Hugging Face's logo

Spaces:
CZLC
/
BenCzechMark-unstable
Running

App Files Community
1
idolezal commited on
Commit
c93b288
·
1 Parent(s): 20b8116

Přidány kategorie do `tasks_metadata.json`

Browse files
Files changed (5) hide show
  1. .gitignore +21 -0
  2. app.py +2 -2
  3. compare_significance.py +1 -1
  4. server.py +2 -3
  5. tasks_metadata.json +280 -202
.gitignore ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ .eric6project/
2
+ .eric7project/
3
+ .ropeproject/
4
+ .jedi/
5
+ .directory/
6
+ *.pyc
7
+ *.pyo
8
+ *.orig
9
+ *.bak
10
+ *.rej
11
+ *~
12
+ cur/
13
+ tmp/
14
+ __pycache__/
15
+ __pypackages__
16
+ *.DS_Store
17
+ .pytest_cache/
18
+ venv/
19
+ .venv/
20
+ env/
21
+ .env/
app.py CHANGED
@@ -8,7 +8,7 @@ from gradio_modal import Modal
8
  from content import (HEADER_MARKDOWN, LEADERBOARD_TAB_TITLE_MARKDOWN, SUBMISSION_TAB_TITLE_MARKDOWN,
9
  MODAL_SUBMIT_MARKDOWN,
10
  SUBMISSION_DETAILS_MARKDOWN, RANKING_AFTER_SUBMISSION_MARKDOWN, MORE_DETAILS_MARKDOWN)
11
- from server import LeaderboardServer, categories
12
 
13
  leaderboard_server = LeaderboardServer()
14
 
@@ -157,7 +157,7 @@ with (gr.Blocks(theme=gr.themes.Soft(text_size=text_md), css=custom_css) as main
157
  with gr.Tab("Overall"):
158
  results_table = gr.DataFrame(leaderboard_server.get_leaderboard(), interactive=False, label=None,
159
  visible=True, elem_classes="leaderboard-table")
160
- for c in categories:
161
  with gr.Tab(c):
162
  results_table = gr.DataFrame(leaderboard_server.get_leaderboard(), interactive=False, label=None,
163
  visible=True, elem_classes="leaderboard-table")
 
8
  from content import (HEADER_MARKDOWN, LEADERBOARD_TAB_TITLE_MARKDOWN, SUBMISSION_TAB_TITLE_MARKDOWN,
9
  MODAL_SUBMIT_MARKDOWN,
10
  SUBMISSION_DETAILS_MARKDOWN, RANKING_AFTER_SUBMISSION_MARKDOWN, MORE_DETAILS_MARKDOWN)
11
+ from server import LeaderboardServer
12
 
13
  leaderboard_server = LeaderboardServer()
14
 
 
157
  with gr.Tab("Overall"):
158
  results_table = gr.DataFrame(leaderboard_server.get_leaderboard(), interactive=False, label=None,
159
  visible=True, elem_classes="leaderboard-table")
160
+ for c in leaderboard_server.tasks_categories:
161
  with gr.Tab(c):
162
  results_table = gr.DataFrame(leaderboard_server.get_leaderboard(), interactive=False, label=None,
163
  visible=True, elem_classes="leaderboard-table")
compare_significance.py CHANGED
@@ -176,7 +176,7 @@ def read_json(file_path):
176
  with open(METADATA_FILE, "r") as f:
177
  metadata = json.load(f)
178
 
179
- all_tasks = list(metadata["tasks"].keys())
180
  all_missing_tasks = []
181
  for task in all_tasks:
182
  if task not in data:
 
176
  with open(METADATA_FILE, "r") as f:
177
  metadata = json.load(f)
178
 
179
+ all_tasks = list(metadata.keys())
180
  all_missing_tasks = []
181
  for task in all_tasks:
182
  if task not in data:
server.py CHANGED
@@ -18,8 +18,6 @@ REPO = f"{ORG}/LLM_benchmark_data"
18
  HF_TOKEN = os.environ.get("HF_TOKEN")
19
  TASKS_METADATA_PATH = "./tasks_metadata.json"
20
 
