@huggingface/tasks 0.11.2 → 0.11.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/index.cjs +174 -9
- package/dist/index.js +174 -9
- package/dist/src/dataset-libraries.d.ts +6 -0
- package/dist/src/dataset-libraries.d.ts.map +1 -1
- package/dist/src/model-libraries-snippets.d.ts +1 -0
- package/dist/src/model-libraries-snippets.d.ts.map +1 -1
- package/dist/src/model-libraries.d.ts +16 -2
- package/dist/src/model-libraries.d.ts.map +1 -1
- package/dist/src/tasks/document-question-answering/data.d.ts.map +1 -1
- package/dist/src/tasks/image-feature-extraction/data.d.ts.map +1 -1
- package/dist/src/tasks/image-text-to-text/data.d.ts.map +1 -1
- package/dist/src/tasks/image-to-3d/data.d.ts +4 -0
- package/dist/src/tasks/image-to-3d/data.d.ts.map +1 -0
- package/dist/src/tasks/index.d.ts.map +1 -1
- package/dist/src/tasks/text-to-3d/data.d.ts +4 -0
- package/dist/src/tasks/text-to-3d/data.d.ts.map +1 -0
- package/package.json +1 -1
- package/src/dataset-libraries.ts +6 -0
- package/src/model-libraries-snippets.ts +6 -0
- package/src/model-libraries.ts +14 -0
- package/src/tasks/document-question-answering/data.ts +6 -3
- package/src/tasks/image-feature-extraction/data.ts +4 -0
- package/src/tasks/image-text-to-text/data.ts +6 -2
- package/src/tasks/image-to-3d/about.md +62 -0
- package/src/tasks/image-to-3d/data.ts +75 -0
- package/src/tasks/index.ts +6 -4
- package/src/tasks/text-to-3d/about.md +62 -0
- package/src/tasks/text-to-3d/data.ts +56 -0
package/dist/index.cjs
CHANGED
|
@@ -1617,7 +1617,10 @@ var data_default3 = taskData3;
|
|
|
1617
1617
|
var taskData4 = {
|
|
1618
1618
|
datasets: [
|
|
1619
1619
|
{
|
|
1620
|
-
|
|
1620
|
+
description: "Largest document understanding dataset.",
|
|
1621
|
+
id: "HuggingFaceM4/Docmatix"
|
|
1622
|
+
},
|
|
1623
|
+
{
|
|
1621
1624
|
description: "Dataset from the 2020 DocVQA challenge. The documents are taken from the UCSF Industry Documents Library.",
|
|
1622
1625
|
id: "eliolio/docvqa"
|
|
1623
1626
|
}
|
|
@@ -1658,8 +1661,8 @@ var taskData4 = {
|
|
|
1658
1661
|
id: "impira/layoutlm-document-qa"
|
|
1659
1662
|
},
|
|
1660
1663
|
{
|
|
1661
|
-
description: "A special model for OCR-free Document QA task.
|
|
1662
|
-
id: "
|
|
1664
|
+
description: "A special model for OCR-free Document QA task.",
|
|
1665
|
+
id: "microsoft/udop-large"
|
|
1663
1666
|
},
|
|
1664
1667
|
{
|
|
1665
1668
|
description: "A powerful model for document question answering.",
|
|
@@ -1939,6 +1942,10 @@ var taskData8 = {
|
|
|
1939
1942
|
{
|
|
1940
1943
|
description: "A robust image feature extraction models.",
|
|
1941
1944
|
id: "facebook/dino-vitb16"
|
|
1945
|
+
},
|
|
1946
|
+
{
|
|
1947
|
+
description: "Strong image-text-to-text model made for information retrieval from documents.",
|
|
1948
|
+
id: "vidore/colpali"
|
|
1942
1949
|
}
|
|
1943
1950
|
],
|
|
1944
1951
|
spaces: [],
|
|
@@ -2165,8 +2172,8 @@ var taskData11 = {
|
|
|
2165
2172
|
metrics: [],
|
|
2166
2173
|
models: [
|
|
2167
2174
|
{
|
|
2168
|
-
description: "Cutting-edge vision language model that can
|
|
2169
|
-
id: "
|
|
2175
|
+
description: "Cutting-edge vision language model that can take multiple image inputs.",
|
|
2176
|
+
id: "facebook/chameleon-7b"
|
|
2170
2177
|
},
|
|
2171
2178
|
{
|
|
2172
2179
|
description: "Cutting-edge conversational vision language model that can take multiple image inputs.",
|
|
@@ -2179,6 +2186,10 @@ var taskData11 = {
|
|
|
2179
2186
|
{
|
|
2180
2187
|
description: "Strong image-text-to-text model made to understand documents.",
|
|
2181
2188
|
id: "mPLUG/DocOwl1.5"
|
|
2189
|
+
},
|
|
2190
|
+
{
|
|
2191
|
+
description: "Strong image-text-to-text model.",
|
|
2192
|
+
id: "llava-hf/llava-v1.6-mistral-7b-hf"
|
|
2182
2193
|
}
|
|
2183
2194
|
],
|
|
2184
2195
|
spaces: [
|
|
@@ -4034,6 +4045,135 @@ var taskData36 = {
|
|
|
4034
4045
|
};
|
|
4035
4046
|
var data_default36 = taskData36;
|
|
4036
4047
|
|
|
4048
|
+
// src/tasks/image-to-3d/data.ts
|
|
4049
|
+
var taskData37 = {
|
|
4050
|
+
datasets: [
|
|
4051
|
+
{
|
|
4052
|
+
description: "A large dataset of over 10 million 3D objects.",
|
|
4053
|
+
id: "allenai/objaverse-xl"
|
|
4054
|
+
},
|
|
4055
|
+
{
|
|
4056
|
+
description: "A dataset of isolated object images for evaluating image-to-3D models.",
|
|
4057
|
+
id: "dylanebert/iso3d"
|
|
4058
|
+
}
|
|
4059
|
+
],
|
|
4060
|
+
demo: {
|
|
4061
|
+
inputs: [
|
|
4062
|
+
{
|
|
4063
|
+
filename: "image-to-3d-image-input.png",
|
|
4064
|
+
type: "img"
|
|
4065
|
+
}
|
|
4066
|
+
],
|
|
4067
|
+
outputs: [
|
|
4068
|
+
{
|
|
4069
|
+
label: "Result",
|
|
4070
|
+
content: "image-to-3d-3d-output-filename.glb",
|
|
4071
|
+
type: "text"
|
|
4072
|
+
}
|
|
4073
|
+
]
|
|
4074
|
+
},
|
|
4075
|
+
metrics: [],
|
|
4076
|
+
models: [
|
|
4077
|
+
{
|
|
4078
|
+
description: "Fast image-to-3D mesh model by Tencent.",
|
|
4079
|
+
id: "TencentARC/InstantMesh"
|
|
4080
|
+
},
|
|
4081
|
+
{
|
|
4082
|
+
description: "Fast image-to-3D mesh model by StabilityAI",
|
|
4083
|
+
id: "stabilityai/TripoSR"
|
|
4084
|
+
},
|
|
4085
|
+
{
|
|
4086
|
+
description: "A scaled up image-to-3D mesh model derived from TripoSR.",
|
|
4087
|
+
id: "hwjiang/Real3D"
|
|
4088
|
+
},
|
|
4089
|
+
{
|
|
4090
|
+
description: "Generative 3D gaussian splatting model.",
|
|
4091
|
+
id: "ashawkey/LGM"
|
|
4092
|
+
}
|
|
4093
|
+
],
|
|
4094
|
+
spaces: [
|
|
4095
|
+
{
|
|
4096
|
+
description: "Leaderboard to evaluate image-to-3D models.",
|
|
4097
|
+
id: "dylanebert/3d-arena"
|
|
4098
|
+
},
|
|
4099
|
+
{
|
|
4100
|
+
description: "Image-to-3D demo with mesh outputs.",
|
|
4101
|
+
id: "TencentARC/InstantMesh"
|
|
4102
|
+
},
|
|
4103
|
+
{
|
|
4104
|
+
description: "Image-to-3D demo with mesh outputs.",
|
|
4105
|
+
id: "stabilityai/TripoSR"
|
|
4106
|
+
},
|
|
4107
|
+
{
|
|
4108
|
+
description: "Image-to-3D demo with mesh outputs.",
|
|
4109
|
+
id: "hwjiang/Real3D"
|
|
4110
|
+
},
|
|
4111
|
+
{
|
|
4112
|
+
description: "Image-to-3D demo with splat outputs.",
|
|
4113
|
+
id: "dylanebert/LGM-mini"
|
|
4114
|
+
}
|
|
4115
|
+
