[go: nahoru, domu]
Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add schema.org sdLicense #545

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Add schema.org sdLicense #545

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
94ed732
Add schema.org sdLicense
mkuchnik Feb 21, 2024
5468eea
Fix license linking to URL
mkuchnik Feb 26, 2024
50ac1e8
Revert breaking metadata changes
mkuchnik Feb 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Revert breaking metadata changes
  • Loading branch information
@mkuchnik
mkuchnik committed Feb 26, 2024
commit 50ac1e8d8b48665c2bd1304792007a17e8bf4f3c
17 changes: 12 additions & 5 deletions datasets/1.0/bigcode-the-stack/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,18 +47,25 @@
"name": "bigcode-the-stack",
"conformsTo": "http://mlcommons.org/croissant/1.0",
"description": "The Stack contains over 6TB of permissively-licensed source code files covering 358 programming languages. The dataset was created as part of the BigCode Project, an open scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs). The Stack serves as a pre-training dataset for Code LLMs, i.e., code-generating AI systems which enable the synthesis of programs from natural language descriptions as well as other from code snippets.",
"citeAs": "@article{Kocetkov2022TheStack, title={The Stack: 3 TB of permissively licensed source code}, author={Kocetkov, Denis and Li, Raymond and Ben Allal, Loubna and Li, Jia and Mou,Chenghao and Mu\u00f1oz Ferrandis, Carlos and Jernite, Yacine and Mitchell, Margaret and Hughes, Sean and Wolf, Thomas and Bahdanau, Dzmitry and von Werra, Leandro and de Vries, Harm}, journal={Preprint}, year={2022} }",
"creator": [
{
"@type": "Organization",
"name": "Harm de Vries"
"@type": "Person",
"name": "Harm de Vries",
"email": "harm.devries@servicenow.com"
},
{
"@type": "Organization",
"name": "Leandro von Werra"
"@type": "Person",
"name": "Leandro von Werra",
"email": "leandro@huggingface.co"
}
],
"citeAs": "@article{Kocetkov2022TheStack, title={The Stack: 3 TB of permissively licensed source code}, author={Kocetkov, Denis and Li, Raymond and Ben Allal, Loubna and Li, Jia and Mou,Chenghao and Mu\u00f1oz Ferrandis, Carlos and Jernite, Yacine and Mitchell, Margaret and Hughes, Sean and Wolf, Thomas and Bahdanau, Dzmitry and von Werra, Leandro and de Vries, Harm}, journal={Preprint}, year={2022} }",
"keywords": [
"crowdsourced",
"expert-generated"
],
"license": "other",
"sameAs": "https://www.bigcode-project.org/docs/about/the-stack/",
"sdLicense": "https://www.apache.org/licenses/LICENSE-2.0",
"url": "https://huggingface.co/datasets/bigcode/the-stack",
"distribution": [
Expand Down
11 changes: 2 additions & 9 deletions ...mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_bad_contained_in/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,8 @@
"@context": {
"@language": "en",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "ml:column",
"conformsTo": "dct:conformsTo",
"cr": "http://mlcommons.org/croissant/",
"data": {
"@id": "ml:data",
"@type": "@json"
Expand All @@ -20,15 +18,11 @@
"extract": "ml:extract",
"field": "ml:field",
"fileProperty": "ml:fileProperty",
"fileObject": "cr:fileObject",
"fileSet": "cr:fileSet",
"format": "ml:format",
"includes": "ml:includes",
"isEnumeration": "ml:isEnumeration",
"isLiveDataset": "cr:isLiveDataset",
"jsonPath": "ml:jsonPath",
"key": "cr:key",
"md5": "cr:md5",
"ml": "http://mlcommons.org/schema/",
"parentField": "ml:parentField",
"path": "ml:path",
"personalSensitiveInformation": "ml:personalSensitiveInformation",
Expand All @@ -41,8 +35,7 @@
"separator": "ml:separator",
"source": "ml:source",
"subField": "ml:subField",
"transform": "ml:transform",
"ml": "http://mlcommons.org/schema/"
"transform": "ml:transform"
},
"@type": "sc:Dataset",
"name": "mydataset",
Expand Down
11 changes: 2 additions & 9 deletions python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_bad_type/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,8 @@
"@context": {
"@language": "en",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "ml:column",
"conformsTo": "dct:conformsTo",
"cr": "http://mlcommons.org/croissant/",
"data": {
"@id": "ml:data",
"@type": "@json"
Expand All @@ -20,15 +18,11 @@
"extract": "ml:extract",
"field": "ml:field",
"fileProperty": "ml:fileProperty",
"fileObject": "cr:fileObject",
"fileSet": "cr:fileSet",