21
- categories = ['Czech Math Reasoning', 'General Reasoning', 'Historical', 'Knowledge', 'Language Modeling', 'NER', 'NLI', 'Sentiment', 'Summarization', 'Syntactical Reasoning', 'Topic Classification']
22
-
23
  class LeaderboardServer:
24
  def __init__(self):
25
  self.server_address = REPO
@@ -27,7 +25,8 @@ class LeaderboardServer:
27
  self.local_leaderboard = snapshot_download(self.server_address, repo_type=self.repo_type, token=HF_TOKEN,
28
  local_dir="./")
29
  self.submisssion_id_to_file = {} # Map submission ids to file paths
30
- self.tasks_metadata = json.load(open(TASKS_METADATA_PATH))['tasks']
 
31
  self.submission_ids = set()
32
  self.fetch_existing_models()
33
  self.tournament_results = self.load_tournament_results()
 
18
  HF_TOKEN = os.environ.get("HF_TOKEN")
19
  TASKS_METADATA_PATH = "./tasks_metadata.json"
20
 
 
 
21
  class LeaderboardServer:
22
  def __init__(self):
23
  self.server_address = REPO
 
25
  self.local_leaderboard = snapshot_download(self.server_address, repo_type=self.repo_type, token=HF_TOKEN,
26
  local_dir="./")
27
  self.submisssion_id_to_file = {} # Map submission ids to file paths
28
+ self.tasks_metadata = json.load(open(TASKS_METADATA_PATH))
29
+ self.tasks_categories = {self.tasks_metadata[task]["category"] for task in self.tasks_metadata}
30
  self.submission_ids = set()
31
  self.fetch_existing_models()
32
  self.tournament_results = self.load_tournament_results()
tasks_metadata.json CHANGED
@@ -1,204 +1,282 @@
1
  {
2
- "tasks": {
3
- "benczechmark_propaganda_argumentace": {
4
- "task": "benczechmark_propaganda_argumentace",
5
- "name": "P-Argumentace",
6
- "source_url": "https://huggingface.co/datasets/CZLC/propaganda_argumentace"
7
- },
8
- "benczechmark_propaganda_fabulace": {
9
- "task": "benczechmark_propaganda_fabulace",
10
- "name": "P-Fabulace",
11
- "source_url": "https://huggingface.co/datasets/CZLC/propaganda_fabulace"
12
- },
13
- "benczechmark_propaganda_nazor": {
14
- "task": "benczechmark_propaganda_nazor",
15
- "name": "P-Názor",
16
- "source_url": "https://huggingface.co/datasets/CZLC/propaganda_nazor"
17
- },
18
- "benczechmark_propaganda_strach": {
19
- "task": "benczechmark_propaganda_strach",
20
- "name": "P-Strach",
21
- "source_url": "https://huggingface.co/datasets/CZLC/propaganda_strach"
22
- },
23
- "benczechmark_propaganda_zamereni": {
24
- "task": "benczechmark_propaganda_zamereni",
25
- "name": "P-Zaměření",
26
- "source_url": "https://huggingface.co/datasets/CZLC/propaganda_zamereni"
27
- },
28
- "benczechmark_propaganda_demonizace": {
29
- "task": "benczechmark_propaganda_demonizace",
30
- "name": "P-Demonizace",
31
- "source_url": "https://huggingface.co/datasets/CZLC/propaganda_demonizace"
32
- },
33
- "benczechmark_propaganda_lokace": {
34
- "task": "benczechmark_propaganda_lokace",
35
- "name": "P-Lokace",
36
- "source_url": "https://huggingface.co/datasets/CZLC/propaganda_lokace"
37
- },
38
- "benczechmark_propaganda_relativizace": {
39
- "task": "benczechmark_propaganda_relativizace",
40
- "name": "P-Relativizace",
41
- "source_url": "https://huggingface.co/datasets/CZLC/propaganda_relativizace"
42
- },
43
- "benczechmark_propaganda_vina": {
44
- "task": "benczechmark_propaganda_vina",
45