],
|
|
4116
|
+
summary: "Image-to-3D models take in image input and produce 3D output.",
|
|
4117
|
+
widgetModels: [],
|
|
4118
|
+
youtubeId: ""
|
|
4119
|
+
};
|
|
4120
|
+
var data_default37 = taskData37;
|
|
4121
|
+
|
|
4122
|
+
// src/tasks/text-to-3d/data.ts
|
|
4123
|
+
var taskData38 = {
|
|
4124
|
+
datasets: [
|
|
4125
|
+
{
|
|
4126
|
+
description: "A large dataset of over 10 million 3D objects.",
|
|
4127
|
+
id: "allenai/objaverse-xl"
|
|
4128
|
+
},
|
|
4129
|
+
{
|
|
4130
|
+
description: "Descriptive captions for 3D objects in Objaverse.",
|
|
4131
|
+
id: "tiange/Cap3D"
|
|
4132
|
+
}
|
|
4133
|
+
],
|
|
4134
|
+
demo: {
|
|
4135
|
+
inputs: [
|
|
4136
|
+
{
|
|
4137
|
+
label: "Prompt",
|
|
4138
|
+
content: "a cat statue",
|
|
4139
|
+
type: "text"
|
|
4140
|
+
}
|
|
4141
|
+
],
|
|
4142
|
+
outputs: [
|
|
4143
|
+
{
|
|
4144
|
+
label: "Result",
|
|
4145
|
+
content: "text-to-3d-3d-output-filename.glb",
|
|
4146
|
+
type: "text"
|
|
4147
|
+
}
|
|
4148
|
+
]
|
|
4149
|
+
},
|
|
4150
|
+
metrics: [],
|
|
4151
|
+
models: [
|
|
4152
|
+
{
|
|
4153
|
+
description: "Text-to-3D mesh model by OpenAI",
|
|
4154
|
+
id: "openai/shap-e"
|
|
4155
|
+
},
|
|
4156
|
+
{
|
|
4157
|
+
description: "Generative 3D gaussian splatting model.",
|
|
4158
|
+
id: "ashawkey/LGM"
|
|
4159
|
+
}
|
|
4160
|
+
],
|
|
4161
|
+
spaces: [
|
|
4162
|
+
{
|
|
4163
|
+
description: "Text-to-3D demo with mesh outputs.",
|
|
4164
|
+
id: "hysts/Shap-E"
|
|
4165
|
+
},
|
|
4166
|
+
{
|
|
4167
|
+
description: "Text/image-to-3D demo with splat outputs.",
|
|
4168
|
+
id: "ashawkey/LGM"
|
|
4169
|
+
}
|
|
4170
|
+
],
|
|
4171
|
+
summary: "Text-to-3D models take in text input and produce 3D output.",
|
|
4172
|
+
widgetModels: [],
|
|
4173
|
+
youtubeId: ""
|
|
4174
|
+
};
|
|
4175
|
+
var data_default38 = taskData38;
|
|
4176
|
+
|
|
4037
4177
|
// src/tasks/index.ts
|
|
4038
4178
|
var TASKS_MODEL_LIBRARIES = {
|
|
4039
4179
|
"audio-classification": ["speechbrain", "transformers", "transformers.js"],
|
|
@@ -4091,8 +4231,8 @@ var TASKS_MODEL_LIBRARIES = {
|
|
|
4091
4231
|
"zero-shot-classification": ["transformers", "transformers.js"],
|
|
4092
4232
|
"zero-shot-image-classification": ["transformers", "transformers.js"],
|
|
4093
4233
|
"zero-shot-object-detection": ["transformers", "transformers.js"],
|
|
4094
|
-
"text-to-3d": [],
|
|
4095
|
-
"image-to-3d": []
|
|
4234
|
+
"text-to-3d": ["diffusers"],
|
|
4235
|
+
"image-to-3d": ["diffusers"]
|
|
4096
4236
|
};
|
|
4097
4237
|
function getData(type, partialTaskData = data_default16) {
|
|
4098
4238
|
return {
|
|
@@ -4150,8 +4290,8 @@ var TASKS_DATA = {
|
|
|
4150
4290
|
"zero-shot-classification": getData("zero-shot-classification", data_default34),
|
|
4151
4291
|
"zero-shot-image-classification": getData("zero-shot-image-classification", data_default35),
|
|
4152
4292
|
"zero-shot-object-detection": getData("zero-shot-object-detection", data_default36),
|
|
4153
|
-
"text-to-3d": getData("text-to-3d",
|
|
4154
|
-
"image-to-3d": getData("image-to-3d",
|
|
4293
|
+
"text-to-3d": getData("text-to-3d", data_default38),
|
|
4294
|
+
"image-to-3d": getData("image-to-3d", data_default37)
|
|
4155
4295
|
};
|
|
4156
4296
|
|
|
4157
4297
|
// src/model-libraries-snippets.ts
|
|
@@ -4390,6 +4530,11 @@ from huggingface_hub import from_pretrained_keras
|
|
|
4390
4530
|
model = from_pretrained_keras("${model.id}")
|
|
4391
4531
|
`
|
|
4392
4532
|
];
|
|
4533
|
+
var mamba_ssm = (model) => [
|
|
4534
|
+
`from mamba_ssm import MambaLMHeadModel
|
|
4535
|
+
|
|
4536
|
+
model = MambaLMHeadModel.from_pretrained("${model.id}")`
|
|
4537
|
+
];
|
|
4393
4538
|
var mars5_tts = (model) => [
|
|
4394
4539
|
`# Install from https://github.com/Camb-ai/MARS5-TTS
|
|
4395
4540
|
|
|
@@ -5104,11 +5249,25 @@ var MODEL_LIBRARIES_UI_ELEMENTS = {
|
|
|
5104
5249
|
repoName: "k2",
|
|
5105
5250
|
repoUrl: "https://github.com/k2-fsa/k2"
|
|
5106
5251
|
},
|
|
5252
|
+
liveportrait: {
|
|
5253
|
+
prettyLabel: "LivePortrait",
|
|
5254
|
+
repoName: "LivePortrait",
|
|
5255
|
+
repoUrl: "https://github.com/KwaiVGI/LivePortrait",
|
|
5256
|
+
filter: false,
|
|
5257
|
+
countDownloads: `path:"liveportrait/landmark.onnx"`
|
|
5258
|
+
},
|
|
5107
5259
|
mindspore: {
|
|
5108
5260
|
prettyLabel: "MindSpore",
|
|
5109
5261
|
repoName: "mindspore",
|
|
5110
5262
|
repoUrl: "https://github.com/mindspore-ai/mindspore"
|
|
5111
5263
|
},
|
|
5264
|
+
"mamba-ssm": {
|
|
5265
|
+
prettyLabel: "MambaSSM",
|
|
5266
|
+
repoName: "MambaSSM",
|
|
5267
|
+
repoUrl: "https://github.com/state-spaces/mamba",
|
|
5268
|
+
filter: false,
|
|
5269
|
+
snippets: mamba_ssm
|
|
5270
|
+
},
|
|
5112
5271
|
"mars5-tts": {
|
|
5113
5272
|
prettyLabel: "MARS5-TTS",
|
|
5114
5273
|
repoName: "MARS5-TTS",
|
|
@@ -6478,6 +6637,12 @@ var DATASET_LIBRARIES_UI_ELEMENTS = {
|
|
|
6478
6637
|
repoName: "argilla",
|
|
6479
6638
|
repoUrl: "https://github.com/argilla-io/argilla",
|
|
6480
6639
|
docsUrl: "https://argilla-io.github.io/argilla"
|
|
6640
|
+
},
|
|
6641
|
+
polars: {
|
|
6642
|
+
prettyLabel: "Polars",
|
|
6643
|
+
repoName: "polars",
|
|
6644
|
+
repoUrl: "https://github.com/pola-rs/polars",
|
|
6645
|
+
docsUrl: "https://docs.pola.rs/"
|
|
6481
6646
|
}
|
|
6482
6647
|
};
|
|
6483
6648
|
// Annotate the CommonJS export names for ESM import in node:
|
package/dist/index.js
CHANGED
|
@@ -1579,7 +1579,10 @@ var data_default3 = taskData3;
|
|
|
1579
1579
|
var taskData4 = {
|
|
1580
1580
|
datasets: [
|
|
1581
1581
|
{
|
|
1582
|
-
|
|
1582
|
+
description: "Largest document understanding dataset.",
|
|
1583
|
+
id: "HuggingFaceM4/Docmatix"
|
|
1584
|
+
},
|
|
1585
|
+
{
|
|
1583
1586
|
description: "Dataset from the 2020 DocVQA challenge. The documents are taken from the UCSF Industry Documents Library.",
|
|
1584
1587
|
id: "eliolio/docvqa"
|
|
1585
1588
|
}
|
|
@@ -1620,8 +1623,8 @@ var taskData4 = {
|
|
|
1620
1623
|
id: "impira/layoutlm-document-qa"
|
|
1621
1624
|
},
|
|
1622
1625
|
{
|
|
1623
|
-
description: "A special model for OCR-free Document QA task.
