Changes
On January 2, 2025 at 11:59:52 PM UTC, admin:
-
Changed value of field
doi_status
toTrue
in mC4 -
Changed value of field
doi_date_published
to2025-01-02
in mC4 -
Added resource Original Metadata to mC4
f | 1 | { | f | 1 | { |
2 | "access_rights": "", | 2 | "access_rights": "", | ||
3 | "author": "Kshitij Gupta", | 3 | "author": "Kshitij Gupta", | ||
4 | "author_email": "", | 4 | "author_email": "", | ||
5 | "citation": [ | 5 | "citation": [ | ||
6 | "https://doi.org/10.48550/arXiv.2311.09344", | 6 | "https://doi.org/10.48550/arXiv.2311.09344", | ||
7 | "https://doi.org/10.48550/arXiv.2312.06134", | 7 | "https://doi.org/10.48550/arXiv.2312.06134", | ||
8 | "https://doi.org/10.48550/arXiv.2110.05838", | 8 | "https://doi.org/10.48550/arXiv.2110.05838", | ||
9 | "https://doi.org/10.48550/arXiv.2404.08191" | 9 | "https://doi.org/10.48550/arXiv.2404.08191" | ||
10 | ], | 10 | ], | ||
11 | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | 11 | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | ||
12 | "defined_in": "https://doi.org/10.48550/arXiv.2210.00320", | 12 | "defined_in": "https://doi.org/10.48550/arXiv.2210.00320", | ||
13 | "doi": "10.57702/v6e39h1h", | 13 | "doi": "10.57702/v6e39h1h", | ||
n | 14 | "doi_date_published": null, | n | 14 | "doi_date_published": "2025-01-02", |
15 | "doi_publisher": "TIB", | 15 | "doi_publisher": "TIB", | ||
n | 16 | "doi_status": false, | n | 16 | "doi_status": true, |
17 | "domain": "https://service.tib.eu/ldmservice", | 17 | "domain": "https://service.tib.eu/ldmservice", | ||
18 | "groups": [ | 18 | "groups": [ | ||
19 | { | 19 | { | ||
20 | "description": "", | 20 | "description": "", | ||
21 | "display_name": "Multilingual Language Modeling", | 21 | "display_name": "Multilingual Language Modeling", | ||
22 | "id": "98faf760-33f4-4bb9-806e-c80f4145c8e9", | 22 | "id": "98faf760-33f4-4bb9-806e-c80f4145c8e9", | ||
23 | "image_display_url": "", | 23 | "image_display_url": "", | ||
24 | "name": "multilingual-language-modeling", | 24 | "name": "multilingual-language-modeling", | ||
25 | "title": "Multilingual Language Modeling" | 25 | "title": "Multilingual Language Modeling" | ||
26 | }, | 26 | }, | ||
27 | { | 27 | { | ||
28 | "description": "", | 28 | "description": "", | ||
29 | "display_name": "Multilingual Pre-training", | 29 | "display_name": "Multilingual Pre-training", | ||
30 | "id": "957b2c5c-4c52-48de-83de-ba035f0083e9", | 30 | "id": "957b2c5c-4c52-48de-83de-ba035f0083e9", | ||
31 | "image_display_url": "", | 31 | "image_display_url": "", | ||
32 | "name": "multilingual-pre-training", | 32 | "name": "multilingual-pre-training", | ||
33 | "title": "Multilingual Pre-training" | 33 | "title": "Multilingual Pre-training" | ||
34 | }, | 34 | }, | ||
35 | { | 35 | { | ||
36 | "description": "", | 36 | "description": "", | ||
37 | "display_name": "Natural Language Processing", | 37 | "display_name": "Natural Language Processing", | ||
38 | "id": "5b974bcc-8f79-40fc-a05d-75b861d55ed0", | 38 | "id": "5b974bcc-8f79-40fc-a05d-75b861d55ed0", | ||
39 | "image_display_url": "", | 39 | "image_display_url": "", | ||
40 | "name": "natural-language-processing", | 40 | "name": "natural-language-processing", | ||