"format": "ml:format",
"includes": "ml:includes",
"isEnumeration": "ml:isEnumeration",
"isLiveDataset": "cr:isLiveDataset",
"jsonPath": "ml:jsonPath",
"key": "cr:key",
"md5": "cr:md5",
"ml": "http://mlcommons.org/schema/",
"parentField": "ml:parentField",
"path": "ml:path",
"personalSensitiveInformation": "ml:personalSensitiveInformation",
Expand All @@ -41,8 +35,7 @@
"separator": "ml:separator",
"source": "ml:source",
"subField": "ml:subField",
"transform": "ml:transform",
"ml": "http://mlcommons.org/schema/"
"transform": "ml:transform"
},
"@type": "sc:Dataset",
"name": "mydataset",
Expand Down
11 changes: 2 additions & 9 deletions python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_missing_name/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,8 @@
"@context": {
"@language": "en",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "ml:column",
"conformsTo": "dct:conformsTo",
"cr": "http://mlcommons.org/croissant/",
"data": {
"@id": "ml:data",
"@type": "@json"
Expand All @@ -20,15 +18,11 @@
"extract": "ml:extract",
"field": "ml:field",
"fileProperty": "ml:fileProperty",
"fileObject": "cr:fileObject",
"fileSet": "cr:fileSet",
"format": "ml:format",
"includes": "ml:includes",
"isEnumeration": "ml:isEnumeration",
"isLiveDataset": "cr:isLiveDataset",
"jsonPath": "ml:jsonPath",
"key": "cr:key",
"md5": "cr:md5",
"ml": "http://mlcommons.org/schema/",
"parentField": "ml:parentField",
"path": "ml:path",
"personalSensitiveInformation": "ml:personalSensitiveInformation",
Expand All @@ -41,8 +35,7 @@
"separator": "ml:separator",
"source": "ml:source",
"subField": "ml:subField",
"transform": "ml:transform",
"ml": "http://mlcommons.org/schema/"
"transform": "ml:transform"
},
"@type": "sc:Dataset",
"name": "mydataset",
Expand Down
11 changes: 2 additions & 9 deletions ...mlcroissant/_src/tests/graphs/0.8/distribution_missing_property_content_url/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,8 @@
"@context": {
"@language": "en",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "ml:column",
"conformsTo": "dct:conformsTo",
"cr": "http://mlcommons.org/croissant/",
"data": {
"@id": "ml:data",
"@type": "@json"
Expand All @@ -20,15 +18,11 @@
"extract": "ml:extract",
"field": "ml:field",
"fileProperty": "ml:fileProperty",
"fileObject": "cr:fileObject",
"fileSet": "cr:fileSet",
"format": "ml:format",
"includes": "ml:includes",
"isEnumeration": "ml:isEnumeration",
"isLiveDataset": "cr:isLiveDataset",
"jsonPath": "ml:jsonPath",
"key": "cr:key",
"md5": "cr:md5",
"ml": "http://mlcommons.org/schema/",
"parentField": "ml:parentField",
"path": "ml:path",
"personalSensitiveInformation": "ml:personalSensitiveInformation",
Expand All @@ -41,8 +35,7 @@
"separator": "ml:separator",
"source": "ml:source",
"subField": "ml:subField",
"transform": "ml:transform",
"ml": "http://mlcommons.org/schema/"
"transform": "ml:transform"
},
"@type": "sc:Dataset",
"name": "mydataset",
Expand Down
11 changes: 2 additions & 9 deletions python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/metadata_bad_type/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,8 @@
"@context": {
"@language": "en",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "ml:column",
"conformsTo": "dct:conformsTo",
"cr": "http://mlcommons.org/croissant/",
"data": {
"@id": "ml:data",
"@type": "@json"
Expand All @@ -20,15 +18,11 @@
"extract": "ml:extract",
"field": "ml:field",
"fileProperty": "ml:fileProperty",
"fileObject": "cr:fileObject",
"fileSet": "cr:fileSet",
"format": "ml:format",
"includes": "ml:includes",
"isEnumeration": "ml:isEnumeration",
"isLiveDataset": "cr:isLiveDataset",
"jsonPath": "ml:jsonPath",
"key": "cr:key",
"md5": "cr:md5",
"ml": "http://mlcommons.org/schema/",
"parentField": "ml:parentField",
"path": "ml:path",
"personalSensitiveInformation": "ml:personalSensitiveInformation",
Expand All @@ -41,8 +35,7 @@
"separator": "ml:separator",
"source": "ml:source",
"subField": "ml:subField",
"transform": "ml:transform",
"ml": "http://mlcommons.org/schema/"
"transform": "ml:transform"
},
"@type": "sc:WRONG_TYPE",
"name": "mydataset",
Expand Down
11 changes: 2 additions & 9 deletions ...lcroissant/mlcroissant/_src/tests/graphs/0.8/metadata_missing_property_name/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,8 @@
"@context": {
"@language": "en",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "ml:column",
"conformsTo": "dct:conformsTo",
