figsize=(24, 16),
+                         annot=True,
+                         mask=o_df.isnull(),
+                         dendrogram_ratio=dendrogram_ratio,
+                         fmt='.2f',
+                         col_cluster=col_cluster,
+                         row_cluster=row_cluster)
+
+    # Adjust the size of the cells (less wide)
+    plt.setp(fig.ax_heatmap.get_yticklabels(), rotation=0)
+    plt.setp(fig.ax_heatmap.get_xticklabels(), rotation=90)
+
+    # Save the clustermap to file
+    fig.savefig(f'plots/clustermap_{plot_type}.pdf')
+    fig.savefig(f'plots/clustermap_{plot_type}.png')
+
+    o_df.to_json(f'plots/clustermap_{plot_type}.json', orient='split')

plots/clustermap_all.json

@@ -1 +1 @@
-{"columns":["TheBloke\/Llama-2-13B-chat-GPTQ","TheBloke\/Llama-2-7B-Chat-GPTQ","TheBloke\/Wizard-Vicuna-13B-Uncensored-GPTQ","teknium\/OpenHermes-2-Mistral-7B","mistralai\/Mistral-7B-Instruct-v0.2","mistralai\/Mistral-7B-Instruct-v0.1","bigscience\/bloom-7b1","bigscience\/bloom-560m","berkeley-nest\/Starling-LM-7B-alpha","EleutherAI\/gpt-neo-125m","EleutherAI\/gpt-neo-2.7B","EleutherAI\/gpt-j-6b","EleutherAI\/gpt-neo-1.3B","Gryphe\/MythoMax-L2-13b","Open-Orca\/Mistral-7B-OpenOrca","pankajmathur\/orca_mini_3b","KoboldAI\/OPT-13B-Erebus","ehartford\/dolphin-2.1-mistral-7b","togethercomputer\/LLaMA-2-7B-32K","togethercomputer\/GPT-JT-6B-v1","togethercomputer\/Llama-2-7B-32K-Instruct","HuggingFaceH4\/zephyr-7b-alpha","HuggingFaceH4\/zephyr-7b-beta","tiiuae\/falcon-7b-instruct","tiiuae\/falcon-7b","ai-forever\/mGPT","NousResearch\/Yarn-Mistral-7b-128k","NousResearch\/Nous-Hermes-Llama2-13b","DiscoResearch\/mixtral-7b-8expert","meta-llama\/Llama-2-7b-chat-hf","meta-llama\/Llama-2-7b-hf","meta-llama\/Llama-2-13b-chat-hf","meta-llama\/Llama-2-13b-hf","upstage\/SOLAR-10.7B-Instruct-v1.0"],"index":["TruthfulQA MC1, Accuracy","SQuADv2, EM","SQuADv2, HasAns","SQuADv2, NoAns","TriviaQA, EM","HaluEval Dialog, Accuracy","XSum, ROUGE-L","XSum, factKB","XSum, BERT-P","MemoTrap, Accuracy","IFEval, Prompt-Level Accuracy","RACE, Accuracy","NQ, EM","TruthfulQA MC2, Accuracy","HaluEval Summarization, Accuracy","True-False, Accuracy","CNN\/DM, ROUGE-L","CNN\/DM, factKB","CNN\/DM, BERT-P","HaluEval QA, Accuracy","SelfCheckGPT, AVG"],"data":[[0.2656058752,0.2900856793,0.358629131,0.3390452876,0.5250917993,0.3916768666,0.2239902081,0.2447980416,0.3157894737,0.2582619339,0.2386780906,0.2019583843,0.2313341493,0.364749082,0.3525091799,0.2802937576,0.205630355,0.3904528764,0.2558139535,0.2264381885,0.3096695226,0.4063647491,0.3867809058,0.2876376989,0.2239902081,0.2325581395,0.2741738066,0.3476132191,0.247246022,0.3023255814,0.2521419829,0.2802937576,0.2594859241,null],[0.1329908195,0.1431820096,0.1281900109,null,0.3019455908,null,0.2228585867,0.0799292512,0.3982986608,0.0476711867,0.1752716247,0.2339762486,0.1510991325,0.1514360313,0.3049776805,0.2034026783,0.2296807883,0.3536595637,0.1234734271,0.3176956119,0.139560347,0.3088520172,0.3112103091,0.2263117999,0.2642129201,0.1662595806,null,0.257811842,0.0,0.1199359892,0.1446138297,0.1327381454,0.1591004801,null],[0.0811403509,0.0718623482,0.0558367072,null,0.604757085,null,0.4461875843,0.1589068826,0.7967273954,0.0755735493,0.3500337382,0.467780027,0.3021255061,0.0733805668,0.6108299595,0.407219973,0.4586707152,0.7083333333,0.0632591093,0.6363022942,0.0841767881,0.6185897436,0.6233130904,0.4531039136,0.5291835358,0.000168691,null,0.5163630229,0.0,0.0657894737,0.0566801619,0.0796221323,0.0775978408,null],[0.1846930193,0.2142977292,0.2003364172,null,0.0,null,0.0001682086,0.0011774601,0.0010092515,0.0198486123,0.0010092515,0.0008410429,0.0005046257,0.2292682927,0.0,0.0001682086,0.0013456686,0.0,0.1835155593,0.0,0.1947855341,0.0,0.0,0.0001682086,0.0,0.3318755257,null,0.0,0.0,0.1739276703,0.2322960471,0.1857022708,0.2403700589,null],[0.0947949175,0.0817543469,0.0961324119,0.6805060187,0.6389322336,0.5224030317,0.2633749443,0.0570664289,0.6594962104,0.0155483727,0.2011257245,0.3931676326,0.1415514935,0.0974141774,0.6583816317,0.3750557289,0.3940592956,0.6674654481,0.0815871601,0.4172982613,0.0927329469,0.6591618368,0.6443379403,0.3915514935,0.5866584931,0.1061078912,0.7003455194,0.0984730272,0.0,0.0883303611,0.0921756576,0.0978600089,0.0948506465,0.4198060633],[0.5928,0.6085,0.6471,null,null,0.6649,0.4625,0.4998,0.6674,0.472,0.4772,0.4984,0.4836,0.7173,0.7699,0.4694,0.3997,0.7963,0.5478,0.4979,0.6043,0.7917,0.7634,0.3878,0.4203,0.0001,0.558,0.7326,0.0712,0.6425,0.4997,0.6548,0.7393,null],[0.0371901778,0.0347891843,0.0428959698,null,null,null,0.1668276326,0.1356427068,0.0504142569,0.1262087692,0.1205109613,0.2136831021,0.1487592997,0.0384377825,null,0.1854881243,0.2370092437,null,0.0432590646,0.2647281333,0.042540476,null,null,0.1822281713,0.1657837663,0.0141983599,null,null,null,0.0340250019,0.0445139517,0.0359765055,0.0413856309,0.0011478244],[0.0401970892,0.0394161696,0.0428647574,null,null,null,0.5674834215,0.2298042738,0.0397678158,0.2459031195,0.3441669812,0.4791825971,0.4144174002,0.0384018147,null,0.5666702185,0.4707080535,null,0.0407451505,0.3412336695,0.0400569668,null,null,0.4089209967,0.3192473228,0.1421243598,null,null,null,0.0379350583,0.0428665575,0.0387781905,0.0411868449,0.1811100146],[0.3949103208,0.3837605404,0.4030390077,null,null,null,0.6528773697,0.6049370656,0.4270770697,0.5845326816,0.4448599865,0.6811507025,0.6106414046,0.3989033275,null,0.6324491786,0.709515113,null,0.4014707047,0.7352085092,0.3991319337,null,null,0.6545591434,0.5731293539,0.4255551427,null,null,null,0.3853941111,0.4050690645,0.3917698265,0.401477077,0.0021477235],[0.641025641,0.7179487179,0.5886752137,0.6079059829,0.5405982906,0.7061965812,0.6826923077,0.860042735,0.6314102564,0.8344017094,0.7756410256,0.7574786325,0.7980769231,0.6463675214,0.6346153846,0.594017094,0.7532051282,0.5897435897,0.561965812,0.6645299145,0.5758547009,0.5352564103,0.5854700855,0.858974359,0.7126068376,0.8643162393,0.5641025641,0.5523504274,0.5737179487,0.733974359,0.6143162393,0.6079059829,0.5758547009,null],[0.2735674677,0.2606284658,0.1626617375,0.2255083179,0.3844731978,0.3049907579,0.0868761553,0.0850277264,0.2310536044,0.1293900185,0.1885397412,0.179297597,0.1423290203,0.2402957486,0.033271719,0.0628465804,null,0.2735674677,0.1497227357,0.146025878,0.1700554529,0.0609981516,0.0924214418,0.1534195933,0.1164510166,0.1940850277,null,0.1423290203,0.1423290203,0.2865064695,0.1866913124,0.314232902,0.1829944547,null],[0.4574162679,0.4220095694,0.4325358852,0.4392344498,0.4593