41 | "title": "Natural Language Processing" | 41 | "title": "Natural Language Processing" | ||
42 | } | 42 | } | ||
43 | ], | 43 | ], | ||
44 | "id": "4585a108-1553-46fc-a013-be7e5c9a6a2c", | 44 | "id": "4585a108-1553-46fc-a013-be7e5c9a6a2c", | ||
45 | "isopen": false, | 45 | "isopen": false, | ||
46 | "landing_page": "https://huggingface.co/mT5", | 46 | "landing_page": "https://huggingface.co/mT5", | ||
47 | "license_title": null, | 47 | "license_title": null, | ||
48 | "link_orkg": "", | 48 | "link_orkg": "", | ||
49 | "metadata_created": "2025-01-02T23:59:50.891464", | 49 | "metadata_created": "2025-01-02T23:59:50.891464", | ||
n | 50 | "metadata_modified": "2025-01-02T23:59:50.891470", | n | 50 | "metadata_modified": "2025-01-02T23:59:51.414277", |
51 | "name": "mc4", | 51 | "name": "mc4", | ||
52 | "notes": "Parameter-efficient fine-tuning (PEFT) using labeled task | 52 | "notes": "Parameter-efficient fine-tuning (PEFT) using labeled task | ||
53 | data can significantly improve the performance of large language | 53 | data can significantly improve the performance of large language | ||
54 | models (LLMs) on the downstream task. However, there are 7000 | 54 | models (LLMs) on the downstream task. However, there are 7000 | ||
55 | languages in the world and many of these languages lack labeled data | 55 | languages in the world and many of these languages lack labeled data | ||
56 | for real-world language generation tasks.", | 56 | for real-world language generation tasks.", | ||
n | 57 | "num_resources": 0, | n | 57 | "num_resources": 1, |
58 | "num_tags": 11, | 58 | "num_tags": 11, | ||
59 | "organization": { | 59 | "organization": { | ||
60 | "approval_status": "approved", | 60 | "approval_status": "approved", | ||
61 | "created": "2024-11-25T12:11:38.292601", | 61 | "created": "2024-11-25T12:11:38.292601", | ||
62 | "description": "", | 62 | "description": "", | ||
63 | "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", | 63 | "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", | ||
64 | "image_url": "", | 64 | "image_url": "", | ||
65 | "is_organization": true, | 65 | "is_organization": true, | ||
66 | "name": "no-organization", | 66 | "name": "no-organization", | ||
67 | "state": "active", | 67 | "state": "active", | ||
68 | "title": "No Organization", | 68 | "title": "No Organization", | ||
69 | "type": "organization" | 69 | "type": "organization" | ||
70 | }, | 70 | }, | ||
71 | "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", | 71 | "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", | ||
72 | "private": false, | 72 | "private": false, | ||
73 | "relationships_as_object": [], | 73 | "relationships_as_object": [], | ||
74 | "relationships_as_subject": [], | 74 | "relationships_as_subject": [], | ||
t | 75 | "resources": [], | t | 75 | "resources": [ |
76 | { | ||||
77 | "cache_last_updated": null, | ||||
78 | "cache_url": null, | ||||
79 | "created": "2025-01-03T00:16:31", | ||||
80 | "data": [ | ||||
81 | "dcterms:title", | ||||
82 | "dcterms:accessRights", | ||||
83 | "dcterms:creator", | ||||
84 | "dcterms:description", | ||||