|
|
1624
|
-
id: "
|
|
1626
|
+
description: "A special model for OCR-free Document QA task.",
|
|
1627
|
+
id: "microsoft/udop-large"
|
|
1625
1628
|
},
|
|
1626
1629
|
{
|
|
1627
1630
|
description: "A powerful model for document question answering.",
|
|
@@ -1901,6 +1904,10 @@ var taskData8 = {
|
|
|
1901
1904
|
{
|
|
1902
1905
|
description: "A robust image feature extraction models.",
|
|
1903
1906
|
id: "facebook/dino-vitb16"
|
|
1907
|
+
},
|
|
1908
|
+
{
|
|
1909
|
+
description: "Strong image-text-to-text model made for information retrieval from documents.",
|
|
1910
|
+
id: "vidore/colpali"
|
|
1904
1911
|
}
|
|
1905
1912
|
],
|
|
1906
1913
|
spaces: [],
|
|
@@ -2127,8 +2134,8 @@ var taskData11 = {
|
|
|
2127
2134
|
metrics: [],
|
|
2128
2135
|
models: [
|
|
2129
2136
|
{
|
|
2130
|
-
description: "Cutting-edge vision language model that can
|
|
2131
|
-
id: "
|
|
2137
|
+
description: "Cutting-edge vision language model that can take multiple image inputs.",
|
|
2138
|
+
id: "facebook/chameleon-7b"
|
|
2132
2139
|
},
|
|
2133
2140
|
{
|
|
2134
2141
|
description: "Cutting-edge conversational vision language model that can take multiple image inputs.",
|
|
@@ -2141,6 +2148,10 @@ var taskData11 = {
|
|
|
2141
2148
|
{
|
|
2142
2149
|
description: "Strong image-text-to-text model made to understand documents.",
|
|
2143
2150
|
id: "mPLUG/DocOwl1.5"
|
|
2151
|
+
},
|
|
2152
|
+
{
|
|
2153
|
+
description: "Strong image-text-to-text model.",
|
|
2154
|
+
id: "llava-hf/llava-v1.6-mistral-7b-hf"
|
|
2144
2155
|
}
|
|
2145
2156
|
],
|
|
2146
2157
|
spaces: [
|
|
@@ -3996,6 +4007,135 @@ var taskData36 = {
|
|
|
3996
4007
|
};
|
|
3997
4008
|
var data_default36 = taskData36;
|
|
3998
4009
|
|
|
4010
|
+
// src/tasks/image-to-3d/data.ts
|
|
4011
|
+
var taskData37 = {
|
|
4012
|
+
datasets: [
|
|
4013
|
+
{
|
|
4014
|
+
description: "A large dataset of over 10 million 3D objects.",
|
|
4015
|
+
id: "allenai/objaverse-xl"
|
|
4016
|
+
},
|
|
4017
|
+
{
|
|
4018
|
+
description: "A dataset of isolated object images for evaluating image-to-3D models.",
|
|
4019
|
+
id: "dylanebert/iso3d"
|
|
4020
|
+
}
|
|
4021
|
+
],
|
|
4022
|
+
demo: {
|
|
4023
|
+
inputs: [
|
|
4024
|
+
{
|
|
4025
|
+
filename: "image-to-3d-image-input.png",
|
|
4026
|
+
type: "img"
|
|
4027
|
+
}
|
|
4028
|
+
],
|
|
4029
|
+
outputs: [
|
|
4030
|
+
{
|
|
4031
|
+
label: "Result",
|
|
4032
|
+
content: "image-to-3d-3d-output-filename.glb",
|
|
4033
|
+
type: "text"
|
|
4034
|
+
}
|
|
4035
|
+
]
|
|
4036
|
+
},
|
|
4037
|
+
metrics: [],
|
|
4038
|
+
models: [
|
|
4039
|
+
{
|
|
4040
|
+
description: "Fast image-to-3D mesh model by Tencent.",
|
|
4041
|
+
id: "TencentARC/InstantMesh"
|
|
4042
|
+
},
|
|
4043
|
+
{
|
|
4044
|
+
description: "Fast image-to-3D mesh model by StabilityAI",
|
|
4045
|
+
id: "stabilityai/TripoSR"
|
|
4046
|
+
},
|
|
4047
|
+
{
|
|
4048
|
+
description: "A scaled up image-to-3D mesh model derived from TripoSR.",
|
|
4049
|
+
id: "hwjiang/Real3D"
|
|
4050
|
+
},
|
|
4051
|
+
{
|
|
4052
|
+
description: "Generative 3D gaussian splatting model.",
|
|
4053
|
+
id: "ashawkey/LGM"
|
|
4054
|
+
}
|
|
4055
|
+
],
|
|
4056
|
+
spaces: [
|
|
4057
|
+
{
|
|
4058
|
+
description: "Leaderboard to evaluate image-to-3D models.",
|
|
4059
|
+
id: "dylanebert/3d-arena"
|
|
4060
|
+
},
|
|
4061
|
+
{
|
|
4062
|
+
description: "Image-to-3D demo with mesh outputs.",
|
|
4063
|
+
id: "TencentARC/InstantMesh"
|
|
4064
|
+
},
|
|
4065
|
+
{
|
|
4066
|
+
description: "Image-to-3D demo with mesh outputs.",
|
|
4067
|
+
id: "stabilityai/TripoSR"
|
|
4068
|
+
},
|
|
4069
|
+
{
|
|
4070
|
+
description: "Image-to-3D demo with mesh outputs.",
|
|
4071
|
+
id: "hwjiang/Real3D"
|
|
4072
|
+
},
|
|
4073
|
+
{
|
|
4074
|
+
description: "Image-to-3D demo with splat outputs.",
|
|
4075
|
+
id: "dylanebert/LGM-mini"
|
|
4076
|
+
}
|
|
4077
|
+
],
|
|
4078
|
+
summary: "Image-to-3D models take in image input and produce 3D output.",
|
|
4079
|
+
widgetModels: [],
|
|
4080
|
+
youtubeId: ""
|
|
4081
|
+
};
|
|
4082
|
+
var data_default37 = taskData37;
|
|
4083
|
+
|
|
4084
|
+
// src/tasks/text-to-3d/data.ts
|
|
4085
|
+
var taskData38 = {
|
|
4086
|
+
datasets: [
|
|
4087
|
+
{
|
|
4088
|
+
description: "A large dataset of over 10 million 3D objects.",
|
|
4089
|
+
id: "allenai/objaverse-xl"
|
|
4090
|
+
},
|
|
4091
|
+
{
|
|
4092
|
+
description: "Descriptive captions for 3D objects in Objaverse.",
|
|
4093
|
+
id: "tiange/Cap3D"
|
|
4094
|
+
}
|
|
4095
|
+
],
|
|
4096
|
+
demo: {
|
|
4097
|
+
inputs: [
|
|
4098
|
+
{
|
|
4099
|
+
label: "Prompt",
|
|
4100
|
+
content: "a cat statue",
|
|
4101
|
+
type: "text"
|
|
4102
|
+
}
|
|
4103
|
+
],
|
|
4104
|
+
outputs: [
|
|
4105
|
+
{
|
|
4106
|
+
label: "Result",
|
|
4107
|
+
content: "text-to-3d-3d-output-filename.glb",
|
|
4108
|
+
type: "text"
|
|
4109
|
+
}
|
|
4110
|
+
]
|
|
4111
|
+
},
|
|
4112
|
+
metrics: [],
|
|
4113
|
+
models: [
|
|
4114
|
+
{
|
|
4115
|
+
description: "Text-to-3D mesh model by OpenAI",
|
|
4116
|
+
id: "openai/shap-e"
|
|
4117
|
+
},
|
|
4118
|
+
{
|
|
4119
|
+
description: "Generative 3D gaussian splatting model.",
|
|
4120
|
+
id: "ashawkey/LGM"
|
|
4121
|
+
}
|
|
4122
|
+
],
|
|
4123
|
+
spaces: [
|
|
4124
|
+
{
|
|
4125
|
+
description: "Text-to-3D demo with mesh outputs.",
|
|
4126
|
+
id: "hysts/Shap-E"
|
|
4127
|
+
},
|
|
4128
|
+
{
|
|
4129
|
+
description: "Text/image-to-3D demo with splat outputs.",
|
|
4130
|
+
id: "ashawkey/LGM"
|
|
4131
|
+
}
|
|
4132
|
+
],
|
|
4133
|
+