301435,0.4229665072,0.3655502392,0.3023923445,0.4688995215,0.2755980861,0.35215311,0.376076555,0.3406698565,0.433492823,0.4717703349,0.3674641148,0.3827751196,0.4555023923,0.3770334928,0.3645933014,0.4,0.4641148325,0.4583732057,0.3722488038,0.3741626794,0.2937799043,0.4076555024,0.4593301435,0.2220095694,0.4373205742,0.395215311,0.4612440191,0.404784689,0.419138756],[0.0263157895,0.0263157895,0.0232686981,0.0335180055,0.0313019391,0.0249307479,0.0329639889,0.0102493075,0.0343490305,0.0049861496,0.0542936288,0.0916897507,0.0368421053,0.028531856,0.0293628809,0.0265927978,0.1307479224,0.0293628809,0.0238227147,0.1091412742,0.0271468144,0.0304709141,0.0315789474,0.135734072,0.2207756233,0.0232686981,null,0.0254847645,0.0,0.0252077562,0.0268698061,0.0268698061,0.0274238227,0.1991689751],[0.4167499124,0.4410061226,0.5164091712,0.509255685,0.6681645582,0.5592109222,0.3889466583,0.4243149954,0.4731016618,0.4557936883,0.3986263303,0.3595710074,0.3961377938,0.515367679,0.5225657507,0.423037498,0.352115369,0.558968896,0.3841009802,0.3706818154,0.4572778615,0.5602234073,0.5511952533,0.4407667557,0.3426523695,0.3962402525,0.4225232911,0.5026754146,0.4947679694,0.4531160226,0.389651281,0.4394613382,0.3689257684,null],[0.4645,0.4193,0.4436,0.5464,0.4465,0.4504,0.4652,0.4653,0.5459,0.4651,0.4668,0.4658,0.4457,0.476,0.5147,0.4701,0.4536,0.448,0.4904,0.5224,0.4696,0.5268,0.5238,0.4402,0.448,0.0,0.4588,null,0.0774,0.4906,0.4279,0.4772,null,0.5574],[0.8534100247,0.7733771569,0.8087099425,0.8895645029,0.8905505341,0.8348397699,0.5314708299,0.5041906327,0.8917009039,0.4940016434,0.5059983566,0.5413311422,0.507641742,0.8698438784,0.8793755136,0.5860312243,0.5393590797,0.883483977,0.8059161873,0.6271158587,0.8195562859,0.8854560394,0.8323746919,0.6364831553,0.5814297453,0.4926869351,0.8376335251,0.8670501233,0.5064913722,0.8023007395,0.7268693509,0.8514379622,0.8315529992,0.8933442892],[0.0132261781,0.0098347434,0.012722468,0.0114292948,null,0.008927303,0.2075387019,0.1227088127,0.0169222534,0.1243996336,0.1958355522,0.2238202254,0.2016505067,0.0135334171,0.0157445278,0.2242330745,0.2130128961,0.0142701427,0.0133793406,0.2408143362,0.012671213,0.0117323751,0.0111061484,0.1882467392,0.1691898288,0.0164863838,0.0116271987,0.0131859896,0.0000716868,0.0103604417,0.0145397085,null,0.0135674045,0.0006113776],[0.1686613542,0.2305715843,0.1762471835,0.1795055867,null,0.1750336135,0.9249732766,0.7988642532,0.2070823135,0.7133009049,0.9058066799,0.9396594147,0.8739379747,0.1648057051,0.2233354576,0.8669051787,0.9215527018,0.1965546069,0.1575508605,0.94858605,0.1617593629,0.1759309876,0.1893680342,0.8267075767,0.901661868,0.7995222351,0.166116994,0.1795224981,0.0805047156,0.1580946885,0.1517425501,null,0.155634531,0.9509124595],[0.3668251897,0.3243336913,0.3548213557,0.3652777882,null,0.3544185533,0.6009727172,0.4646713339,0.3964162779,0.4789093344,0.5761275867,0.617234758,0.5888279105,0.3663381487,0.3898203604,0.6159694987,0.6594958169,0.3785245521,0.3663761784,0.7087181979,0.3645764744,0.3628082484,0.3673437638,0.5926767984,0.5112991874,0.4542439283,0.3637139385,0.3722801591,0.3306992617,0.3566615503,0.367965746,null,0.3640197324,0.0013591523],[0.5454,0.4519,0.5206,0.6605,0.23,0.4917,0.5806,0.4995,0.5969,0.4653,0.4376,0.5139,0.4625,0.3992,0.4502,0.4446,0.3526,0.4208,0.4555,0.5093,0.3233,0.6235,0.5185,0.2968,0.4672,0.0549,0.5699,0.5715,0.0708,0.5231,0.4566,0.5728,0.6879,null],[0.0900088111,0.0378151261,0.1105999164,0.0288242793,0.0767584532,0.0042016807,0.012605042,0.063491636,0.0504201681,0.0865653082,0.0168067227,0.0042016807,0.0885709807,0.0782453898,0.987394958,0.0336183781,0.0797089047,0.0358374659,0.3529411765,0.012605042,0.1020439002,0.0210084034,0.0758733581,0.0291536913,0.0210084034,0.0084033613,null,0.1206660487,0.6692579906,0.0413645344,0.1043527865,0.0,null,null]]}
+{"columns":["TheBloke\/Llama-2-13B-chat-GPTQ","TheBloke\/Llama-2-7B-Chat-GPTQ","TheBloke\/Wizard-Vicuna-13B-Uncensored-GPTQ","teknium\/OpenHermes-2-Mistral-7B","teknium\/OpenHermes-2.5-Mistral-7B","mistralai\/Mistral-7B-Instruct-v0.2","mistralai\/Mistral-7B-Instruct-v0.1","bigscience\/bloom-7b1","bigscience\/bloom-560m","berkeley-nest\/Starling-LM-7B-alpha","EleutherAI\/gpt-neo-125m","EleutherAI\/gpt-neo-2.7B","EleutherAI\/gpt-j-6b","EleutherAI\/gpt-neo-1.3B","Gryphe\/MythoMax-L2-13b","Open-Orca\/Mistral-7B-OpenOrca","pankajmathur\/orca_mini_3b","KoboldAI\/OPT-13B-Erebus","ehartford\/dolphin-2.1-mistral-7b","togethercomputer\/LLaMA-2-7B-32K","togethercomputer\/GPT-JT-6B-v1","togethercomputer\/Llama-2-7B-32K-Instruct","HuggingFaceH4\/zephyr-7b-alpha","HuggingFaceH4\/zephyr-7b-beta","tiiuae\/falcon-7b-instruct","tiiuae\/falcon-7b","ai-forever\/mGPT","NousResearch\/Yarn-Mistral-7b-128k","NousResearch\/Nous-Hermes-Llama2-13b","DiscoResearch\/mixtral-7b-8expert","meta-llama\/Llama-2-7b-chat-hf","meta-llama\/Llama-2-7b-hf","meta-llama\/Llama-2-13b-chat-hf","meta-llama\/Llama-2-13b-hf","upstage\/SOLAR-10.7B-Instruct-v1.0"],"index":["TruthfulQA MC1, Accuracy","SQuADv2, EM","TriviaQA, EM","HaluEval Dialog, Accuracy","XSum, ROUGE-L","XSum, factKB","XSum, BERT-P","MemoTrap, Accuracy","IFEval, Prompt-Level Accuracy","RACE, Accuracy","NQ, EM","TruthfulQA MC2, Accuracy","HaluEval Summarization, Accuracy","True-False, Accuracy","CNN\/DM, ROUGE-L","CNN\/DM, factKB","CNN\/DM, BERT-P","HaluEval QA, Accuracy","SelfCheckGPT, MAX","CNN\/DM v2, ROUGE-L","CNN\/DM v2, factKB","CNN\/DM v2, BERT-P","XSum v2, ROUGE-L","XSum v2, factKB","XSum v2, BERT-P"],"data":[[0.2656058752,0.2900856793,0.358629131,0.3390452876,0.3598531212,0.5250917993,0.3916768666,0.2239902081,0.2447980416,0.3157894737,0.2582619339,0.2386780906,0.2019583843,0.2313341493,0.364749082,0.3525091799,0.2802937576,0.205630355,0.3904528764,0.2558139535,0.2264381885,0.3096695226,0.4063647491,0.3867809058,0.2876376989,0.2239902081,0.2325581395,0.2741738066,0.3476132191,0.247246022,0.3023255814,0.2521419829,0.2802937576,0.2594859241,null],[0.1329908195,0.1431820096,0.1281900109,null,0.0681377916,0.3019455908,null,0.2228585867,0.0799292512,0.3982986608,0.0476711867,0.1752716247,0.2339762486,0.1510991325,0.1514360313,0.3049776805,0.2034026783,0.2296807883,0.3536595637,0.1234734271,0.3176956119,0.139560347,0.3088520172,0.3112103091,0.2263117999,0.2642129201,0.1662595806,null,0.257811842,0.0,0.1199359892,0.1446138297,0.1327381454,0.1591004801,null],[0.0947949175,0.0817543469,0.0961324119,0.6805060187,null,0.6389322336,0.5224030317,0.2633749443,0.0570664289,0.6594962104,0.0155483727,0.2011257245,0.3931676326