85 | "dcterms:issued", | ||||
86 | "dcterms:language", | ||||
87 | "dcterms:identifier", | ||||
88 | "dcat:theme", | ||||
89 | "dcterms:type", | ||||
90 | "dcat:keyword", | ||||
91 | "dcat:landingPage", | ||||
92 | "dcterms:hasVersion", | ||||
93 | "dcterms:format", | ||||
94 | "mls:task", | ||||
95 | "datacite:isDescribedBy" | ||||
96 | ], | ||||
97 | "description": "The json representation of the dataset with its | ||||
98 | distributions based on DCAT.", | ||||
99 | "format": "JSON", | ||||
100 | "hash": "", | ||||
101 | "id": "9bed56c0-c99a-4d19-b74a-e250dd48c60c", | ||||
102 | "last_modified": "2025-01-02T23:59:51.405461", | ||||
103 | "metadata_modified": "2025-01-02T23:59:51.417275", | ||||
104 | "mimetype": "application/json", | ||||
105 | "mimetype_inner": null, | ||||
106 | "name": "Original Metadata", | ||||
107 | "package_id": "4585a108-1553-46fc-a013-be7e5c9a6a2c", | ||||
108 | "position": 0, | ||||
109 | "resource_type": null, | ||||
110 | "size": 1294, | ||||
111 | "state": "active", | ||||
112 | "url": | ||||
113 | resource/9bed56c0-c99a-4d19-b74a-e250dd48c60c/download/metadata.json", | ||||
114 | "url_type": "upload" | ||||
115 | } | ||||
116 | ], | ||||
76 | "services_used_list": "", | 117 | "services_used_list": "", | ||
77 | "state": "active", | 118 | "state": "active", | ||
78 | "tags": [ | 119 | "tags": [ | ||
79 | { | 120 | { | ||
80 | "display_name": "Large Language Models", | 121 | "display_name": "Large Language Models", | ||
81 | "id": "6e366b4a-402d-4c0e-b818-6fec429fc72f", | 122 | "id": "6e366b4a-402d-4c0e-b818-6fec429fc72f", | ||
82 | "name": "Large Language Models", | 123 | "name": "Large Language Models", | ||
83 | "state": "active", | 124 | "state": "active", | ||
84 | "vocabulary_id": null | 125 | "vocabulary_id": null | ||
85 | }, | 126 | }, | ||
86 | { | 127 | { | ||
87 | "display_name": "Multilingual", | 128 | "display_name": "Multilingual", | ||
88 | "id": "6de060ee-b4b7-4b76-b978-29ec374b6594", | 129 | "id": "6de060ee-b4b7-4b76-b978-29ec374b6594", | ||
89 | "name": "Multilingual", | 130 | "name": "Multilingual", | ||
90 | "state": "active", | 131 | "state": "active", | ||
91 | "vocabulary_id": null | 132 | "vocabulary_id": null | ||
92 | }, | 133 | }, | ||
93 | { | 134 | { | ||
94 | "display_name": "Multilingual Language Modeling", | 135 | "display_name": "Multilingual Language Modeling", | ||
95 | "id": "668819ac-1a09-49e2-ae9b-c04533887632", | 136 | "id": "668819ac-1a09-49e2-ae9b-c04533887632", | ||
96 | "name": "Multilingual Language Modeling", | 137 | "name": "Multilingual Language Modeling", | ||
97 | "state": "active", | 138 | "state": "active", | ||
98 | "vocabulary_id": null | 139 | "vocabulary_id": null | ||
99 | }, | 140 | }, | ||
100 | { | 141 | { | ||
101 | "display_name": "Multilingual Pre-training", | 142 | "display_name": "Multilingual Pre-training", | ||
102 | "id": "5554aa12-176e-479a-a678-57e96c73460e", | 143 | "id": "5554aa12-176e-479a-a678-57e96c73460e", | ||
103 | "name": "Multilingual Pre-training", | 144 | "name": "Multilingual Pre-training", | ||
104 | "state": "active", | 145 | "state": "active", | ||
105 | "vocabulary_id": null | 146 | "vocabulary_id": null | ||