summary: "Text-to-3D models take in text input and produce 3D output.",
|
|
4134
|
+
widgetModels: [],
|
|
4135
|
+
youtubeId: ""
|
|
4136
|
+
};
|
|
4137
|
+
var data_default38 = taskData38;
|
|
4138
|
+
|
|
3999
4139
|
// src/tasks/index.ts
|
|
4000
4140
|
var TASKS_MODEL_LIBRARIES = {
|
|
4001
4141
|
"audio-classification": ["speechbrain", "transformers", "transformers.js"],
|
|
@@ -4053,8 +4193,8 @@ var TASKS_MODEL_LIBRARIES = {
|
|
|
4053
4193
|
"zero-shot-classification": ["transformers", "transformers.js"],
|
|
4054
4194
|
"zero-shot-image-classification": ["transformers", "transformers.js"],
|
|
4055
4195
|
"zero-shot-object-detection": ["transformers", "transformers.js"],
|
|
4056
|
-
"text-to-3d": [],
|
|
4057
|
-
"image-to-3d": []
|
|
4196
|
+
"text-to-3d": ["diffusers"],
|
|
4197
|
+
"image-to-3d": ["diffusers"]
|
|
4058
4198
|
};
|
|
4059
4199
|
function getData(type, partialTaskData = data_default16) {
|
|
4060
4200
|
return {
|
|
@@ -4112,8 +4252,8 @@ var TASKS_DATA = {
|
|
|
4112
4252
|
"zero-shot-classification": getData("zero-shot-classification", data_default34),
|
|
4113
4253
|
"zero-shot-image-classification": getData("zero-shot-image-classification", data_default35),
|
|
4114
4254
|
"zero-shot-object-detection": getData("zero-shot-object-detection", data_default36),
|
|
4115
|
-
"text-to-3d": getData("text-to-3d",
|
|
4116
|
-
"image-to-3d": getData("image-to-3d",
|
|
4255
|
+
"text-to-3d": getData("text-to-3d", data_default38),
|
|
4256
|
+
"image-to-3d": getData("image-to-3d", data_default37)
|
|
4117
4257
|
};
|
|
4118
4258
|
|
|
4119
4259
|
// src/model-libraries-snippets.ts
|
|
@@ -4352,6 +4492,11 @@ from huggingface_hub import from_pretrained_keras
|
|
|
4352
4492
|
model = from_pretrained_keras("${model.id}")
|
|
4353
4493
|
`
|
|
4354
4494
|
];
|
|
4495
|
+
var mamba_ssm = (model) => [
|
|
4496
|
+
`from mamba_ssm import MambaLMHeadModel
|
|
4497
|
+
|
|
4498
|
+
model = MambaLMHeadModel.from_pretrained("${model.id}")`
|
|
4499
|
+
];
|
|
4355
4500
|
var mars5_tts = (model) => [
|
|
4356
4501
|
`# Install from https://github.com/Camb-ai/MARS5-TTS
|
|
4357
4502
|
|
|
@@ -5066,11 +5211,25 @@ var MODEL_LIBRARIES_UI_ELEMENTS = {
|
|
|
5066
5211
|
repoName: "k2",
|
|
5067
5212
|
repoUrl: "https://github.com/k2-fsa/k2"
|
|
5068
5213
|
},
|
|
5214
|
+
liveportrait: {
|
|
5215
|
+
prettyLabel: "LivePortrait",
|
|
5216
|
+
repoName: "LivePortrait",
|
|
5217
|
+
repoUrl: "https://github.com/KwaiVGI/LivePortrait",
|
|
5218
|
+
filter: false,
|
|
5219
|
+
countDownloads: `path:"liveportrait/landmark.onnx"`
|
|
5220
|
+
},
|
|
5069
5221
|
mindspore: {
|
|
5070
5222
|
prettyLabel: "MindSpore",
|
|
5071
5223
|
repoName: "mindspore",
|
|
5072
5224
|
repoUrl: "https://github.com/mindspore-ai/mindspore"
|
|
5073
5225
|
},
|
|
5226
|
+
"mamba-ssm": {
|
|
5227
|
+
prettyLabel: "MambaSSM",
|
|
5228
|
+
repoName: "MambaSSM",
|
|
5229
|
+
repoUrl: "https://github.com/state-spaces/mamba",
|
|
5230
|
+
filter: false,
|
|
5231
|
+
snippets: mamba_ssm
|
|
5232
|
+
},
|
|
5074
5233
|
"mars5-tts": {
|
|
5075
5234
|
prettyLabel: "MARS5-TTS",
|
|
5076
5235
|
repoName: "MARS5-TTS",
|
|
@@ -6440,6 +6599,12 @@ var DATASET_LIBRARIES_UI_ELEMENTS = {
|
|
|
6440
6599
|
repoName: "argilla",
|
|
6441
6600
|
repoUrl: "https://github.com/argilla-io/argilla",
|
|
6442
6601
|
docsUrl: "https://argilla-io.github.io/argilla"
|
|
6602
|
+
},
|
|
6603
|
+
polars: {
|
|
6604
|
+
prettyLabel: "Polars",
|
|
6605
|
+
repoName: "polars",
|
|
6606
|
+
repoUrl: "https://github.com/pola-rs/polars",
|
|
6607
|
+
docsUrl: "https://docs.pola.rs/"
|
|
6443
6608
|
}
|
|
6444
6609
|
};
|
|
6445
6610
|
export {
|
|
@@ -70,6 +70,12 @@ export declare const DATASET_LIBRARIES_UI_ELEMENTS: {
|
|
|
70
70
|
repoUrl: string;
|
|
71
71
|
docsUrl: string;
|
|
72
72
|
};
|
|
73
|
+
polars: {
|
|
74
|
+
prettyLabel: string;
|
|
75
|
+
repoName: string;
|
|
76
|
+
repoUrl: string;
|
|
77
|
+
docsUrl: string;
|
|
78
|
+
};
|
|
73
79
|
};
|
|
74
80
|
export type DatasetLibraryKey = keyof typeof DATASET_LIBRARIES_UI_ELEMENTS;
|
|
75
81
|
//# sourceMappingURL=dataset-libraries.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"dataset-libraries.d.ts","sourceRoot":"","sources":["../../src/dataset-libraries.ts"],"names":[],"mappings":"AAAA;;GAEG;AACH,MAAM,WAAW,uBAAuB;IACvC;;;;OAIG;IACH,WAAW,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAC;IACjB;;OAEG;IACH,OAAO,EAAE,MAAM,CAAC;IAChB;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,CAAC;CACjB;AAED,eAAO,MAAM,6BAA6B
|
|
1
|
+
{"version":3,"file":"dataset-libraries.d.ts","sourceRoot":"","sources":["../../src/dataset-libraries.ts"],"names":[],"mappings":"AAAA;;GAEG;AACH,MAAM,WAAW,uBAAuB;IACvC;;;;OAIG;IACH,WAAW,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAC;IACjB;;OAEG;IACH,OAAO,EAAE,MAAM,CAAC;IAChB;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,CAAC;CACjB;AAED,eAAO,MAAM,6BAA6B;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAuDS,CAAC;AAGpD,MAAM,MAAM,iBAAiB,GAAG,MAAM,OAAO,6BAA6B,CAAC"}
|
|
@@ -17,6 +17,7 @@ export declare const gliner: (model: ModelData) => string[];
|
|
|
17
17
|
export declare const keras: (model: ModelData) => string[];
|
|
18
18
|
export declare const keras_nlp: (model: ModelData) => string[];
|
|
19
19
|
export declare const tf_keras: (model: ModelData) => string[];
|
|
20
|
+
export declare const mamba_ssm: (model: ModelData) => string[];
|
|
20
21
|
export declare const mars5_tts: (model: ModelData) => string[];
|
|
21
22
|
export declare const mesh_anything: () => string[];
|
|
22
23
|
export declare const open_clip: (model: ModelData) => string[];