,0.1415514935,0.0974141774,0.6583816317,0.3750557289,0.3940592956,0.6674654481,0.0815871601,0.4172982613,0.0927329469,0.6591618368,0.6443379403,0.3915514935,0.5866584931,0.1061078912,0.7003455194,0.0984730272,0.0,0.0883303611,0.0921756576,0.0978600089,0.0948506465,0.4198060633],[0.5928,0.6085,0.6471,null,0.7826,null,0.6649,0.4625,0.4998,0.6674,0.472,0.4772,0.4984,0.4836,0.7173,0.7699,0.4694,0.3997,0.7963,0.5478,0.4979,0.6043,0.7917,0.7634,0.3878,0.4203,0.0001,0.558,0.7326,0.0712,0.6425,0.4997,0.6548,0.7393,null],[0.0371901778,0.0347891843,0.0428959698,null,null,null,null,0.1668276326,0.1356427068,0.0504142569,0.1262087692,0.1205109613,0.2136831021,0.1487592997,0.0384377825,null,0.1854881243,0.2370092437,null,0.0432590646,0.2647281333,0.042540476,null,null,0.1822281713,0.1657837663,0.0141983599,null,null,null,0.0340250019,0.0445139517,0.0359765055,0.0413856309,0.0011478244],[0.0401970892,0.0394161696,0.0428647574,null,null,null,null,0.5674834215,0.2298042738,0.0397678158,0.2459031195,0.3441669812,0.4791825971,0.4144174002,0.0384018147,null,0.5666702185,0.4707080535,null,0.0407451505,0.3412336695,0.0400569668,null,null,0.4089209967,0.3192473228,0.1421243598,null,null,null,0.0379350583,0.0428665575,0.0387781905,0.0411868449,0.1811100146],[0.3949103208,0.3837605404,0.4030390077,null,null,null,null,0.6528773697,0.6049370656,0.4270770697,0.5845326816,0.4448599865,0.6811507025,0.6106414046,0.3989033275,null,0.6324491786,0.709515113,null,0.4014707047,0.7352085092,0.3991319337,null,null,0.6545591434,0.5731293539,0.4255551427,null,null,null,0.3853941111,0.4050690645,0.3917698265,0.401477077,0.0021477235],[0.641025641,0.7179487179,0.5886752137,0.6079059829,0.6388888889,0.5405982906,0.7061965812,0.6826923077,0.860042735,0.6314102564,0.8344017094,0.7756410256,0.7574786325,0.7980769231,0.6463675214,0.6346153846,0.594017094,0.7532051282,0.5897435897,0.561965812,0.6645299145,0.5758547009,0.5352564103,0.5854700855,0.858974359,0.7126068376,0.8643162393,0.5641025641,0.5523504274,0.5737179487,0.733974359,0.6143162393,0.6079059829,0.5758547009,null],[0.2735674677,0.2606284658,0.1626617375,0.2255083179,null,0.3844731978,0.3049907579,0.0868761553,0.0850277264,0.2310536044,0.1293900185,0.1885397412,0.179297597,0.1423290203,0.2402957486,0.033271719,0.0628465804,null,0.2735674677,0.1497227357,0.146025878,0.1700554529,0.0609981516,0.0924214418,0.1534195933,0.1164510166,0.1940850277,null,0.1423290203,0.1423290203,0.2865064695,0.1866913124,0.314232902,0.1829944547,null],[0.4574162679,0.4220095694,0.4325358852,0.4392344498,0.44784689,0.4593301435,0.4229665072,0.3655502392,0.3023923445,0.4688995215,0.2755980861,0.35215311,0.376076555,0.3406698565,0.433492823,0.4717703349,0.3674641148,0.3827751196,0.4555023923,0.3770334928,0.3645933014,0.4,0.4641148325,0.4583732057,0.3722488038,0.3741626794,0.2937799043,0.4076555024,0.4593301435,0.2220095694,0.4373205742,0.395215311,0.4612440191,0.404784689,0.419138756],[0.0263157895,0.0263157895,0.0232686981,0.0335180055,0.0349030471,0.0313019391,0.0249307479,0.0329639889,0.0102493075,0.0343490305,0.0049861496,0.0542936288,0.0916897507,0.0368421053,0.028531856,0.0293628809,0.0265927978,0.1307479224,0.0293628809,0.0238227147,0.1091412742,0.0271468144,0.0304709141,0.0315789474,0.135734072,0.2207756233,0.0232686981,null,0.0254847645,0.0,0.0252077562,0.0268698061,0.0268698061,0.0274238227,0.1991689751],[0.4167499124,0.4410061226,0.5164091712,0.509255685,0.530496424,0.6681645582,0.5592109222,0.3889466583,0.4243149954,0.4731016618,0.4557936883,0.3986263303,0.3595710074,0.3961377938,0.515367679,0.5225657507,0.423037498,0.352115369,0.558968896,0.3841009802,0.3706818154,0.4572778615,0.5602234073,0.5511952533,0.4407667557,0.3426523695,0.3962402525,0.4225232911,0.5026754146,0.4947679694,0.4531160226,0.389651281,0.4394613382,0.3689257684,null],[0.4645,0.4193,0.4436,0.5464,0.5909,0.4465,0.4504,0.4652,0.4653,0.5459,0.4651,0.4668,0.4658,0.4457,0.476,0.5147,0.4701,0.4536,0.448,0.4904,0.5224,0.4696,0.5268,0.5238,0.4402,0.448,0.0,0.4588,null,0.0774,0.4906,0.4279,0.4772,null,0.5574],[0.8534100247,0.7733771569,0.8087099425,0.8895645029,0.8879211175,0.8905505341,0.8348397699,0.5314708299,0.5041906327,0.8917009039,0.4940016434,0.5059983566,0.5413311422,0.507641742,0.8698438784,0.8793755136,0.5860312243,0.5393590797,0.883483977,0.8059161873,0.6271158587,0.8195562859,0.8854560394,0.8323746919,0.6364831553,0.5814297453,0.4926869351,0.8376335251,0.8670501233,0.5064913722,0.8023007395,0.7268693509,0.8514379622,0.8315529992,0.8933442892],[0.0132261781,0.0098347434,0.012722468,0.0114292948,null,null,0.008927303,0.2075387019,0.1227088127,0.0169222534,0.1243996336,0.1958355522,0.2238202254,0.2016505067,0.0135334171,0.0157445278,0.2242330745,0.2130128961,0.0142701427,0.0133793406,0.2408143362,0.012671213,0.0117323751,0.0111061484,0.1882467392,0.1691898288,0.0164863838,0.0116271987,0.0131859896,0.0000716868,0.0103604417,0.0145397085,null,0.0135674045,0.0006113776],[0.1686613542,0.2305715843,0.1762471835,0.1795055867,null,null,0.1750336135,0.9249732766,0.7988642532,0.2070823135,0.7133009049,0.9058066799,0.9396594147,0.8739379747,0.1648057051,0.2233354576,0.8669051787,0.9215527018,0.1965546069,0.1575508605,0.94858605,0.1617593629,0.1759309876,0.1893680342,0.8267075767,0.901661868,0.7995222351,0.166116994,0.1795224981,0.0805047156,0.1580946885,0.1517425501,null,0.155634531,0.9509124595],[0.3668251897,0.3243336913,0.3548213557,0.3652777882,null,null,0.3544185533,0.6009727172,0.4646713339,0.3964162779,0.4789093344,0.5761275867,0.617234758,0.5888279105,0.3663381487,0.3898203604,0.6159694987,0.6594958169,0.3785245521,0.3663761784,0.7087181979,0.3645764744,0.3628082484,0.3673437638,0.5926767984,0.5112991874,0.4542439283,0.3637139385,0.3722801591,0.3306992617,0.3566615503,0.367965746,null,0.3640197324,0.0013591523],[0.5454,0.4519,0.5206,0.6605,0.5135,0.23,0.4917,0.5806,0.4995,0.5969,0.4653,0.4376,0.5139,0.4625,0.3992,0.4502,0.4446,0.3526,0.4208,0.4555,0.5093,0.3233,0.6235,0.5185,0.2968,0.4672,0.0549,0.5699,0.5715,0.0708,0.5231,0.4566,0.5728,0.6879,null],[0.2447584892,0.281512605,0.2558918005,0.1120163592,0.1324451679,0.2752668233,0.1512605042,0.3277310924,0.2040760759,0.2941176471,0.2339250687,0.2394957983,0.2058823529,0.2829557667,0.2295219446,0.987394958,0.1199278912,0.3158274114,0.1444317716,0.4453781513,0.2352941176,0.2793721332,0.1848739496,0.2734539158,0.076986247,0.1974789916,0.1554621849,null,0.2455076835,0.8670519793,0.151334934,0.2598217688,0.0588235294,null,null],[null,null,null,null,null,null,null,null,null,null,null,0.1559188347,null,0.1900936275,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],[null,null,null,null,null,null,null,null,null,null,null,0.9662616708,null,0.9704224166,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],[null,null,null,null,null,null,null,null,null,null,null,0.352680524,null,0.4360266906,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,0.1185889375,null,null,null,null,null,null,null,null,null,null],[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,0.6746885531,null,null,null,null,null,null,null,null,null,null],[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,0.3937310434,null,null,null,null,null,null,null,null,null,null]]}