- "name": "P-Vina",
46
- "source_url": "https://huggingface.co/datasets/CZLC/propaganda_vina"
47
- },
48
- "benczechmark_propaganda_zanr": {
49
- "task": "benczechmark_propaganda_zanr",
50
- "name": "P-Žánr",
51
- "source_url": "https://huggingface.co/datasets/CZLC/propaganda_zanr"
52
- },
53
- "benczechmark_propaganda_emoce": {
54
- "task": "benczechmark_propaganda_emoce",
55
- "name": "P-Emoce",
56
- "source_url": "https://huggingface.co/datasets/CZLC/propaganda_emoce"
57
- },
58
- "benczechmark_propaganda_nalepkovani": {
59
- "task": "benczechmark_propaganda_nalepkovani",
60
- "name": "P-Nalepkování",
61
- "source_url": "https://huggingface.co/datasets/CZLC/propaganda_nalepkovani"
62
- },
63
- "benczechmark_propaganda_rusko": {
64
- "task": "benczechmark_propaganda_rusko",
65
- "name": "P-Rusko",
66
- "source_url": "https://huggingface.co/datasets/CZLC/propaganda_rusko"
67
- },
68
- "benczechmark_sentiment_mall": {
69
- "task": "benczechmark_sentiment_mall",
70
- "name": "S-Mall",
71
- "source_url": "https://huggingface.co/datasets/CZLC/mall_sentiment_balanced"
72
- },
73
- "benczechmark_sentiment_fb": {
74
- "task": "benczechmark_sentiment_fb",
75
- "name": "S-FB",
76
- "source_url": "https://huggingface.co/datasets/CZLC/fb_sentiment_balanced"
77
- },
78
- "benczechmark_sentiment_csfd": {
79
- "task": "benczechmark_sentiment_csfd",
80
- "name": "S-CSFD",
81
- "source_url": "https://huggingface.co/datasets/CZLC/csfd_sentiment_balanced"
82
- },
83
- "benczechmark_summarization": {
84
- "task": "benczechmark_summarization",
85
- "name": "Summarization",
86
- "source_url": "https://huggingface.co/datasets/CZLC/sumeczech_downsampled"
87
- },
88
- "benczechmark_grammarerrorcorrection": {
89
- "task": "benczechmark_grammarerrorcorrection",
90
- "name": "Grammar Error Correction",
91
- "source_url": "https://huggingface.co/datasets/CZLC/cs_gec"
92
- },
93
- "benczechmark_cs_naturalquestions": {
94
- "task": "benczechmark_cs_naturalquestions",
95
- "name": "CS Natural Questions",
96
- "source_url": "https://huggingface.co/datasets/CZLC/cs_naturalquestions"
97
- },
98
- "benczechmark_cs_sqad32": {
99
- "task": "benczechmark_cs_sqad32",
100
- "name": "CS SQAD 3.2",
101
- "source_url": "https://huggingface.co/datasets/CZLC/SQAD_3.2"
102
- },
103
- "benczechmark_cs_triviaQA": {
104
- "task": "benczechmark_cs_triviaQA",
105
- "name": "CS TriviaQA",
106
- "source_url": "https://huggingface.co/datasets/CZLC/cs_triviaqa"
107
- },
108
- "benczechmark_csfever_nli": {
109
- "task": "benczechmark_csfever_nli",
110
- "name": "CSFever NLI",
111
- "source_url": "https://huggingface.co/datasets/CZLC/ctu-aic/csfever_nli"
112
- },
113
- "benczechmark_ctkfacts_nli": {
114
- "task": "benczechmark_ctkfacts_nli",
115
- "name": "CTKFacts NLI",
116
- "source_url": "https://huggingface.co/datasets/CZLC/ctu-aic/ctkfacts_nli"
117
- },
118
- "benczechmark_cs_ner": {
119
- "task": "benczechmark_cs_ner",
120
- "name": "CS NER",
121
- "source_url": "https://huggingface.co/datasets/CZLC/fewshot-goes-multilingual/cs_czech-named-entity-corpus_2.0"
122
- },
123
- "benczechmark_hellaswag": {
124
- "task": "benczechmark_hellaswag",
125
- "name": "HellaSwag",
126
- "source_url": "https://huggingface.co/datasets/CZLC/cs_hellaswag"