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"model-libraries-snippets.d.ts","sourceRoot":"","sources":["../../src/model-libraries-snippets.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,cAAc,CAAC;AAY9C,eAAO,MAAM,QAAQ,UAAW,SAAS,KAAG,MAAM,EAKjD,CAAC;AAkBF,eAAO,MAAM,QAAQ,UAAW,SAAS,KAAG,MAAM,EAKjD,CAAC;AAEF,eAAO,MAAM,QAAQ,UAAW,SAAS,KAAG,MAAM,EAIjD,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAkBlD,CAAC;AAMF,eAAO,MAAM,QAAQ,UAAW,SAAS,KAAG,MAAM,EAIjD,CAAC;AAEF,eAAO,MAAM,KAAK,UAAW,SAAS,KAAG,MAAM,EAI9C,CAAC;AAEF,eAAO,MAAM,iBAAiB,UAAW,SAAS,KAAG,MAAM,EA6C1D,CAAC;AA+BF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAUlD,CAAC;AAEF,eAAO,MAAM,MAAM,UAAW,SAAS,KAAG,MAAM,EAgB/C,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAMlD,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EASlD,CAAC;AAIF,eAAO,MAAM,MAAM,UAAW,SAAS,KAAG,MAAM,EAO/C,CAAC;AAEF,eAAO,MAAM,OAAO,UAAW,SAAS,KAAG,MAAM,EAMhD,CAAC;AAEF,eAAO,MAAM,KAAK,UAAW,SAAS,KAAG,MAAM,EAI9C,CAAC;AAEF,eAAO,MAAM,MAAM,UAAW,SAAS,KAAG,MAAM,EAI/C,CAAC;AAEF,eAAO,MAAM,KAAK,UAAW,SAAS,KAAG,MAAM,EAS9C,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAUlD,CAAC;AAEF,eAAO,MAAM,QAAQ,UAAW,SAAS,KAAG,MAAM,EAOjD,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAKlD,CAAC;AAEF,eAAO,MAAM,aAAa,QAAO,MAAM,EAQtC,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAKlD,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAsBlD,CAAC;AAEF,eAAO,MAAM,uBAAuB,UAAW,SAAS,KAAG,MAAM,EAehE,CAAC;AAiBF,eAAO,MAAM,cAAc,UAAW,SAAS,KAAG,MAAM,EAKvD,CAAC;AAyBF,eAAO,MAAM,aAAa,UAAW,SAAS,KAAG,MAAM,EAOtD,CAAC;AAEF,eAAO,MAAM,IAAI,UAAW,SAAS,KAAG,MAAM,EAI7C,CAAC;AAsCF,eAAO,MAAM,OAAO,UAAW,SAAS,KAAG,MAAM,EAehD,CAAC;AAEF,eAAO,MAAM,kBAAkB,UAAW,SAAS,KAAG,MAAM,EAmC3D,CAAC;AAEF,eAAO,MAAM,MAAM,UAAW,SAAS,KAAG,MAAM,EAI/C,CAAC;AAEF,eAAO,MAAM,aAAa,UAAW,SAAS,KAAG,MAAM,EAEtD,CAAC;AAEF,eAAO,MAAM,oBAAoB,UAAW,SAAS,KAAG,MAAM,EAI7D,CAAC;AAEF,eAAO,MAAM,MAAM,UAAW,SAAS,KAAG,MAAM,EAI/C,CAAC;AAEF,eAAO,MAAM,KAAK,UAAW,SAAS,KAAG,MAAM,EAU9C,CAAC;AAEF,eAAO,MAAM,WAAW,UAAW,SAAS,KAAG,MAAM,EAIpD,CAAC;AAEF,eAAO,MAAM,MAAM,UAAW,SAAS,KAAG,MAAM,EAK/C,CAAC;AAkBF,eAAO,MAAM,WAAW,UAAW,SAAS,KAAG,MAAM,EAkBpD,CAAC;AAEF,eAAO,MAAM,YAAY,UAAW,SAAS,KAAG,MAAM,EA4CrD,CAAC;AAEF,eAAO,MAAM,cAAc,UAAW,SAAS,KAAG,MAAM,EAcvD,CAAC;AAiBF,eAAO,MAAM,IAAI,UAAW,SAAS,KAAG,MAAM,EAkB7C,CAAC;AAEF,eAAO,MAAM,QAAQ,UAAW,SAAS,KAAG,MAAM,EAKjD,CAAC;AAEF,eAAO,MAAM,gBAAgB,UAAW,SAAS,KAAG,MAAM,EAMzD,CAAC;AAgBF,eAAO,MAAM,QAAQ,UAAW,SAAS,KAAG,MAAM,EAEjD,CAAC;AAEF,eAAO,MAAM,MAAM,QAA6B,MAAM,EAMrD,CAAC;AAEF,eAAO,MAAM,UAAU,UAAW,SAAS,KAAG,MAAM,EAInD,CAAC;AAEF,eAAO,MAAM,OAAO,QAAO,MAAM,EAYhC,CAAC;AAEF,eAAO,MAAM,GAAG,UAAW,SAAS,KAAG,MAAM,EAK5C,CAAC;AAEF,eAAO,MAAM,KAAK,UAAW,SAAS,KAAG,MAAM,EAI9C,CAAC;AAEF,eAAO,MAAM,IAAI,UAAW,SAAS,KAAG,MAAM,EAQ7C,CAAC;AAEF,eAAO,MAAM,MAAM,UAAW,SAAS,KAAG,MAAM,EAI/C,CAAC;AA6BF,eAAO,MAAM,UAAU,UAAW,SAAS,KAAG,MAAM,EAUnD,CAAC;AAEF,eAAO,MAAM,UAAU,QAAO,MAAM,EAYnC,CAAC"}
|
|
1
|
+
{"version":3,"file":"model-libraries-snippets.d.ts","sourceRoot":"","sources":["../../src/model-libraries-snippets.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,cAAc,CAAC;AAY9C,eAAO,MAAM,QAAQ,UAAW,SAAS,KAAG,MAAM,EAKjD,CAAC;AAkBF,eAAO,MAAM,QAAQ,UAAW,SAAS,KAAG,MAAM,EAKjD,CAAC;AAEF,eAAO,MAAM,QAAQ,UAAW,SAAS,KAAG,MAAM,EAIjD,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAkBlD,CAAC;AAMF,eAAO,MAAM,QAAQ,UAAW,SAAS,KAAG,MAAM,EAIjD,CAAC;AAEF,eAAO,MAAM,KAAK,UAAW,SAAS,KAAG,MAAM,EAI9C,CAAC;AAEF,eAAO,MAAM,iBAAiB,UAAW,SAAS,KAAG,MAAM,EA6C1D,CAAC;AA+BF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAUlD,CAAC;AAEF,eAAO,MAAM,MAAM,UAAW,SAAS,KAAG,MAAM,EAgB/C,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAMlD,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EASlD,CAAC;AAIF,eAAO,MAAM,MAAM,UAAW,SAAS,KAAG,MAAM,EAO/C,CAAC;AAEF,eAAO,MAAM,OAAO,UAAW,SAAS,KAAG,MAAM,EAMhD,CAAC;AAEF,eAAO,MAAM,KAAK,UAAW,SAAS,KAAG,MAAM,EAI9C,CAAC;AAEF,eAAO,MAAM,MAAM,UAAW,SAAS,KAAG,MAAM,EAI/C,CAAC;AAEF,eAAO,MAAM,KAAK,UAAW,SAAS,KAAG,MAAM,EAS9C,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAUlD,CAAC;AAEF,eAAO,MAAM,QAAQ,UAAW,SAAS,KAAG,MAAM,EAOjD,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAIlD,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAKlD,CAAC;AAEF,eAAO,MAAM,aAAa,QAAO,MAAM,EAQtC,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAKlD,CAAC;AAEF,eAAO,MAAM,SAAS,UAAW,SAAS,KAAG,MAAM,EAsBlD,CAAC;AAEF,eAAO,MAAM,uBAAuB,UAAW,SAAS,KAAG,MAAM,EAehE,CAAC;AAiBF,eAAO,MAAM,cAAc,UAAW,SAAS,KAAG,MAAM,EAKvD,CAAC;AAyBF,eAAO,MAAM,aAAa,UAAW,SAAS,KAAG,MAAM,EAOtD,CAAC;AAEF,eAAO,MAAM,IAAI,UAAW,SAAS,KAAG,MAAM,EAI7C,CAAC;AAsCF,eAAO,MAAM,OAAO,UAAW,SAAS,KAAG,MAAM,EAehD,CAAC;AAEF,eAAO,MAAM,kBAAkB,UAAW,SAAS,KAAG,MAAM,EAmC3D,CAAC;AAEF,eAAO,MAAM,MAAM,UAAW,SAAS,KAAG,MAAM,EAI/C,CAAC;AAEF,eAAO,MAAM,aAAa,UAAW,SAAS,KAAG,MAAM,EAEtD,CAAC;AAEF,eAAO,MAAM,oBAAoB,UAAW,SAAS,KAAG,MAAM,EAI7D,CAAC;AAEF,eAAO,MAAM,MAAM,UAAW,SAAS,KAAG,MAAM,EAI/C,CAAC;AAEF,eAAO,MAAM,KAAK,UAAW,SAAS,KAAG,MAAM,EAU9C,CAAC;AAEF,eAAO,MAAM,WAAW,UAAW,SAAS,KAAG,MAAM,EAIpD,CAAC;AAEF,eAAO,MAAM,MAAM,UAAW,SAAS,KAAG,MAAM,EAK/C,CAAC;AAkBF,eAAO,MAAM,WAAW,UAAW,SAAS,KAAG,MAAM,EAkBpD,CAAC;AAEF,eAAO,MAAM,YAAY,UAAW,SAAS,KAAG,MAAM,EA4CrD,CAAC;AAEF,eAAO,MAAM,cAAc,UAAW,SAAS,KAAG,MAAM,EAcvD,CAAC;AAiBF,eAAO,MAAM,IAAI,UAAW,SAAS,KAAG,MAAM,EAkB7C,CAAC;AAEF,eAAO,MAAM,QAAQ,UAAW,SAAS,KAAG,MAAM,EAKjD,CAAC;AAEF,eAAO,MAAM,gBAAgB,UAAW,SAAS,KAAG,MAAM,EAMzD,CAAC;AAgBF,eAAO,MAAM,QAAQ,UAAW,SAAS,KAAG,MAAM,EAEjD,CAAC;AAEF,eAAO,MAAM,MAAM,QAA6B,MAAM,EAMrD,CAAC;AAEF,eAAO,MAAM,UAAU,UAAW,SAAS,KAAG,MAAM,EAInD,CAAC;AAEF,eAAO,MAAM,OAAO,QAAO,MAAM,EAYhC,CAAC;AAEF,eAAO,MAAM,GAAG,UAAW,SAAS,KAAG,MAAM,EAK5C,CAAC;AAEF,eAAO,MAAM,KAAK,UAAW,SAAS,KAAG,MAAM,EAI9C,CAAC;AAEF,eAAO,MAAM,IAAI,UAAW,SAAS,KAAG,MAAM,EAQ7C,CAAC;AAEF,eAAO,MAAM,MAAM,UAAW,SAAS,KAAG,MAAM,EAI/C,CAAC;AA6BF,eAAO,MAAM,UAAU,UAAW,SAAS,KAAG,MAAM,EAUnD,CAAC;AAEF,eAAO,MAAM,UAAU,QAAO,MAAM,EAYnC,CAAC"}