plots/clustermap_detect.json

@@ -1 +1 @@
-{"columns":["TheBloke\/Llama-2-13B-chat-GPTQ","TheBloke\/Llama-2-7B-Chat-GPTQ","TheBloke\/Wizard-Vicuna-13B-Uncensored-GPTQ","mistralai\/Mistral-7B-Instruct-v0.1","bigscience\/bloom-7b1","bigscience\/bloom-560m","berkeley-nest\/Starling-LM-7B-alpha","EleutherAI\/gpt-neo-125m","EleutherAI\/gpt-neo-2.7B","EleutherAI\/gpt-j-6b","EleutherAI\/gpt-neo-1.3B","Gryphe\/MythoMax-L2-13b","Open-Orca\/Mistral-7B-OpenOrca","pankajmathur\/orca_mini_3b","KoboldAI\/OPT-13B-Erebus","ehartford\/dolphin-2.1-mistral-7b","togethercomputer\/LLaMA-2-7B-32K","togethercomputer\/GPT-JT-6B-v1","togethercomputer\/Llama-2-7B-32K-Instruct","HuggingFaceH4\/zephyr-7b-alpha","HuggingFaceH4\/zephyr-7b-beta","tiiuae\/falcon-7b-instruct","tiiuae\/falcon-7b","ai-forever\/mGPT","NousResearch\/Yarn-Mistral-7b-128k","NousResearch\/Nous-Hermes-Llama2-13b","DiscoResearch\/mixtral-7b-8expert","meta-llama\/Llama-2-7b-chat-hf","meta-llama\/Llama-2-7b-hf","meta-llama\/Llama-2-13b-chat-hf","meta-llama\/Llama-2-13b-hf","teknium\/OpenHermes-2-Mistral-7B","mistralai\/Mistral-7B-Instruct-v0.2","upstage\/SOLAR-10.7B-Instruct-v1.0"],"index":["HaluEval Dialog, Accuracy","HaluEval Summarization, Accuracy","HaluEval QA, Accuracy","SelfCheckGPT, AVG"],"data":[[0.5928,0.6085,0.6471,0.6649,0.4625,0.4998,0.6674,0.472,0.4772,0.4984,0.4836,0.7173,0.7699,0.4694,0.3997,0.7963,0.5478,0.4979,0.6043,0.7917,0.7634,0.3878,0.4203,0.0001,0.558,0.7326,0.0712,0.6425,0.4997,0.6548,0.7393,null,null,null],[0.4645,0.4193,0.4436,0.4504,0.4652,0.4653,0.5459,0.4651,0.4668,0.4658,0.4457,0.476,0.5147,0.4701,0.4536,0.448,0.4904,0.5224,0.4696,0.5268,0.5238,0.4402,0.448,0.0,0.4588,null,0.0774,0.4906,0.4279,0.4772,null,0.5464,0.4465,0.5574],[0.5454,0.4519,0.5206,0.4917,0.5806,0.4995,0.5969,0.4653,0.4376,0.5139,0.4625,0.3992,0.4502,0.4446,0.3526,0.4208,0.4555,0.5093,0.3233,0.6235,0.5185,0.2968,0.4672,0.0549,0.5699,0.5715,0.0708,0.5231,0.4566,0.5728,0.6879,0.6605,0.23,null],[0.0900088111,0.0378151261,0.1105999164,0.0042016807,0.012605042,0.063491636,0.0504201681,0.0865653082,0.0168067227,0.0042016807,0.0885709807,0.0782453898,0.987394958,0.0336183781,0.0797089047,0.0358374659,0.3529411765,0.012605042,0.1020439002,0.0210084034,0.0758733581,0.0291536913,0.0210084034,0.0084033613,null,0.1206660487,0.6692579906,0.0413645344,0.1043527865,0.0,null,0.0288242793,0.0767584532,null]]}
+{"columns":["TheBloke\/Llama-2-13B-chat-GPTQ","TheBloke\/Llama-2-7B-Chat-GPTQ","TheBloke\/Wizard-Vicuna-13B-Uncensored-GPTQ","teknium\/OpenHermes-2.5-Mistral-7B","mistralai\/Mistral-7B-Instruct-v0.1","bigscience\/bloom-7b1","bigscience\/bloom-560m","berkeley-nest\/Starling-LM-7B-alpha","EleutherAI\/gpt-neo-125m","EleutherAI\/gpt-neo-2.7B","EleutherAI\/gpt-j-6b","EleutherAI\/gpt-neo-1.3B","Gryphe\/MythoMax-L2-13b","Open-Orca\/Mistral-7B-OpenOrca","pankajmathur\/orca_mini_3b","KoboldAI\/OPT-13B-Erebus","ehartford\/dolphin-2.1-mistral-7b","togethercomputer\/LLaMA-2-7B-32K","togethercomputer\/GPT-JT-6B-v1","togethercomputer\/Llama-2-7B-32K-Instruct","HuggingFaceH4\/zephyr-7b-alpha","HuggingFaceH4\/zephyr-7b-beta","tiiuae\/falcon-7b-instruct","tiiuae\/falcon-7b","ai-forever\/mGPT","NousResearch\/Yarn-Mistral-7b-128k","NousResearch\/Nous-Hermes-Llama2-13b","DiscoResearch\/mixtral-7b-8expert","meta-llama\/Llama-2-7b-chat-hf","meta-llama\/Llama-2-7b-hf","meta-llama\/Llama-2-13b-chat-hf","meta-llama\/Llama-2-13b-hf","teknium\/OpenHermes-2-Mistral-7B","mistralai\/Mistral-7B-Instruct-v0.2","upstage\/SOLAR-10.7B-Instruct-v1.0"],"index":["HaluEval Dialog, Accuracy","HaluEval Summarization, Accuracy","HaluEval QA, Accuracy","SelfCheckGPT, AVG","SelfCheckGPT, MAX"],"data":[[0.5928,0.6085,0.6471,0.7826,0.6649,0.4625,0.4998,0.6674,0.472,0.4772,0.4984,0.4836,0.7173,0.7699,0.4694,0.3997,0.7963,0.5478,0.4979,0.6043,0.7917,0.7634,0.3878,0.4203,0.0001,0.558,0.7326,0.0712,0.6425,0.4997,0.6548,0.7393,null,null,null],[0.4645,0.4193,0.4436,0.5909,0.4504,0.4652,0.4653,0.5459,0.4651,0.4668,0.4658,0.4457,0.476,0.5147,0.4701,0.4536,0.448,0.4904,0.5224,0.4696,0.5268,0.5238,0.4402,0.448,0.0,0.4588,null,0.0774,0.4906,0.4279,0.4772,null,0.5464,0.4465,0.5574],[0.5454,0.4519,0.5206,0.5135,0.4917,0.5806,0.4995,0.5969,0.4653,0.4376,0.5139,0.4625,0.3992,0.4502,0.4446,0.3526,0.4208,0.4555,0.5093,0.3233,0.6235,0.5185,0.2968,0.4672,0.0549,0.5699,0.5715,0.0708,0.5231,0.4566,0.5728,0.6879,0.6605,0.23,null],[0.0900088111,0.0378151261,0.1105999164,0.0401887953,0.0042016807,0.012605042,0.063491636,0.0504201681,0.0865653082,0.0168067227,0.0042016807,0.0885709807,0.0782453898,0.987394958,0.0336183781,0.0797089047,0.0358374659,0.3529411765,0.012605042,0.1020439002,0.0210084034,0.0758733581,0.0291536913,0.0210084034,0.0084033613,null,0.1206660487,0.6692579906,0.0413645344,0.1043527865,0.0,null,0.0288242793,0.0767584532,null],[0.2447584892,0.281512605,0.2558918005,0.1324451679,0.1512605042,0.3277310924,0.2040760759,0.2941176471,0.2339250687,0.2394957983,0.2058823529,0.2829557667,0.2295219446,0.987394958,0.1199278912,0.3158274114,0.1444317716,0.4453781513,0.2352941176,0.2793721332,0.1848739496,0.2734539158,0.076986247,0.1974789916,0.1554621849,null,0.2455076835,0.8670519793,0.151334934,0.2598217688,0.0588235294,null,0.1120163592,0.2752668233,null]]}

plots/clustermap_instr.json

@@ -1 +1 @@