127
- },
128
- "benczechmark_histcorpus": {
129
- "task": "benczechmark_histcorpus",
130
- "name": "HistCorpus",
131
- "source_url": "https://huggingface.co/datasets/CZLC/benczechmark_histcorpus"
132
- },
133
- "benczechmark_klokan_qa": {
134
- "task": "benczechmark_klokan_qa",
135
- "name": "Klokan QA",
136
- "source_url": "https://huggingface.co/datasets/hynky/klokan-qa"
137
- },
138
- "benczechmark_cs_court_decisions_ner": {
139
- "task": "benczechmark_cs_court_decisions_ner",
140
- "name": "CS Court Decisions NER",
141
- "source_url": "https://huggingface.co/datasets/CZLC/fewshot-goes-multilingual/cs_czech-court-decisions-ner"
142
- },
143
- "benczechmark_umimeto_biology": {
144
- "task": "benczechmark_umimeto_biology",
145
- "name": "Umimeto.cz - Biology",
146
- "source_url": "https://huggingface.co/datasets/CZLC/umimeto-biology"
147
- },
148
- "benczechmark_umimeto_chemistry": {
149
- "task": "benczechmark_umimeto_chemistry",
150
- "name": "Umimeto.cz - Chemistry",
151
- "source_url": "https://huggingface.co/datasets/CZLC/umimeto-chemistry"
152
- },
153
- "benczechmark_umimeto_czech": {
154
- "task": "benczechmark_umimeto_czech",
155
- "name": "Umimeto.cz - Czech",
156
- "source_url": "https://huggingface.co/datasets/CZLC/umimeto-czech"
157
- },
158
- "benczechmark_umimeto_history": {
159
- "task": "benczechmark_umimeto_history",
160
- "name": "Umimeto.cz - History",
161
- "source_url": "https://huggingface.co/datasets/CZLC/umimeto-history"
162
- },
163
- "benczechmark_umimeto_informatics": {
164
- "task": "benczechmark_umimeto_informatics",
165
- "name": "Umimeto.cz - Informatics",
166
- "source_url": "https://huggingface.co/datasets/CZLC/umimeto-informatics"
167
- },
168
- "benczechmark_umimeto_math": {
169
- "task": "benczechmark_umimeto_math",
170
- "name": "Umimeto.cz - Math",
171
- "source_url": "https://huggingface.co/datasets/CZLC/umimeto-math"
172
- },
173
- "benczechmark_umimeto_physics": {
174
- "task": "benczechmark_umimeto_physics",
175
- "name": "Umimeto.cz - Physics",
176
- "source_url": "https://huggingface.co/datasets/CZLC/umimeto-physics"
177
- },
178
- "benczechmark_cermat_czmath_mc": {
179
- "task": "benczechmark_cermat_czmath_mc",
180
- "name": "Cermat Czech Math MC",
181
- "source_url": "https://huggingface.co/datasets/CZLC/cermat_math_mc"
182
- },
183
- "benczechmark_cermat_czmath_open": {
184
- "task": "benczechmark_cermat_czmath_open",
185
- "name": "Cermat Czech Math Open",
186
- "source_url": "https://huggingface.co/datasets/CZLC/cermat_math_open"
187
- },
188
- "benczechmark_cermat_czech_tf": {
189
- "task": "benczechmark_cermat_czech_tf",
190
- "name": "Cermat Czech Language TF",
191
- "source_url": "https://huggingface.co/datasets/CZLC/cermat_czech_tf"
192
- },
193
- "benczechmark_cermat_czech_mc": {
194
- "task": "benczechmark_cermat_czech_mc",
195
- "name": "Cermat Czech Language MC",
196
- "source_url": "https://huggingface.co/datasets/CZLC/cermat_czech_mc"
197
- },
198
- "benczechmark_cermat_czech_open": {
199
- "task": "benczechmark_cermat_czech_open",
200
- "name": "Cermat Czech Language Open",
201
- "source_url": "https://huggingface.co/datasets/CZLC/cermat_czech_open"
202
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
203
  }
204
- }
 