|
|
@@ -287,11 +287,25 @@ export declare const MODEL_LIBRARIES_UI_ELEMENTS: {
|
|
|
287
287
|
repoName: string;
|
|
288
288
|
repoUrl: string;
|
|
289
289
|
};
|
|
290
|
+
liveportrait: {
|
|
291
|
+
prettyLabel: string;
|
|
292
|
+
repoName: string;
|
|
293
|
+
repoUrl: string;
|
|
294
|
+
filter: false;
|
|
295
|
+
countDownloads: string;
|
|
296
|
+
};
|
|
290
297
|
mindspore: {
|
|
291
298
|
prettyLabel: string;
|
|
292
299
|
repoName: string;
|
|
293
300
|
repoUrl: string;
|
|
294
301
|
};
|
|
302
|
+
"mamba-ssm": {
|
|
303
|
+
prettyLabel: string;
|
|
304
|
+
repoName: string;
|
|
305
|
+
repoUrl: string;
|
|
306
|
+
filter: false;
|
|
307
|
+
snippets: (model: ModelData) => string[];
|
|
308
|
+
};
|
|
295
309
|
"mars5-tts": {
|
|
296
310
|
prettyLabel: string;
|
|
297
311
|
repoName: string;
|
|
@@ -557,6 +571,6 @@ export declare const MODEL_LIBRARIES_UI_ELEMENTS: {
|
|
|
557
571
|
};
|
|
558
572
|
};
|
|
559
573
|
export type ModelLibraryKey = keyof typeof MODEL_LIBRARIES_UI_ELEMENTS;
|
|
560
|
-
export declare const ALL_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "asteroid" | "audiocraft" | "audioseal" | "bertopic" | "big_vision" | "bm25s" | "champ" | "chat_tts" | "colpali" | "depth-anything-v2" | "diffusers" | "doctr" | "edsnlp" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gemma.cpp" | "gliner" | "glyph-byt5" | "grok" | "hallo" | "hunyuan-dit" | "keras" | "tf-keras" | "keras-nlp" | "k2" | "mindspore" | "mars5-tts" | "mesh-anything" | "ml-agents" | "mlx" | "mlx-image" | "mlc-llm" | "nemo" | "open_clip" | "paddlenlp" | "peft" | "pyannote-audio" | "pythae" | "recurrentgemma" | "sample-factory" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "speechbrain" | "stable-audio-tools" | "diffusion-single-file" | "stable-baselines3" | "stanza" | "tensorflowtts" | "tic-clip" | "timesfm" | "timm" | "transformers" | "transformers.js" | "unity-sentis" | "voicecraft" | "whisperkit")[];
|
|
561
|
-
export declare const ALL_DISPLAY_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "asteroid" | "audiocraft" | "audioseal" | "bertopic" | "big_vision" | "bm25s" | "champ" | "chat_tts" | "colpali" | "depth-anything-v2" | "diffusers" | "doctr" | "edsnlp" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gemma.cpp" | "gliner" | "glyph-byt5" | "grok" | "hallo" | "hunyuan-dit" | "keras" | "tf-keras" | "keras-nlp" | "k2" | "mindspore" | "mars5-tts" | "mesh-anything" | "ml-agents" | "mlx" | "mlx-image" | "mlc-llm" | "nemo" | "open_clip" | "paddlenlp" | "peft" | "pyannote-audio" | "pythae" | "recurrentgemma" | "sample-factory" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "speechbrain" | "stable-audio-tools" | "diffusion-single-file" | "stable-baselines3" | "stanza" | "tensorflowtts" | "tic-clip" | "timesfm" | "timm" | "transformers" | "transformers.js" | "unity-sentis" | "voicecraft" | "whisperkit")[];
|
|
574
|
+
export declare const ALL_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "asteroid" | "audiocraft" | "audioseal" | "bertopic" | "big_vision" | "bm25s" | "champ" | "chat_tts" | "colpali" | "depth-anything-v2" | "diffusers" | "doctr" | "edsnlp" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gemma.cpp" | "gliner" | "glyph-byt5" | "grok" | "hallo" | "hunyuan-dit" | "keras" | "tf-keras" | "keras-nlp" | "k2" | "liveportrait" | "mindspore" | "mamba-ssm" | "mars5-tts" | "mesh-anything" | "ml-agents" | "mlx" | "mlx-image" | "mlc-llm" | "nemo" | "open_clip" | "paddlenlp" | "peft" | "pyannote-audio" | "pythae" | "recurrentgemma" | "sample-factory" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "speechbrain" | "stable-audio-tools" | "diffusion-single-file" | "stable-baselines3" | "stanza" | "tensorflowtts" | "tic-clip" | "timesfm" | "timm" | "transformers" | "transformers.js" | "unity-sentis" | "voicecraft" | "whisperkit")[];
|
|
575
|
+
export declare const ALL_DISPLAY_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "asteroid" | "audiocraft" | "audioseal" | "bertopic" | "big_vision" | "bm25s" | "champ" | "chat_tts" | "colpali" | "depth-anything-v2" | "diffusers" | "doctr" | "edsnlp" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gemma.cpp" | "gliner" | "glyph-byt5" | "grok" | "hallo" | "hunyuan-dit" | "keras" | "tf-keras" | "keras-nlp" | "k2" | "liveportrait" | "mindspore" | "mamba-ssm" | "mars5-tts" | "mesh-anything" | "ml-agents" | "mlx" | "mlx-image" | "mlc-llm" | "nemo" | "open_clip" | "paddlenlp" | "peft" | "pyannote-audio" | "pythae" | "recurrentgemma" | "sample-factory" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "speechbrain" | "stable-audio-tools" | "diffusion-single-file" | "stable-baselines3" | "stanza" | "tensorflowtts" | "tic-clip" | "timesfm" | "timm" | "transformers" | "transformers.js" | "unity-sentis" | "voicecraft" | "whisperkit")[];
|
|
562
576
|
//# sourceMappingURL=model-libraries.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"model-libraries.d.ts","sourceRoot":"","sources":["../../src/model-libraries.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,cAAc,CAAC;AAC9C,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,6BAA6B,CAAC;AAEtE;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC;;;;OAIG;IACH,WAAW,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAC;IACjB;;OAEG;IACH,OAAO,EAAE,MAAM,CAAC;IAChB;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB;;OAEG;IACH,QAAQ,CAAC,EAAE,CAAC,KAAK,EAAE,SAAS,KAAK,MAAM,EAAE,CAAC;IAC1C;;;;;OAKG;IACH,cAAc,CAAC,EAAE,kBAAkB,CAAC;IACpC;;;OAGG;IACH,MAAM,CAAC,EAAE,OAAO,CAAC;CACjB;AAED;;;;;;;;;;;;;GAaG;AAEH,eAAO,MAAM,2BAA2B