-{"columns":["TheBloke\/Llama-2-13B-chat-GPTQ","TheBloke\/Llama-2-7B-Chat-GPTQ","TheBloke\/Wizard-Vicuna-13B-Uncensored-GPTQ","teknium\/OpenHermes-2-Mistral-7B","mistralai\/Mistral-7B-Instruct-v0.2","mistralai\/Mistral-7B-Instruct-v0.1","bigscience\/bloom-7b1","bigscience\/bloom-560m","berkeley-nest\/Starling-LM-7B-alpha","EleutherAI\/gpt-neo-125m","EleutherAI\/gpt-neo-2.7B","EleutherAI\/gpt-j-6b","EleutherAI\/gpt-neo-1.3B","Gryphe\/MythoMax-L2-13b","Open-Orca\/Mistral-7B-OpenOrca","pankajmathur\/orca_mini_3b","KoboldAI\/OPT-13B-Erebus","ehartford\/dolphin-2.1-mistral-7b","togethercomputer\/LLaMA-2-7B-32K","togethercomputer\/GPT-JT-6B-v1","togethercomputer\/Llama-2-7B-32K-Instruct","HuggingFaceH4\/zephyr-7b-alpha","HuggingFaceH4\/zephyr-7b-beta","tiiuae\/falcon-7b-instruct","tiiuae\/falcon-7b","ai-forever\/mGPT","NousResearch\/Yarn-Mistral-7b-128k","NousResearch\/Nous-Hermes-Llama2-13b","DiscoResearch\/mixtral-7b-8expert","meta-llama\/Llama-2-7b-chat-hf","meta-llama\/Llama-2-7b-hf","meta-llama\/Llama-2-13b-chat-hf","meta-llama\/Llama-2-13b-hf"],"index":["MemoTrap, Accuracy","IFEval, Prompt-Level Accuracy"],"data":[[0.641025641,0.7179487179,0.5886752137,0.6079059829,0.5405982906,0.7061965812,0.6826923077,0.860042735,0.6314102564,0.8344017094,0.7756410256,0.7574786325,0.7980769231,0.6463675214,0.6346153846,0.594017094,0.7532051282,0.5897435897,0.561965812,0.6645299145,0.5758547009,0.5352564103,0.5854700855,0.858974359,0.7126068376,0.8643162393,0.5641025641,0.5523504274,0.5737179487,0.733974359,0.6143162393,0.6079059829,0.5758547009],[0.2735674677,0.2606284658,0.1626617375,0.2255083179,0.3844731978,0.3049907579,0.0868761553,0.0850277264,0.2310536044,0.1293900185,0.1885397412,0.179297597,0.1423290203,0.2402957486,0.033271719,0.0628465804,null,0.2735674677,0.1497227357,0.146025878,0.1700554529,0.0609981516,0.0924214418,0.1534195933,0.1164510166,0.1940850277,null,0.1423290203,0.1423290203,0.2865064695,0.1866913124,0.314232902,0.1829944547]]}
+{"columns":["TheBloke\/Llama-2-13B-chat-GPTQ","TheBloke\/Llama-2-7B-Chat-GPTQ","TheBloke\/Wizard-Vicuna-13B-Uncensored-GPTQ","teknium\/OpenHermes-2-Mistral-7B","teknium\/OpenHermes-2.5-Mistral-7B","mistralai\/Mistral-7B-Instruct-v0.2","mistralai\/Mistral-7B-Instruct-v0.1","bigscience\/bloom-7b1","bigscience\/bloom-560m","berkeley-nest\/Starling-LM-7B-alpha","EleutherAI\/gpt-neo-125m","EleutherAI\/gpt-neo-2.7B","EleutherAI\/gpt-j-6b","EleutherAI\/gpt-neo-1.3B","Gryphe\/MythoMax-L2-13b","Open-Orca\/Mistral-7B-OpenOrca","pankajmathur\/orca_mini_3b","KoboldAI\/OPT-13B-Erebus","ehartford\/dolphin-2.1-mistral-7b","togethercomputer\/LLaMA-2-7B-32K","togethercomputer\/GPT-JT-6B-v1","togethercomputer\/Llama-2-7B-32K-Instruct","HuggingFaceH4\/zephyr-7b-alpha","HuggingFaceH4\/zephyr-7b-beta","tiiuae\/falcon-7b-instruct","tiiuae\/falcon-7b","ai-forever\/mGPT","NousResearch\/Yarn-Mistral-7b-128k","NousResearch\/Nous-Hermes-Llama2-13b","DiscoResearch\/mixtral-7b-8expert","meta-llama\/Llama-2-7b-chat-hf","meta-llama\/Llama-2-7b-hf","meta-llama\/Llama-2-13b-chat-hf","meta-llama\/Llama-2-13b-hf"],"index":["MemoTrap, Accuracy","IFEval, Prompt-Level Accuracy"],"data":[[0.641025641,0.7179487179,0.5886752137,0.6079059829,0.6388888889,0.5405982906,0.7061965812,0.6826923077,0.860042735,0.6314102564,0.8344017094,0.7756410256,0.7574786325,0.7980769231,0.6463675214,0.6346153846,0.594017094,0.7532051282,0.5897435897,0.561965812,0.6645299145,0.5758547009,0.5352564103,0.5854700855,0.858974359,0.7126068376,0.8643162393,0.5641025641,0.5523504274,0.5737179487,0.733974359,0.6143162393,0.6079059829,0.5758547009],[0.2735674677,0.2606284658,0.1626617375,0.2255083179,null,0.3844731978,0.3049907579,0.0868761553,0.0850277264,0.2310536044,0.1293900185,0.1885397412,0.179297597,0.1423290203,0.2402957486,0.033271719,0.0628465804,null,0.2735674677,0.1497227357,0.146025878,0.1700554529,0.0609981516,0.0924214418,0.1534195933,0.1164510166,0.1940850277,null,0.1423290203,0.1423290203,0.2865064695,0.1866913124,0.314232902,0.1829944547]]}

plots/clustermap_qa.json

@@ -1 +1 @@
-{"columns":["TheBloke\/Llama-2-13B-chat-GPTQ","TheBloke\/Llama-2-7B-Chat-GPTQ","TheBloke\/Wizard-Vicuna-13B-Uncensored-GPTQ","teknium\/OpenHermes-2-Mistral-7B","mistralai\/Mistral-7B-Instruct-v0.2","mistralai\/Mistral-7B-Instruct-v0.1","bigscience\/bloom-7b1","bigscience\/bloom-560m","berkeley-nest\/Starling-LM-7B-alpha","EleutherAI\/gpt-neo-125m","EleutherAI\/gpt-neo-2.7B","EleutherAI\/gpt-j-6b","EleutherAI\/gpt-neo-1.3B","Gryphe\/MythoMax-L2-13b","Open-Orca\/Mistral-7B-OpenOrca","pankajmathur\/orca_mini_3b","KoboldAI\/OPT-13B-Erebus","ehartford\/dolphin-2.1-mistral-7b","togethercomputer\/LLaMA-2-7B-32K","togethercomputer\/GPT-JT-6B-v1","togethercomputer\/Llama-2-7B-32K-Instruct","HuggingFaceH4\/zephyr-7b-alpha","HuggingFaceH4\/zephyr-7b-beta","tiiuae\/falcon-7b-instruct","tiiuae\/falcon-7b","ai-forever\/mGPT","NousResearch\/Yarn-Mistral-7b-128k","NousResearch\/Nous-Hermes-Llama2-13b","DiscoResearch\/mixtral-7b-8expert","meta-llama\/Llama-2-7b-chat-hf","meta-llama\/Llama-2-7b-hf","meta-llama\/Llama-2-13b-chat-hf","meta-llama\/Llama-2-13b-hf","upstage\/SOLAR-10.7B-Instruct-v1.0"],"index":["TruthfulQA MC1, Accuracy","TriviaQA, EM","NQ, EM","TruthfulQA MC2, Accuracy"],"data":[[0.2656058752,0.2900856793,0.358629131,0.3390452876,0.5250917993,0.3916768666,0.2239902081,0.2447980416,0.3157894737,0.2582619339,0.2386780906,0.2019583843,0.2313341493,0.364749082,0.3525091799,0.2802937576,0.205630355,0.3904528764,0.2558139535,0.2264381885,0.3096695226,0.4063647491,0.3867809058,0.2876376989,0.2239902081,0.2325581395,0.2741738066,0.3476132191,0.247246022,0.3023255814,0.2521419829,0.2802937576,0.2594859241,null],[0.0947949175,0.0817543469,0.0961324119,0.6805060187,0.6389322336,0.5224030317,0.2633749443,0.0570664289,0.6594962104,0.0155483727,0.2011257245,0.3931676326,0.1415514935,0.0974141774,0.6583816317,0.3750557289,0.3940592956,0.6674654481,0.0815871601,0.4172982613,0.0927329469,0.6591618368,0.6443379403,0.3915514935,0.5866584931,0.1061078912,0.7003455194,0.0984730272,0.0,0.0883303611,0.0921756576,0.0978600089,0.0948506465,0.4198060633],[0.0263157895,0.0263157895,0.0232686981,0.0335180055,0.0313019391,0.0249307479,0.0329639889,0.0102493075,0.0343490305,0.0049861496,0.0542936288,0.0916897507,0.0368421053,0.028531856,0.0293628809,0.0265927978,0.1307479224,0.0293628809,0.0238227147,0.1091412742,0.0271468144,0.0304709141,0.0315789474,0.135734072,0.2207756233,0.0232686981,null,0.0254847645,0.0,0.0252077562,0.0268698061,0.0268698061,0.0274238227,0.1991689751],[0.4167499124,0.4410061226,0.5164091712,0.509255685,0.6681645582,0.5592109222,0.3889466583,0.4243149954,0.4731016618,0.4557936883,0.3986263303,0.3595710074,0.3961377938,0.515367679,0.5225657507,0.423037498,0.352115369,0.558968896,0.3841009802,0.3706818154,0.4572778615,0.5602234073,0.5511952533,0.4407667557,0.3426523695,0.3962402525,0.4225232911,0.5026754146,0.4947679694,0.4531160226,0.389651281,0.4394613382,0.3689257684,null]]}