106 | }, | 147 | }, | ||
107 | { | 148 | { | ||
108 | "display_name": "Pre-training", | 149 | "display_name": "Pre-training", | ||
109 | "id": "c3559a2b-f8ff-4816-983f-16d506278772", | 150 | "id": "c3559a2b-f8ff-4816-983f-16d506278772", | ||
110 | "name": "Pre-training", | 151 | "name": "Pre-training", | ||
111 | "state": "active", | 152 | "state": "active", | ||
112 | "vocabulary_id": null | 153 | "vocabulary_id": null | ||
113 | }, | 154 | }, | ||
114 | { | 155 | { | ||
115 | "display_name": "Prefix Language Modeling", | 156 | "display_name": "Prefix Language Modeling", | ||
116 | "id": "82b08bde-52f2-4e62-a384-4c1fe274c25b", | 157 | "id": "82b08bde-52f2-4e62-a384-4c1fe274c25b", | ||
117 | "name": "Prefix Language Modeling", | 158 | "name": "Prefix Language Modeling", | ||
118 | "state": "active", | 159 | "state": "active", | ||
119 | "vocabulary_id": null | 160 | "vocabulary_id": null | ||
120 | }, | 161 | }, | ||
121 | { | 162 | { | ||
122 | "display_name": "dataset", | 163 | "display_name": "dataset", | ||
123 | "id": "ce5ad030-ca3d-47e6-abd1-5c92a2806f1b", | 164 | "id": "ce5ad030-ca3d-47e6-abd1-5c92a2806f1b", | ||
124 | "name": "dataset", | 165 | "name": "dataset", | ||
125 | "state": "active", | 166 | "state": "active", | ||
126 | "vocabulary_id": null | 167 | "vocabulary_id": null | ||
127 | }, | 168 | }, | ||
128 | { | 169 | { | ||
129 | "display_name": "mC4", | 170 | "display_name": "mC4", | ||
130 | "id": "ee7753b3-7eb2-4a4c-b099-15a0c73cc155", | 171 | "id": "ee7753b3-7eb2-4a4c-b099-15a0c73cc155", | ||
131 | "name": "mC4", | 172 | "name": "mC4", | ||
132 | "state": "active", | 173 | "state": "active", | ||
133 | "vocabulary_id": null | 174 | "vocabulary_id": null | ||
134 | }, | 175 | }, | ||
135 | { | 176 | { | ||
136 | "display_name": "mT5", | 177 | "display_name": "mT5", | ||
137 | "id": "4aa5c3e1-27b3-4b85-b8bd-d6daaa2f6508", | 178 | "id": "4aa5c3e1-27b3-4b85-b8bd-d6daaa2f6508", | ||
138 | "name": "mT5", | 179 | "name": "mT5", | ||
139 | "state": "active", | 180 | "state": "active", | ||
140 | "vocabulary_id": null | 181 | "vocabulary_id": null | ||
141 | }, | 182 | }, | ||
142 | { | 183 | { | ||
143 | "display_name": "multilingual", | 184 | "display_name": "multilingual", | ||
144 | "id": "ee7200c1-f044-4a4e-9c0d-3244e46c833d", | 185 | "id": "ee7200c1-f044-4a4e-9c0d-3244e46c833d", | ||
145 | "name": "multilingual", | 186 | "name": "multilingual", | ||
146 | "state": "active", | 187 | "state": "active", | ||
147 | "vocabulary_id": null | 188 | "vocabulary_id": null | ||
148 | }, | 189 | }, | ||
149 | { | 190 | { | ||
150 | "display_name": "nlp", | 191 | "display_name": "nlp", | ||
151 | "id": "b315aa21-42a3-42df-9151-d1a7e014a622", | 192 | "id": "b315aa21-42a3-42df-9151-d1a7e014a622", | ||
152 | "name": "nlp", | 193 | "name": "nlp", | ||
153 | "state": "active", | 194 | "state": "active", | ||
154 | "vocabulary_id": null | 195 | "vocabulary_id": null | ||
155 | } | 196 | } | ||
156 | ], | 197 | ], | ||
157 | "title": "mC4", | 198 | "title": "mC4", | ||
158 | "type": "dataset", | 199 | "type": "dataset", | ||
159 | "version": "" | 200 | "version": "" | ||
160 | } | 201 | } |