|
|
1
|
+
{"version":3,"file":"model-libraries.d.ts","sourceRoot":"","sources":["../../src/model-libraries.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,cAAc,CAAC;AAC9C,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,6BAA6B,CAAC;AAEtE;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC;;;;OAIG;IACH,WAAW,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAC;IACjB;;OAEG;IACH,OAAO,EAAE,MAAM,CAAC;IAChB;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB;;OAEG;IACH,QAAQ,CAAC,EAAE,CAAC,KAAK,EAAE,SAAS,KAAK,MAAM,EAAE,CAAC;IAC1C;;;;;OAKG;IACH,cAAc,CAAC,EAAE,kBAAkB,CAAC;IACpC;;;OAGG;IACH,MAAM,CAAC,EAAE,OAAO,CAAC;CACjB;AAED;;;;;;;;;;;;;GAaG;AAEH,eAAO,MAAM,2BAA2B;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAsgBI,CAAC;AAE7C,MAAM,MAAM,eAAe,GAAG,MAAM,OAAO,2BAA2B,CAAC;AAEvE,eAAO,MAAM,sBAAsB,i7BAAgE,CAAC;AAEpG,eAAO,MAAM,8BAA8B,i7BAQ1B,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/document-question-answering/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,
|
|
1
|
+
{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/document-question-answering/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cA4Ef,CAAC;AAEF,eAAe,QAAQ,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-feature-extraction/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,
|
|
1
|
+
{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-feature-extraction/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cAkDf,CAAC;AAEF,eAAe,QAAQ,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-text-to-text/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,
|
|
1
|
+
{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-text-to-text/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cAyFf,CAAC;AAEF,eAAe,QAAQ,CAAC"}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-to-3d/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cAsEf,CAAC;AAEF,eAAe,QAAQ,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/tasks/index.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;
|
|
1
|
+
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/tasks/index.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AA0CjD,mBAAmB,kCAAkC,CAAC;AACtD,mBAAmB,0CAA0C,CAAC;AAC9D,YAAY,EACX,mBAAmB,EACnB,0BAA0B,EAC1B,oBAAoB,EACpB,4BAA4B,EAC5B,2BAA2B,EAC3B,0BAA0B,EAC1B,gCAAgC,EAChC,+BAA+B,GAC/B,MAAM,6BAA6B,CAAC;AACrC,mBAAmB,yCAAyC,CAAC;AAC7D,mBAAmB,gCAAgC,CAAC;AACpD,mBAAmB,uBAAuB,CAAC;AAC3C,YAAY,EACX,wBAAwB,EACxB,yBAAyB,EACzB,gCAAgC,EAChC,6BAA6B,GAC7B,MAAM,kCAAkC,CAAC;AAC1C,mBAAmB,4BAA4B,CAAC;AAChD,YAAY,EAAE,gBAAgB,EAAE,iBAAiB,EAAE,qBAAqB,EAAE,MAAM,2BAA2B,CAAC;AAC5G,mBAAmB,gCAAgC,CAAC;AACpD,mBAAmB,8BAA8B,CAAC;AAClD,mBAAmB,8BAA8B,CAAC;AAClD,mBAAmB,gCAAgC,CAAC;AACpD,mBAAmB,iCAAiC,CAAC;AACrD,mBAAmB,2BAA2B,CAAC;AAC/C,mBAAmB,sCAAsC,CAAC;AAC1D,YAAY,EAAE,gBAAgB,EAAE,iBAAiB,EAAE,qBAAqB,EAAE,MAAM,2BAA2B,CAAC;AAC5G,YAAY,EAAE,qBAAqB,EAAE,iBAAiB,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAC;AAC/G,mBAAmB,kCAAkC,CAAC;AACtD,YAAY,EACX,6BAA6B,EAC7B,qCAAqC,EACrC,gBAAgB,EAChB,iBAAiB,GACjB,MAAM,yBAAyB,CAAC;AACjC,YAAY,EACX,6BAA6B,EAC7B,uBAAuB,EACvB,wBAAwB,EACxB,+BAA+B,EAC/B,4BAA4B,GAC5B,MAAM,iCAAiC,CAAC;AACzC,YAAY,EACX,gCAAgC,EAChC,gCAAgC,EAChC,mBAAmB,EACnB,oBAAoB,EACpB,2BAA2B,EAC3B,qCAAqC,EACrC,kCAAkC,EAClC,yBAAyB,EACzB,uCAAuC,EACvC,0BAA0B,GAC1B,MAAM,6BAA6B,CAAC;AACrC,mBAAmB,kCAAkC,CAAC;AACtD,mBAAmB,uCAAuC,CAAC;AAC3D,mBAAmB,sCAAsC,CAAC;AAC1D,mBAAmB,4CAA4C,CAAC;AAChE,YAAY,EACX,WAAW,EACX,4BAA4B,EAC5B,gCAAgC,EAChC,6BAA6B,EAC7B,oCAAoC,GACpC,MAAM,wCAAwC,CAAC;AAEhD,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,oBAAoB,CAAC;AAE1D;;GAEG;AACH,eAAO,MAAM,qBAAqB,EAAE,MAAM,CAAC,YAAY,EAAE,eAAe,EAAE,CA0DzE,CAAC;AAoBF,eAAO,MAAM,UAAU,EAAE,MAAM,CAAC,YAAY,EAAE,QAAQ,GAAG,SAAS,CAkDxD,CAAC;AAEX,MAAM,WAAW,WAAW;IAC3B,WAAW,EAAE,MAAM,CAAC;IACpB,EAAE,EAAE,MAAM,CAAC;CACX;AAED,MAAM,MAAM,aAAa,GACtB;IACA,QAAQ,EAAE,MAAM,CAAC;IACjB,IAAI,EAAE,OAAO,CAAC;CACb,GACD;IACA,IAAI,EAAE,KAAK,CAAC;QACX,KAAK,EAAE,MAAM,CAAC;QACd,KAAK,EAAE,MAAM,CAAC;KACd,CAAC,CAAC;IACH,IAAI,EAAE,OAAO,CAAC;CACb,GACD;IACA,QAAQ,EAAE,MAAM,CAAC;IACjB,IAAI,EAAE,KAAK,CAAC;CACX,GACD;IACA,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC;IAClB,IAAI,EAAE,SAAS,CAAC;CACf,GACD;IACA,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,EAAE,MAAM,CAAC;CACZ,GACD;IACA,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,EAAE,KAAK,CAAC;QACb,GAAG,EAAE,MAAM,CAAC;QACZ,KAAK,EAAE,MAAM,CAAC;QACd,IAAI,EAAE,MAAM,CAAC;KACb,CAAC,CAAC;IACH,IAAI,EAAE,kBAAkB,CAAC;CACxB,CAAC;AAEL,MAAM,WAAW,QAAQ;IACxB,MAAM,EAAE,aAAa,EAAE,CAAC;IACxB,OAAO,EAAE,aAAa,EAAE,CAAC;CACzB;AAED,MAAM,WAAW,QAAQ;IACxB,QAAQ,EAAE,WAAW,EAAE,CAAC;IACxB,IAAI,EAAE,QAAQ,CAAC;IACf,EAAE,EAAE,YAAY,CAAC;IACjB,WAAW,CAAC,EAAE,YAAY,CAAC;IAC3B,aAAa,CAAC,EAAE,OAAO,CAAC;IACxB,KAAK,EAAE,MAAM,CAAC;IACd,SAAS,EAAE,eAAe,EAAE,CAAC;IAC7B,OAAO,EAAE,WAAW,EAAE,CAAC;IACvB,MAAM,EAAE,WAAW,EAAE,CAAC;IACtB,MAAM,EAAE,WAAW,EAAE,CAAC;IACtB,OAAO,EAAE,MAAM,CAAC;IAChB,YAAY,EAAE,MAAM,EAAE,CAAC;IACvB,SAAS,CAAC,EAAE,MAAM,CAAC;CACnB;AAED,MAAM,MAAM,cAAc,GAAG,IAAI,CAAC,QAAQ,EAAE,IAAI,GAAG,OAAO,GAAG,WAAW,CAAC,CAAC"}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/text-to-3d/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cAmDf,CAAC;AAEF,eAAe,QAAQ,CAAC"}
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@huggingface/tasks",
|
|
3
3
|
"packageManager": "pnpm@8.10.5",
|
|
4
|
-
"version": "0.11.