+{"columns":["TheBloke\/Llama-2-13B-chat-GPTQ","TheBloke\/Llama-2-7B-Chat-GPTQ","TheBloke\/Wizard-Vicuna-13B-Uncensored-GPTQ","teknium\/OpenHermes-2-Mistral-7B","teknium\/OpenHermes-2.5-Mistral-7B","mistralai\/Mistral-7B-Instruct-v0.2","mistralai\/Mistral-7B-Instruct-v0.1","bigscience\/bloom-7b1","bigscience\/bloom-560m","berkeley-nest\/Starling-LM-7B-alpha","EleutherAI\/gpt-neo-125m","EleutherAI\/gpt-neo-2.7B","EleutherAI\/gpt-j-6b","EleutherAI\/gpt-neo-1.3B","Gryphe\/MythoMax-L2-13b","Open-Orca\/Mistral-7B-OpenOrca","pankajmathur\/orca_mini_3b","KoboldAI\/OPT-13B-Erebus","ehartford\/dolphin-2.1-mistral-7b","togethercomputer\/LLaMA-2-7B-32K","togethercomputer\/GPT-JT-6B-v1","togethercomputer\/Llama-2-7B-32K-Instruct","HuggingFaceH4\/zephyr-7b-alpha","HuggingFaceH4\/zephyr-7b-beta","tiiuae\/falcon-7b-instruct","tiiuae\/falcon-7b","ai-forever\/mGPT","NousResearch\/Yarn-Mistral-7b-128k","NousResearch\/Nous-Hermes-Llama2-13b","DiscoResearch\/mixtral-7b-8expert","meta-llama\/Llama-2-7b-chat-hf","meta-llama\/Llama-2-7b-hf","meta-llama\/Llama-2-13b-chat-hf","meta-llama\/Llama-2-13b-hf","upstage\/SOLAR-10.7B-Instruct-v1.0"],"index":["TruthfulQA MC1, Accuracy","TriviaQA, EM","NQ, EM","TruthfulQA MC2, Accuracy"],"data":[[0.2656058752,0.2900856793,0.358629131,0.3390452876,0.3598531212,0.5250917993,0.3916768666,0.2239902081,0.2447980416,0.3157894737,0.2582619339,0.2386780906,0.2019583843,0.2313341493,0.364749082,0.3525091799,0.2802937576,0.205630355,0.3904528764,0.2558139535,0.2264381885,0.3096695226,0.4063647491,0.3867809058,0.2876376989,0.2239902081,0.2325581395,0.2741738066,0.3476132191,0.247246022,0.3023255814,0.2521419829,0.2802937576,0.2594859241,null],[0.0947949175,0.0817543469,0.0961324119,0.6805060187,null,0.6389322336,0.5224030317,0.2633749443,0.0570664289,0.6594962104,0.0155483727,0.2011257245,0.3931676326,0.1415514935,0.0974141774,0.6583816317,0.3750557289,0.3940592956,0.6674654481,0.0815871601,0.4172982613,0.0927329469,0.6591618368,0.6443379403,0.3915514935,0.5866584931,0.1061078912,0.7003455194,0.0984730272,0.0,0.0883303611,0.0921756576,0.0978600089,0.0948506465,0.4198060633],[0.0263157895,0.0263157895,0.0232686981,0.0335180055,0.0349030471,0.0313019391,0.0249307479,0.0329639889,0.0102493075,0.0343490305,0.0049861496,0.0542936288,0.0916897507,0.0368421053,0.028531856,0.0293628809,0.0265927978,0.1307479224,0.0293628809,0.0238227147,0.1091412742,0.0271468144,0.0304709141,0.0315789474,0.135734072,0.2207756233,0.0232686981,null,0.0254847645,0.0,0.0252077562,0.0268698061,0.0268698061,0.0274238227,0.1991689751],[0.4167499124,0.4410061226,0.5164091712,0.509255685,0.530496424,0.6681645582,0.5592109222,0.3889466583,0.4243149954,0.4731016618,0.4557936883,0.3986263303,0.3595710074,0.3961377938,0.515367679,0.5225657507,0.423037498,0.352115369,0.558968896,0.3841009802,0.3706818154,0.4572778615,0.5602234073,0.5511952533,0.4407667557,0.3426523695,0.3962402525,0.4225232911,0.5026754146,0.4947679694,0.4531160226,0.389651281,0.4394613382,0.3689257684,null]]}

plots/clustermap_rc.json

@@ -1 +1 @@
-{"columns":["TheBloke\/Llama-2-13B-chat-GPTQ","TheBloke\/Llama-2-7B-Chat-GPTQ","TheBloke\/Wizard-Vicuna-13B-Uncensored-GPTQ","mistralai\/Mistral-7B-Instruct-v0.2","bigscience\/bloom-7b1","bigscience\/bloom-560m","berkeley-nest\/Starling-LM-7B-alpha","EleutherAI\/gpt-neo-125m","EleutherAI\/gpt-neo-2.7B","EleutherAI\/gpt-j-6b","EleutherAI\/gpt-neo-1.3B","Gryphe\/MythoMax-L2-13b","Open-Orca\/Mistral-7B-OpenOrca","pankajmathur\/orca_mini_3b","KoboldAI\/OPT-13B-Erebus","ehartford\/dolphin-2.1-mistral-7b","togethercomputer\/LLaMA-2-7B-32K","togethercomputer\/GPT-JT-6B-v1","togethercomputer\/Llama-2-7B-32K-Instruct","HuggingFaceH4\/zephyr-7b-alpha","HuggingFaceH4\/zephyr-7b-beta","tiiuae\/falcon-7b-instruct","tiiuae\/falcon-7b","ai-forever\/mGPT","NousResearch\/Nous-Hermes-Llama2-13b","DiscoResearch\/mixtral-7b-8expert","meta-llama\/Llama-2-7b-chat-hf","meta-llama\/Llama-2-7b-hf","meta-llama\/Llama-2-13b-chat-hf","meta-llama\/Llama-2-13b-hf","teknium\/OpenHermes-2-Mistral-7B","mistralai\/Mistral-7B-Instruct-v0.1","NousResearch\/Yarn-Mistral-7b-128k","upstage\/SOLAR-10.7B-Instruct-v1.0"],"index":["SQUADv2, EM","SQUADv2, HasAns","SQUADv2, NoAns","RACE, Accuracy"],"data":[[0.1329908195,0.1431820096,0.1281900109,0.3019455908,0.2228585867,0.0799292512,0.3982986608,0.0476711867,0.1752716247,0.2339762486,0.1510991325,0.1514360313,0.3049776805,0.2034026783,0.2296807883,0.3536595637,0.1234734271,0.3176956119,0.139560347,0.3088520172,0.3112103091,0.2263117999,0.2642129201,0.1662595806,0.257811842,0.0,0.1199359892,0.1446138297,0.1327381454,0.1591004801,null,null,null,null],[0.0811403509,0.0718623482,0.0558367072,0.604757085,0.4461875843,0.1589068826,0.7967273954,0.0755735493,0.3500337382,0.467780027,0.3021255061,0.0733805668,0.6108299595,0.407219973,0.4586707152,0.7083333333,0.0632591093,0.6363022942,0.0841767881,0.6185897436,0.6233130904,0.4531039136,0.5291835358,0.000168691,0.5163630229,0.0,0.0657894737,0.0566801619,0.0796221323,0.0775978408,null,null,null,null],[0.1846930193,0.2142977292,0.2003364172,0.0,0.0001682086,0.0011774601,0.0010092515,0.0198486123,0.0010092515,0.0008410429,0.0005046257,0.2292682927,0.0,0.0001682086,0.0013456686,0.0,0.1835155593,0.0,0.1947855341,0.0,0.0,0.0001682086,0.0,0.3318755257,0.0,0.0,0.1739276703,0.2322960471,0.1857022708,0.2403700589,null,null,null,null],[0.4574162679,0.4220095694,0.4325358852,0.4593301435,0.3655502392,0.3023923445,0.4688995215,0.2755980861,0.35215311,0.376076555,0.3406698565,0.433492823,0.4717703349,0.3674641148,0.3827751196,0.4555023923,0.3770334928,0.3645933014,0.4,0.4641148325,0.4583732057,0.3722488038,0.3741626794,0.2937799043,0.4593301435,0.2220095694,0.4373205742,0.395215311,0.4612440191,0.404784689,0.4392344498,0.4229665072,0.4076555024,0.419138756]]}