1
  {
2
+ "benczechmark_propaganda_argumentace": {
3
+ "name": "Propaganda - Argumentace",
4
+ "source_url": "https://huggingface.co/datasets/CZLC/propaganda_argumentace",
5
+ "short_name": "P-Argumentace",
6
+ "category": "NLI",
7
+ "abbreviation": "P-ARG"
8
+ },
9
+ "benczechmark_propaganda_fabulace": {
10
+ "name": "Propaganda - Fabulace",
11
+ "source_url": "https://huggingface.co/datasets/CZLC/propaganda_fabulace",
12
+ "short_name": "P-Fabulace",
13
+ "category": "NLI",
14
+ "abbreviation": "P-FAB"
15
+ },
16
+ "benczechmark_propaganda_nazor": {
17
+ "name": "Propaganda - Nazor",
18
+ "source_url": "https://huggingface.co/datasets/CZLC/propaganda_nazor",
19
+ "short_name": "P-Názor",
20
+ "category": "NLI",
21
+ "abbreviation": "P-NAZOR"
22
+ },
23
+ "benczechmark_propaganda_strach": {
24
+ "name": "Propaganda - Strach",
25
+ "source_url": "https://huggingface.co/datasets/CZLC/propaganda_strach",
26
+ "short_name": "P-Strach",
27
+ "category": "NLI",
28
+ "abbreviation": "P-STCH"
29
+ },
30
+ "benczechmark_propaganda_zamereni": {
31
+ "name": "Propaganda - Zamereni",
32
+ "source_url": "https://huggingface.co/datasets/CZLC/propaganda_zamereni",
33
+ "short_name": "P-Zaměření",
34
+ "category": "NLI",
35
+ "abbreviation": "P-MER"
36
+ },
37
+ "benczechmark_propaganda_demonizace": {
38
+ "name": "Propaganda - Demonizace",
39
+ "source_url": "https://huggingface.co/datasets/CZLC/propaganda_demonizace",
40
+ "short_name": "P-Demonizace",
41
+ "category": "NLI",
42
+ "abbreviation": "P-DEMON"
43
+ },
44
+ "benczechmark_propaganda_lokace": {
45
+ "name": "Propaganda - Lokace",
46
+ "source_url": "https://huggingface.co/datasets/CZLC/propaganda_lokace",
47
+ "short_name": "P-Lokace",
48
+ "category": "NLI",
49
+ "abbreviation": "P-LOK"
50
+ },
51
+ "benczechmark_propaganda_relativizace": {
52
+ "name": "Propaganda - Relativizace",
53
+ "source_url": "https://huggingface.co/datasets/CZLC/propaganda_relativizace",
54
+ "short_name": "P-Relativizace",
55
+ "category": "NLI",
56
+ "abbreviation": "P-REL"
57
+ },
58
+ "benczechmark_propaganda_vina": {
59
+ "name": "Propaganda - Vina",
60
+ "source_url": "https://huggingface.co/datasets/CZLC/propaganda_vina",
61
+ "short_name": "P-Vina",
62
+ "category": "NLI",
63
+ "abbreviation": "P-VINA"
64
+ },
65
+ "benczechmark_propaganda_zanr": {
66
+ "name": "Propaganda - Zanr",
67
+ "source_url": "https://huggingface.co/datasets/CZLC/propaganda_zanr",
68
+ "short_name": "P-Žánr",
69
+ "category": "NLI",
70
+ "abbreviation": "P-ZANR"
71
+ },
72
+ "benczechmark_propaganda_emoce": {
73
+ "name": "Propaganda - Emoce",
74
+ "source_url": "https://huggingface.co/datasets/CZLC/propaganda_emoce",
75
+ "short_name": "P-Emoce",
76
+ "category": "NLI",
77
+ "abbreviation": "P-EMOCE"
78
+ },
79
+ "benczechmark_propaganda_nalepkovani": {
80
+ "name": "Propaganda - Nalepkovani",
81
+ "source_url": "https://huggingface.co/datasets/CZLC/propaganda_nalepkovani",
82
+ "short_name": "P-Nalepkování",
83
+ "category": "NLI",
84
+ "abbreviation": "P-LEP"
85
+ },
86
+ "benczechmark_propaganda_rusko": {
87
+ "name": "Propaganda - Rusko",
88
+ "source_url": "https://huggingface.co/datasets/CZLC/propaganda_rusko",
89
+ "short_name": "P-Rusko",
90
+ "category": "NLI",
91
+ "abbreviation": "P-RUS"
92
+ },
93
+ "benczechmark_sentiment_mall": {
94
+ "name": "CzechSentiment MALL",
95
+ "source_url": "https://huggingface.co/datasets/CZLC/mall_sentiment_balanced",
96
+ "short_name": "S-Mall",
97
+ "category": "Sentiment",
98
+ "abbreviation": "S-MALL"
99
+ },