"cr": "http://mlcommons.org/croissant/",
"data": {
"@id": "ml:data",
"@type": "@json"
Expand All @@ -20,15 +18,11 @@
"extract": "ml:extract",
"field": "ml:field",
"fileProperty": "ml:fileProperty",
"fileObject": "cr:fileObject",
"fileSet": "cr:fileSet",
"format": "ml:format",
"includes": "ml:includes",
"isEnumeration": "ml:isEnumeration",
"isLiveDataset": "cr:isLiveDataset",
"jsonPath": "ml:jsonPath",
"key": "cr:key",
"md5": "cr:md5",
"ml": "http://mlcommons.org/schema/",
"parentField": "ml:parentField",
"path": "ml:path",
"personalSensitiveInformation": "ml:personalSensitiveInformation",
Expand All @@ -41,8 +35,7 @@
"separator": "ml:separator",
"source": "ml:source",
"subField": "ml:subField",
"transform": "ml:transform",
"ml": "http://mlcommons.org/schema/"
"transform": "ml:transform"
},
"@type": "sc:Dataset",
"description": "This is a description.",
Expand Down
11 changes: 2 additions & 9 deletions python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_bad_source/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,8 @@
"@context": {
"@language": "en",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "ml:column",
"conformsTo": "dct:conformsTo",
"cr": "http://mlcommons.org/croissant/",
"data": {
"@id": "ml:data",
"@type": "@json"
Expand All @@ -20,15 +18,11 @@
"extract": "ml:extract",
"field": "ml:field",
"fileProperty": "ml:fileProperty",
"fileObject": "cr:fileObject",
"fileSet": "cr:fileSet",
"format": "ml:format",
"includes": "ml:includes",
"isEnumeration": "ml:isEnumeration",
"isLiveDataset": "cr:isLiveDataset",
"jsonPath": "ml:jsonPath",
"key": "cr:key",
"md5": "cr:md5",
"ml": "http://mlcommons.org/schema/",
"parentField": "ml:parentField",
"path": "ml:path",
"personalSensitiveInformation": "ml:personalSensitiveInformation",
Expand All @@ -41,8 +35,7 @@
"separator": "ml:separator",
"source": "ml:source",
"subField": "ml:subField",
"transform": "ml:transform",
"ml": "http://mlcommons.org/schema/"
"transform": "ml:transform"
},
"@type": "sc:Dataset",
"name": "mydataset",
Expand Down
11 changes: 2 additions & 9 deletions python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_bad_type/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,8 @@
"@context": {
"@language": "en",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "ml:column",
"conformsTo": "dct:conformsTo",
"cr": "http://mlcommons.org/croissant/",
"data": {
"@id": "ml:data",
"@type": "@json"
Expand All @@ -20,15 +18,11 @@
"extract": "ml:extract",
"field": "ml:field",
"fileProperty": "ml:fileProperty",
"fileObject": "cr:fileObject",
"fileSet": "cr:fileSet",
"format": "ml:format",
"includes": "ml:includes",
"isEnumeration": "ml:isEnumeration",
"isLiveDataset": "cr:isLiveDataset",
"jsonPath": "ml:jsonPath",
"key": "cr:key",
"md5": "cr:md5",
"ml": "http://mlcommons.org/schema/",
"parentField": "ml:parentField",
"path": "ml:path",
"personalSensitiveInformation": "ml:personalSensitiveInformation",
Expand All @@ -41,8 +35,7 @@
"separator": "ml:separator",
"source": "ml:source",
"subField": "ml:subField",
"transform": "ml:transform",
"ml": "http://mlcommons.org/schema/"
"transform": "ml:transform"
},
"@type": "sc:Dataset",
"name": "mydataset",
Expand Down
11 changes: 2 additions & 9 deletions ...mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_missing_property_name/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,8 @@
"@context": {
"@language": "en",
"@vocab": "https://schema.org/",
"citeAs": "cr:citeAs",
"column": "ml:column",
"conformsTo": "dct:conformsTo",
"cr": "http://mlcommons.org/croissant/",
"data": {
"@id": "ml:data",
"@type": "@json"
Expand All @@ -20,15 +18,11 @@
"extract": "ml:extract",
"field": "ml:field",
"fileProperty": "ml:fileProperty",
"fileObject": "cr:fileObject",
"fileSet": "cr:fileSet",
"format": "ml:format",
"includes": "ml:includes",
"isEnumeration": "ml:isEnumeration",
"isLiveDataset": "cr:isLiveDataset",
"jsonPath": "ml:jsonPath",
"key": "cr:key",
"md5": "cr:md5",
"ml": "http://mlcommons.org/schema/",
"parentField": "ml:parentField",
"path": "ml:path",
"personalSensitiveInformation": "ml:personalSensitiveInformation",
Expand All @@ -41,8 +35,7 @@
"separator": "ml:separator",
"source": "ml:source",
"subField": "ml:subField",
"transform": "ml:transform",
"ml": "http://mlcommons.org/schema/"
"transform": "ml:transform"
},
"@type": "sc:Dataset",
"name": "mydataset",
Expand Down
Loading
Loading