+{"columns":["TheBloke\/Llama-2-13B-chat-GPTQ","TheBloke\/Llama-2-7B-Chat-GPTQ","TheBloke\/Wizard-Vicuna-13B-Uncensored-GPTQ","teknium\/OpenHermes-2.5-Mistral-7B","mistralai\/Mistral-7B-Instruct-v0.2","bigscience\/bloom-7b1","bigscience\/bloom-560m","berkeley-nest\/Starling-LM-7B-alpha","EleutherAI\/gpt-neo-125m","EleutherAI\/gpt-neo-2.7B","EleutherAI\/gpt-j-6b","EleutherAI\/gpt-neo-1.3B","Gryphe\/MythoMax-L2-13b","Open-Orca\/Mistral-7B-OpenOrca","pankajmathur\/orca_mini_3b","KoboldAI\/OPT-13B-Erebus","ehartford\/dolphin-2.1-mistral-7b","togethercomputer\/LLaMA-2-7B-32K","togethercomputer\/GPT-JT-6B-v1","togethercomputer\/Llama-2-7B-32K-Instruct","HuggingFaceH4\/zephyr-7b-alpha","HuggingFaceH4\/zephyr-7b-beta","tiiuae\/falcon-7b-instruct","tiiuae\/falcon-7b","ai-forever\/mGPT","NousResearch\/Nous-Hermes-Llama2-13b","DiscoResearch\/mixtral-7b-8expert","meta-llama\/Llama-2-7b-chat-hf","meta-llama\/Llama-2-7b-hf","meta-llama\/Llama-2-13b-chat-hf","meta-llama\/Llama-2-13b-hf","teknium\/OpenHermes-2-Mistral-7B","mistralai\/Mistral-7B-Instruct-v0.1","NousResearch\/Yarn-Mistral-7b-128k","upstage\/SOLAR-10.7B-Instruct-v1.0"],"index":["SQuADv2, EM","SQuADv2, HasAns","SQuADv2, NoAns","RACE, Accuracy"],"data":[[0.1329908195,0.1431820096,0.1281900109,0.0681377916,0.3019455908,0.2228585867,0.0799292512,0.3982986608,0.0476711867,0.1752716247,0.2339762486,0.1510991325,0.1514360313,0.3049776805,0.2034026783,0.2296807883,0.3536595637,0.1234734271,0.3176956119,0.139560347,0.3088520172,0.3112103091,0.2263117999,0.2642129201,0.1662595806,0.257811842,0.0,0.1199359892,0.1446138297,0.1327381454,0.1591004801,null,null,null,null],[0.0811403509,0.0718623482,0.0558367072,0.1364709852,0.604757085,0.4461875843,0.1589068826,0.7967273954,0.0755735493,0.3500337382,0.467780027,0.3021255061,0.0733805668,0.6108299595,0.407219973,0.4586707152,0.7083333333,0.0632591093,0.6363022942,0.0841767881,0.6185897436,0.6233130904,0.4531039136,0.5291835358,0.000168691,0.5163630229,0.0,0.0657894737,0.0566801619,0.0796221323,0.0775978408,null,null,null,null],[0.1846930193,0.2142977292,0.2003364172,0.0,0.0,0.0001682086,0.0011774601,0.0010092515,0.0198486123,0.0010092515,0.0008410429,0.0005046257,0.2292682927,0.0,0.0001682086,0.0013456686,0.0,0.1835155593,0.0,0.1947855341,0.0,0.0,0.0001682086,0.0,0.3318755257,0.0,0.0,0.1739276703,0.2322960471,0.1857022708,0.2403700589,null,null,null,null],[0.4574162679,0.4220095694,0.4325358852,0.44784689,0.4593301435,0.3655502392,0.3023923445,0.4688995215,0.2755980861,0.35215311,0.376076555,0.3406698565,0.433492823,0.4717703349,0.3674641148,0.3827751196,0.4555023923,0.3770334928,0.3645933014,0.4,0.4641148325,0.4583732057,0.3722488038,0.3741626794,0.2937799043,0.4593301435,0.2220095694,0.4373205742,0.395215311,0.4612440191,0.404784689,0.4392344498,0.4229665072,0.4076555024,0.419138756]]}

plots/clustermap_summ.json

@@ -1 +1 @@
-{"columns":["TheBloke\/Llama-2-13B-chat-GPTQ","TheBloke\/Llama-2-7B-Chat-GPTQ","TheBloke\/Wizard-Vicuna-13B-Uncensored-GPTQ","bigscience\/bloom-7b1","bigscience\/bloom-560m","berkeley-nest\/Starling-LM-7B-alpha","EleutherAI\/gpt-neo-125m","EleutherAI\/gpt-neo-2.7B","EleutherAI\/gpt-j-6b","EleutherAI\/gpt-neo-1.3B","Gryphe\/MythoMax-L2-13b","pankajmathur\/orca_mini_3b","KoboldAI\/OPT-13B-Erebus","togethercomputer\/LLaMA-2-7B-32K","togethercomputer\/GPT-JT-6B-v1","togethercomputer\/Llama-2-7B-32K-Instruct","tiiuae\/falcon-7b-instruct","tiiuae\/falcon-7b","ai-forever\/mGPT","upstage\/SOLAR-10.7B-Instruct-v1.0","meta-llama\/Llama-2-7b-chat-hf","meta-llama\/Llama-2-7b-hf","meta-llama\/Llama-2-13b-chat-hf","meta-llama\/Llama-2-13b-hf","teknium\/OpenHermes-2-Mistral-7B","mistralai\/Mistral-7B-Instruct-v0.1","Open-Orca\/Mistral-7B-OpenOrca","ehartford\/dolphin-2.1-mistral-7b","HuggingFaceH4\/zephyr-7b-alpha","HuggingFaceH4\/zephyr-7b-beta","NousResearch\/Yarn-Mistral-7b-128k","NousResearch\/Nous-Hermes-Llama2-13b","DiscoResearch\/mixtral-7b-8expert"],"index":["XSum, ROUGE-1","XSum, ROUGE-2","XSum, ROUGE-L","XSum, factKB","XSum, BERT-P","CNN\/DM, ROUGE-1","CNN\/DM, ROUGE-2","CNN\/DM, ROUGE-L","CNN\/DM, factKB","CNN\/DM, BERT-P"],"data":[[0.0371901778,0.0347891843,0.0428959698,0.2203326049,0.1749600982,0.0504142569,0.1607960902,0.1560967861,0.2724328188,0.1948865046,0.0384377825,0.2457075618,0.298490147,0.0432590646,0.3344535486,0.042540476,0.2352382212,0.2094982527,0.0153408429,0.001309379,0.0340250019,0.0445139517,0.0359765055,0.0413856309,null,null,null,null,null,null,null,null,null],[0.0,0.0,0.0,0.0475386414,0.0262246323,0.0,0.0214328855,0.0377156872,0.0872967218,0.0385742496,0.0,0.0653846178,0.105823501,0.0,0.1240294423,0.0,0.0614764833,0.0613314645,0.0010001753,0.0007904875,0.0,0.0,0.0,0.0,null,null,null,null,null,null,null,null,null],[0.0371901778,0.0347891843,0.0428959698,0.1668276326,0.1356427068,0.0504142569,0.1262087692,0.1205109613,0.2136831021,0.1487592997,0.0384377825,0.1854881243,0.2370092437,0.0432590646,0.2647281333,0.042540476,0.1822281713,0.1657837663,0.0141983599,0.0011478244,0.0340250019,0.0445139517,0.0359765055,0.0413856309,null,null,null,null,null,null,null,null,null],[0.0401970892,0.0394161696,0.0428647574,0.5674834215,0.2298042738,0.0397678158,0.2459031195,0.3441669812,0.4791825971,0.4144174002,0.0384018147,0.5666702185,0.4707080535,0.0407451505,0.3412336695,0.0400569668,0.4089209967,0.3192473228,0.1421243598,0.1811100146,0.0379350583,0.0428665575,0.0387781905,0.0411868449,null,null,null,null,null,null,null,null,null],[0.3949103208,0.3837605404,0.4030390077,0.6528773697,0.6049370656,0.4270770697,0.5845326816,0.4448599865,0.6811507025,0.6106414046,0.3989033275,0.6324491786,0.709515113,0.4014707047,0.7352085092,0.3991319337,0.6545591434,0.5731293539,0.4255551427,0.0021477235,0.3853941111,0.4050690645,0.3917698265,0.401477077,null,null,null,null,null,null,null,null,null],[0.0132261781,0.0098347434,0.012722468,0.2307383556,0.1357875781,0.0169222534,0.1400837608,0.2215130966,0.2555628211,0.2302678427,0.0135334171,0.2558424993,0.2379621599,0.0133793406,0.2670262038,0.012671213,0.2131071975,0.1893372238,0.0165830818,0.0006702693,0.0103604417,0.0145397085,null,0.0135674045,0.0114292948,0.008927303,0.0157445278,0.0142701427,0.0117323751,0.0111061484,0.0116271987,0.0131859896,0.0000716868],[0.0,0.0,0.000001892,0.089367922,0.0423122873,0.000001892,0.0429218938,0.0925038287,0.1067787126,0.0938882235,0.0,0.0985488725,0.0919108951,0.0,0.1076334391,0.0,0.0774515089,0.0724591632,0.000524905,0.0003540662,0.0,0.0,null,0.0,0.0,0.0,0.000001892,0.000001892,0.0,0.0,0.0,0.0,0.0],[0.0132261781,0.0098347434,0.012722468,0.2075387019,0.1227088127,0.0169222534,0.1243996336,0.1958355522,0.2238202254,0.2016505067,0.0135334171,0.2242330745,0.2130128961,0.0133793406,0.2408143362,0.012671213,0.1882467392,0.1691898288,0.0164863838,0.0006113776,0.0103604417,0.0145397085,null,0.0135674045,0.0114292948,0.008927303,0.0157445278,0.0142701427,0.0117323751,0.0111061484,0.0116271987,0.0131859896,0.0000716868],[0.1686613542,0.2305715843,0.1762471835,0.9249732766,0.7988642532,0.2070823135,0.7133009049,0.9058066799,0.9396594147,0.8739379747,0.1648057051,0.8669051787,0.9215527018,0.1575508605,0.94858605,0.1617593629,0.8267075767,0.901661868,0.7995222351,0.9509124595,0.1580946885,0.1517425501,null,0.155634531,0.1795055867,0.1750336135,0.2233354576,0.1965546069,0.1759309876,0.1893680342,0.166116994,0.1795224981,0.0805047156],[0.3668251897,0.3243336913,0.3548213557,0.6009727172,0.4646713339,0.3964162779,0.4789093344,0.5761275867,0.617234758,0.5888279105,0.3663381487,0.6159694987,0.6594958169,0.3663761784,0.7087181979,0.3645764744,0.5926767984,0.5112991874,0.4542439283,0.0013591523,0.3566615503,0.367965746,null,0.3640197324,0.3652777882,0.3544185533,0.3898203604,0.3785245521,0.3628082484,0.3673437638,0.3637139385,0.3722801591,0.3306992617]]}