100
+ "benczechmark_sentiment_fb": {
101
+ "name": "CzechSentiment FB",
102
+ "source_url": "https://huggingface.co/datasets/CZLC/fb_sentiment_balanced",
103
+ "short_name": "S-FB",
104
+ "category": "Sentiment",
105
+ "abbreviation": "S-FB"
106
+ },
107
+ "benczechmark_sentiment_csfd": {
108
+ "name": "CzechSentiment CSFD",
109
+ "source_url": "https://huggingface.co/datasets/CZLC/csfd_sentiment_balanced",
110
+ "short_name": "S-CSFD",
111
+ "category": "Sentiment",
112
+ "abbreviation": "S-CSFD"
113
+ },
114
+ "benczechmark_summarization": {
115
+ "name": "SUMECZECH",
116
+ "source_url": "https://huggingface.co/datasets/CZLC/sumeczech_downsampled",
117
+ "short_name": "Summarization",
118
+ "category": "Summarization",
119
+ "abbreviation": "SUM"
120
+ },
121
+ "benczechmark_grammarerrorcorrection": {
122
+ "name": "GrammarErrorCorrection",
123
+ "source_url": "https://huggingface.co/datasets/CZLC/cs_gec",
124
+ "short_name": "Grammar Error Correction",
125
+ "category": "Syntactical Reasoning",
126
+ "abbreviation": "GEC"
127
+ },
128
+ "benczechmark_cs_naturalquestions": {
129
+ "name": "NaturalQuestions-CZ",
130
+ "source_url": "https://huggingface.co/datasets/CZLC/cs_naturalquestions",
131
+ "short_name": "CS Natural Questions",
132
+ "category": "Knowledge",
133
+ "abbreviation": "NQ"
134
+ },
135
+ "benczechmark_cs_sqad32": {
136
+ "name": "SQAD3.2",
137
+ "source_url": "https://huggingface.co/datasets/CZLC/SQAD_3.2",
138
+ "short_name": "CS SQAD 3.2",
139
+ "category": "Knowledge",
140
+ "abbreviation": "SQAD32"
141
+ },
142
+ "benczechmark_cs_triviaQA": {
143
+ "name": "TriviaQA-CZ",
144
+ "source_url": "https://huggingface.co/datasets/CZLC/cs_triviaqa",
145
+ "short_name": "CS TriviaQA",
146
+ "category": "Knowledge",
147
+ "abbreviation": "TQA"
148
+ },
149
+ "benczechmark_csfever_nli": {
150
+ "name": "CSFEVER",
151
+ "source_url": "https://huggingface.co/datasets/CZLC/ctu-aic/csfever_nli",
152
+ "short_name": "CSFever NLI",
153
+ "category": "NLI",
154
+ "abbreviation": "CFR"
155
+ },
156
+ "benczechmark_ctkfacts_nli": {
157
+ "name": "CTKFACTS",
158
+ "source_url": "https://huggingface.co/datasets/CZLC/ctu-aic/ctkfacts_nli",
159
+ "short_name": "CTKFacts NLI",
160
+ "category": "NLI",
161
+ "abbreviation": "CTK"
162
+ },
163
+ "benczechmark_cs_ner": {
164
+ "name": "CZECH NER CORPUS 2.0",
165
+ "source_url": "https://huggingface.co/datasets/CZLC/fewshot-goes-multilingual/cs_czech-named-entity-corpus_2.0",
166
+ "short_name": "CS NER",
167
+ "category": "NER",
168
+ "abbreviation": "CZNERC"
169
+ },
170
+ "benczechmark_hellaswag": {
171
+ "name": "HellaSwag-CZ",
172
+ "source_url": "https://huggingface.co/datasets/CZLC/cs_hellaswag",
173
+ "short_name": "HellaSwag",
174
+ "category": "Language Modeling",
175
+ "abbreviation": "HASG"
176
+ },
177
+ "benczechmark_histcorpus": {
178
+ "name": "Historical Corpus",
179
+ "source_url": "https://huggingface.co/datasets/CZLC/benczechmark_histcorpus",
180
+ "short_name": "HistCorpus",
181
+ "category": "Language Modeling",
182
+ "abbreviation": "HIST"
183
+ },
184
+ "benczechmark_klokan_qa": {
185
+ "name": "Klokan QA",
186
+ "source_url": "https://huggingface.co/datasets/hynky/klokan-qa",
187
+ "short_name": "Klokan QA",
188
+ "category": "Czech Math Reasoning",
189
+ "abbreviation": "KQA"
190
+ },
191
+ "benczechmark_cs_court_decisions_ner": {
192
+ "name": "Czech Court Decisions",
193
+ "source_url": "https://huggingface.co/datasets/CZLC/fewshot-goes-multilingual/cs_czech-court-decisions-ner",
194