+{"columns":["TheBloke\/Llama-2-13B-chat-GPTQ","TheBloke\/Llama-2-7B-Chat-GPTQ","TheBloke\/Wizard-Vicuna-13B-Uncensored-GPTQ","bigscience\/bloom-7b1","bigscience\/bloom-560m","berkeley-nest\/Starling-LM-7B-alpha","EleutherAI\/gpt-neo-125m","EleutherAI\/gpt-neo-2.7B","EleutherAI\/gpt-j-6b","EleutherAI\/gpt-neo-1.3B","Gryphe\/MythoMax-L2-13b","pankajmathur\/orca_mini_3b","KoboldAI\/OPT-13B-Erebus","togethercomputer\/LLaMA-2-7B-32K","togethercomputer\/GPT-JT-6B-v1","togethercomputer\/Llama-2-7B-32K-Instruct","tiiuae\/falcon-7b-instruct","tiiuae\/falcon-7b","ai-forever\/mGPT","upstage\/SOLAR-10.7B-Instruct-v1.0","meta-llama\/Llama-2-7b-chat-hf","meta-llama\/Llama-2-7b-hf","meta-llama\/Llama-2-13b-chat-hf","meta-llama\/Llama-2-13b-hf","teknium\/OpenHermes-2-Mistral-7B","mistralai\/Mistral-7B-Instruct-v0.1","Open-Orca\/Mistral-7B-OpenOrca","ehartford\/dolphin-2.1-mistral-7b","HuggingFaceH4\/zephyr-7b-alpha","HuggingFaceH4\/zephyr-7b-beta","NousResearch\/Yarn-Mistral-7b-128k","NousResearch\/Nous-Hermes-Llama2-13b","DiscoResearch\/mixtral-7b-8expert"],"index":["XSum, ROUGE-1","XSum, ROUGE-2","XSum, ROUGE-L","XSum, factKB","XSum, BERT-P","CNN\/DM, ROUGE-1","CNN\/DM, ROUGE-2","CNN\/DM, ROUGE-L","CNN\/DM, factKB","CNN\/DM, BERT-P","CNN\/DM v2, ROUGE-1","CNN\/DM v2, ROUGE-2","CNN\/DM v2, ROUGE-L","CNN\/DM v2, factKB","CNN\/DM v2, BERT-P","XSum v2, ROUGE-1","XSum v2, ROUGE-2","XSum v2, ROUGE-L","XSum v2, factKB","XSum v2, BERT-P"],"data":[[0.0371901778,0.0347891843,0.0428959698,0.2203326049,0.1749600982,0.0504142569,0.1607960902,0.1560967861,0.2724328188,0.1948865046,0.0384377825,0.2457075618,0.298490147,0.0432590646,0.3344535486,0.042540476,0.2352382212,0.2094982527,0.0153408429,0.001309379,0.0340250019,0.0445139517,0.0359765055,0.0413856309,null,null,null,null,null,null,null,null,null],[0.0,0.0,0.0,0.0475386414,0.0262246323,0.0,0.0214328855,0.0377156872,0.0872967218,0.0385742496,0.0,0.0653846178,0.105823501,0.0,0.1240294423,0.0,0.0614764833,0.0613314645,0.0010001753,0.0007904875,0.0,0.0,0.0,0.0,null,null,null,null,null,null,null,null,null],[0.0371901778,0.0347891843,0.0428959698,0.1668276326,0.1356427068,0.0504142569,0.1262087692,0.1205109613,0.2136831021,0.1487592997,0.0384377825,0.1854881243,0.2370092437,0.0432590646,0.2647281333,0.042540476,0.1822281713,0.1657837663,0.0141983599,0.0011478244,0.0340250019,0.0445139517,0.0359765055,0.0413856309,null,null,null,null,null,null,null,null,null],[0.0401970892,0.0394161696,0.0428647574,0.5674834215,0.2298042738,0.0397678158,0.2459031195,0.3441669812,0.4791825971,0.4144174002,0.0384018147,0.5666702185,0.4707080535,0.0407451505,0.3412336695,0.0400569668,0.4089209967,0.3192473228,0.1421243598,0.1811100146,0.0379350583,0.0428665575,0.0387781905,0.0411868449,null,null,null,null,null,null,null,null,null],[0.3949103208,0.3837605404,0.4030390077,0.6528773697,0.6049370656,0.4270770697,0.5845326816,0.4448599865,0.6811507025,0.6106414046,0.3989033275,0.6324491786,0.709515113,0.4014707047,0.7352085092,0.3991319337,0.6545591434,0.5731293539,0.4255551427,0.0021477235,0.3853941111,0.4050690645,0.3917698265,0.401477077,null,null,null,null,null,null,null,null,null],[0.0132261781,0.0098347434,0.012722468,0.2307383556,0.1357875781,0.0169222534,0.1400837608,0.2215130966,0.2555628211,0.2302678427,0.0135334171,0.2558424993,0.2379621599,0.0133793406,0.2670262038,0.012671213,0.2131071975,0.1893372238,0.0165830818,0.0006702693,0.0103604417,0.0145397085,null,0.0135674045,0.0114292948,0.008927303,0.0157445278,0.0142701427,0.0117323751,0.0111061484,0.0116271987,0.0131859896,0.0000716868],[0.0,0.0,0.000001892,0.089367922,0.0423122873,0.000001892,0.0429218938,0.0925038287,0.1067787126,0.0938882235,0.0,0.0985488725,0.0919108951,0.0,0.1076334391,0.0,0.0774515089,0.0724591632,0.000524905,0.0003540662,0.0,0.0,null,0.0,0.0,0.0,0.000001892,0.000001892,0.0,0.0,0.0,0.0,0.0],[0.0132261781,0.0098347434,0.012722468,0.2075387019,0.1227088127,0.0169222534,0.1243996336,0.1958355522,0.2238202254,0.2016505067,0.0135334171,0.2242330745,0.2130128961,0.0133793406,0.2408143362,0.012671213,0.1882467392,0.1691898288,0.0164863838,0.0006113776,0.0103604417,0.0145397085,null,0.0135674045,0.0114292948,0.008927303,0.0157445278,0.0142701427,0.0117323751,0.0111061484,0.0116271987,0.0131859896,0.0000716868],[0.1686613542,0.2305715843,0.1762471835,0.9249732766,0.7988642532,0.2070823135,0.7133009049,0.9058066799,0.9396594147,0.8739379747,0.1648057051,0.8669051787,0.9215527018,0.1575508605,0.94858605,0.1617593629,0.8267075767,0.901661868,0.7995222351,0.9509124595,0.1580946885,0.1517425501,null,0.155634531,0.1795055867,0.1750336135,0.2233354576,0.1965546069,0.1759309876,0.1893680342,0.166116994,0.1795224981,0.0805047156],[0.3668251897,0.3243336913,0.3548213557,0.6009727172,0.4646713339,0.3964162779,0.4789093344,0.5761275867,0.617234758,0.5888279105,0.3663381487,0.6159694987,0.6594958169,0.3663761784,0.7087181979,0.3645764744,0.5926767984,0.5112991874,0.4542439283,0.0013591523,0.3566615503,0.367965746,null,0.3640197324,0.3652777882,0.3544185533,0.3898203604,0.3785245521,0.3628082484,0.3673437638,0.3637139385,0.3722801591,0.3306992617],[null,null,null,null,null,null,null,0.1819405822,null,0.22221396,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],[null,null,null,null,null,null,null,0.0842738314,null,0.1031631811,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],[null,null,null,null,null,null,null,0.1559188347,null,0.1900936275,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],[null,null,null,null,null,null,null,0.9662616708,null,0.9704224166,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],[null,null,null,null,null,null,null,0.352680524,null,0.4360266906,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,0.1691722959,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,0.0370226737,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,0.1185889375,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,0.6746885531,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,0.3937310434,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null]]}