+ "short_name": "CS Court Decisions NER",
195
+ "category": "NER",
196
+ "abbreviation": "CCDNER"
197
+ },
198
+ "benczechmark_umimeto_biology": {
199
+ "name": "Umimeto.cz - Biology",
200
+ "source_url": "https://huggingface.co/datasets/CZLC/umimeto-biology",
201
+ "short_name": "Umimeto.cz - Biology",
202
+ "category": "General Reasoning",
203
+ "abbreviation": "UT-BIO"
204
+ },
205
+ "benczechmark_umimeto_chemistry": {
206
+ "name": "Umimeto.cz - Chemistry",
207
+ "source_url": "https://huggingface.co/datasets/CZLC/umimeto-chemistry",
208
+ "short_name": "Umimeto.cz - Chemistry",
209
+ "category": "General Reasoning",
210
+ "abbreviation": "UT-CHEM"
211
+ },
212
+ "benczechmark_umimeto_czech": {
213
+ "name": "Umimeto.cz - Czech Language",
214
+ "source_url": "https://huggingface.co/datasets/CZLC/umimeto-czech",
215
+ "short_name": "Umimeto.cz - Czech",
216
+ "category": "General Reasoning",
217
+ "abbreviation": "UT-CZEL"
218
+ },
219
+ "benczechmark_umimeto_history": {
220
+ "name": "Umimeto.cz - History",
221
+ "source_url": "https://huggingface.co/datasets/CZLC/umimeto-history",
222
+ "short_name": "Umimeto.cz - History",
223
+ "category": "General Reasoning",
224
+ "abbreviation": "UT-HIST"
225
+ },
226
+ "benczechmark_umimeto_informatics": {
227
+ "name": "Umimeto.cz - Informatics",
228
+ "source_url": "https://huggingface.co/datasets/CZLC/umimeto-informatics",
229
+ "short_name": "Umimeto.cz - Informatics",
230
+ "category": "General Reasoning",
231
+ "abbreviation": "UT-IT"
232
+ },
233
+ "benczechmark_umimeto_math": {
234
+ "name": "Umimeto.cz - Math",
235
+ "source_url": "https://huggingface.co/datasets/CZLC/umimeto-math",
236
+ "short_name": "Umimeto.cz - Math",
237
+ "category": "Czech Math Reasoning",
238
+ "abbreviation": "UT-MATH"
239
+ },
240
+ "benczechmark_umimeto_physics": {
241
+ "name": "Umimeto.cz - Physics",
242
+ "source_url": "https://huggingface.co/datasets/CZLC/umimeto-physics",
243
+ "short_name": "Umimeto.cz - Physics",
244
+ "category": "General Reasoning",
245
+ "abbreviation": "UT-PHYS"
246
+ },
247
+ "benczechmark_cermat_czmath_mc": {
248
+ "name": "CERMAT - Czech Math - MC",
249
+ "source_url": "https://huggingface.co/datasets/CZLC/cermat_math_mc",
250
+ "short_name": "Cermat Czech Math MC",
251
+ "category": "Czech Math Reasoning",
252
+ "abbreviation": "CCM-MC"
253
+ },
254
+ "benczechmark_cermat_czmath_open": {
255
+ "name": "CERMAT - Czech Math - OPEN",
256
+ "source_url": "https://huggingface.co/datasets/CZLC/cermat_math_open",
257
+ "short_name": "Cermat Czech Math Open",
258
+ "category": "Czech Math Reasoning",
259
+ "abbreviation": "CCM-OPEN"
260
+ },
261
+ "benczechmark_cermat_czech_tf": {
262
+ "name": "CERMAT - Czech Language - TF",
263
+ "source_url": "https://huggingface.co/datasets/CZLC/cermat_czech_tf",
264
+ "short_name": "Cermat Czech Language TF",
265
+ "category": "General Reasoning",
266
+ "abbreviation": "CCL-TF"
267
+ },
268
+ "benczechmark_cermat_czech_mc": {
269
+ "name": "CERMAT - Czech Language - MC",
270
+ "source_url": "https://huggingface.co/datasets/CZLC/cermat_czech_mc",
271
+ "short_name": "Cermat Czech Language MC",
272
+ "category": "General Reasoning",
273
+ "abbreviation": "CCL-MC"
274
+ },
275
+ "benczechmark_cermat_czech_open": {
276
+ "name": "CERMAT - Czech Language - OPEN",
277
+ "source_url": "https://huggingface.co/datasets/CZLC/cermat_czech_open",
278
+ "short_name": "Cermat Czech Language Open",
279
+ "category": "General Reasoning",
280
+ "abbreviation": "CCL-OPEN"
281
  }
282
+ }