|
|
4
|
+
"version": "0.11.4",
|
|
5
5
|
"description": "List of ML tasks for huggingface.co/tasks",
|
|
6
6
|
"repository": "https://github.com/huggingface/huggingface.js.git",
|
|
7
7
|
"publishConfig": {
|
package/src/dataset-libraries.ts
CHANGED
|
@@ -71,6 +71,12 @@ export const DATASET_LIBRARIES_UI_ELEMENTS = {
|
|
|
71
71
|
repoUrl: "https://github.com/argilla-io/argilla",
|
|
72
72
|
docsUrl: "https://argilla-io.github.io/argilla",
|
|
73
73
|
},
|
|
74
|
+
polars: {
|
|
75
|
+
prettyLabel: "Polars",
|
|
76
|
+
repoName: "polars",
|
|
77
|
+
repoUrl: "https://github.com/pola-rs/polars",
|
|
78
|
+
docsUrl: "https://docs.pola.rs/",
|
|
79
|
+
},
|
|
74
80
|
} satisfies Record<string, DatasetLibraryUiElement>;
|
|
75
81
|
|
|
76
82
|
/// List of the dataset libraries supported by the Hub
|
|
@@ -270,6 +270,12 @@ model = from_pretrained_keras("${model.id}")
|
|
|
270
270
|
`,
|
|
271
271
|
];
|
|
272
272
|
|
|
273
|
+
export const mamba_ssm = (model: ModelData): string[] => [
|
|
274
|
+
`from mamba_ssm import MambaLMHeadModel
|
|
275
|
+
|
|
276
|
+
model = MambaLMHeadModel.from_pretrained("${model.id}")`,
|
|
277
|
+
];
|
|
278
|
+
|
|
273
279
|
export const mars5_tts = (model: ModelData): string[] => [
|
|
274
280
|
`# Install from https://github.com/Camb-ai/MARS5-TTS
|
|
275
281
|
|
package/src/model-libraries.ts
CHANGED
|
@@ -293,11 +293,25 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
|
|
|
293
293
|
repoName: "k2",
|
|
294
294
|
repoUrl: "https://github.com/k2-fsa/k2",
|
|
295
295
|
},
|
|
296
|
+
liveportrait: {
|
|
297
|
+
prettyLabel: "LivePortrait",
|
|
298
|
+
repoName: "LivePortrait",
|
|
299
|
+
repoUrl: "https://github.com/KwaiVGI/LivePortrait",
|
|
300
|
+
filter: false,
|
|
301
|
+
countDownloads: `path:"liveportrait/landmark.onnx"`,
|
|
302
|
+
},
|
|
296
303
|
mindspore: {
|
|
297
304
|
prettyLabel: "MindSpore",
|
|
298
305
|
repoName: "mindspore",
|
|
299
306
|
repoUrl: "https://github.com/mindspore-ai/mindspore",
|
|
300
307
|
},
|
|
308
|
+
"mamba-ssm": {
|
|
309
|
+
prettyLabel: "MambaSSM",
|
|
310
|
+
repoName: "MambaSSM",
|
|
311
|
+
repoUrl: "https://github.com/state-spaces/mamba",
|
|
312
|
+
filter: false,
|
|
313
|
+
snippets: snippets.mamba_ssm,
|
|
314
|
+
},
|
|
301
315
|
"mars5-tts": {
|
|
302
316
|
prettyLabel: "MARS5-TTS",
|
|
303
317
|
repoName: "MARS5-TTS",
|
|
@@ -3,7 +3,10 @@ import type { TaskDataCustom } from "..";
|
|
|
3
3
|
const taskData: TaskDataCustom = {
|
|
4
4
|
datasets: [
|
|
5
5
|
{
|
|
6
|
-
|
|
6
|
+
description: "Largest document understanding dataset.",
|
|
7
|
+
id: "HuggingFaceM4/Docmatix",
|
|
8
|
+
},
|
|
9
|
+
{
|
|
7
10
|
description:
|
|
8
11
|
"Dataset from the 2020 DocVQA challenge. The documents are taken from the UCSF Industry Documents Library.",
|
|
9
12
|
id: "eliolio/docvqa",
|
|
@@ -47,8 +50,8 @@ const taskData: TaskDataCustom = {
|
|
|
47
50
|
id: "impira/layoutlm-document-qa",
|
|
48
51
|
},
|
|
49
52
|
{
|
|
50
|
-
description: "A special model for OCR-free Document QA task.
|
|
51
|
-
id: "
|
|
53
|
+
description: "A special model for OCR-free Document QA task.",
|
|
54
|
+
id: "microsoft/udop-large",
|
|
52
55
|
},
|
|
53
56
|
{
|
|
54
57
|
description: "A powerful model for document question answering.",
|
|
@@ -42,6 +42,10 @@ const taskData: TaskDataCustom = {
|
|
|
42
42
|
description: "A robust image feature extraction models.",
|
|
43
43
|
id: "facebook/dino-vitb16",
|
|
44
44
|
},
|
|
45
|
+
{
|
|
46
|
+
description: "Strong image-text-to-text model made for information retrieval from documents.",
|
|
47
|
+
id: "vidore/colpali",
|
|
48
|
+
},
|
|
45
49
|
],
|
|
46
50
|
spaces: [],
|
|
47
51
|
summary: "Image feature extraction is the task of extracting features learnt in a computer vision model.",
|
|
@@ -43,8 +43,8 @@ const taskData: TaskDataCustom = {
|
|
|
43
43
|
metrics: [],
|
|
44
44
|
models: [
|
|
45
45
|
{
|
|
46
|
-
description: "Cutting-edge vision language model that can
|
|
47
|
-
id: "
|
|
46
|
+
description: "Cutting-edge vision language model that can take multiple image inputs.",
|
|
47
|
+
id: "facebook/chameleon-7b",
|
|
48
48
|
},
|
|
49
49
|
{
|
|
50
50
|
description: "Cutting-edge conversational vision language model that can take multiple image inputs.",
|
|
@@ -58,6 +58,10 @@ const taskData: TaskDataCustom = {
|
|
|
58
58
|
description: "Strong image-text-to-text model made to understand documents.",
|
|
59
59
|
id: "mPLUG/DocOwl1.5",
|
|
60
60
|
},
|
|
61
|
+
{
|
|
62
|
+
description: "Strong image-text-to-text model.",
|
|
63
|
+
id: "llava-hf/llava-v1.6-mistral-7b-hf",
|
|
64
|
+
},
|
|
61
65
|
],
|
|
62
66
|
spaces: [
|
|
63
67
|
{
|
|
@@ -0,0 +1,62 @@
|
|
|
1
|
+
## Use Cases
|
|
2
|
+
|
|
3
|
+
Image-to-3D models can be used in a wide variety of applications that require 3D, such as games, animation, design, architecture, engineering, marketing, and more.
|
|
4
|
+
|
|
5
|
+

|
|
6
|
+
|
|
7
|
+
### Generating Meshes
|
|
8
|
+
|
|
9
|
+
Meshes are the standard representation of 3D in industry.
|
|
10
|
+
|
|
11
|
+
### Generating Gaussian Splats
|
|
12
|
+
|
|
13
|
+
[Gaussian Splatting](https://huggingface.co/blog/gaussian-splatting) is a rendering technique that represents scenes as fuzzy points.
|
|
14
|
+
|
|
15
|
+
### Inference
|
|
16
|
+
|
|
17
|
+
Inference for this task typically leverages the [Diffusers](https://huggingface.co/docs/diffusers/index) library for inference, using [Custom Pipelines](https://huggingface.co/docs/diffusers/v0.6.0/en/using-diffusers/custom_pipelines).
|
|
18
|
+
|
|
19
|
+
These are unstandardized and depend on the model. More details can be found in each model repository.
|
|
20
|
+
|
|
21
|
+
```python
|
|
22
|
+
import torch
|
|
23
|
+
import requests
|
|
24
|
+
import numpy as np
|
|
25
|
+
from io import BytesIO
|
|
26
|
+
from diffusers import DiffusionPipeline
|
|
27
|
+
from PIL import Image
|
|
28
|
+
|
|
29
|
+
pipeline = DiffusionPipeline.from_pretrained(
|
|
30
|
+
"dylanebert/LGM-full",
|
|
31
|
+
custom_pipeline="dylanebert/LGM-full",
|
|
32
|
+
torch_dtype=torch.float16,
|
|
33
|
+
trust_remote_code=True,
|
|
34
|
+
).to("cuda")
|
|
35
|
+
|
|
36
|
+
input_url = "https://huggingface.co/datasets/dylanebert/iso3d/resolve/main/jpg@512/a_cat_statue.jpg"
|
|
37
|
+
input_image = Image.open(BytesIO(requests.get(input_url).content))
|
|
38
|
+
input_image = np.array(input_image, dtype=np.float32) / 255.0
|
|
39
|
+
result = pipeline("", input_image)
|
|
40
|
+
result_path = "/tmp/output.ply"
|
|
41
|
+
pipeline.save_ply(result, result_path)
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
In the code above, we:
|
|
45
|
+
|
|
46
|
+
1. Import the necessary libraries
|
|
47
|
+
2. Load the `LGM-full` model and custom pipeline
|
|
48
|
+
3. Load and preprocess the input image
|
|
49
|
+
4. Run the pipeline on the input image
|
|
50
|
+
5. Save the output to a file
|
|
51
|
+
|
|
52
|
+
### Output Formats
|
|
53
|
+
|
|
54
|
+
Meshes can be in `.obj`, `.glb`, `.stl`, or `.gltf` format. Other formats are allowed, but won't be rendered in the gradio [Model3D](https://www.gradio.app/docs/gradio/model3d) component.
|
|
55
|
+
|
|
56
|
+
Splats can be in `.ply` or `.splat` format. They can be rendered in the gradio [Model3D](https://www.gradio.app/docs/gradio/model3d) component using the [gsplat.js](https://github.com/huggingface/gsplat.js) library.
|
|
57
|
+
|
|
58
|
+
## Useful Resources
|
|
59
|
+
|
|
60
|
+
- [ML for 3D Course](https://huggingface.co/learn/ml-for-3d-course)
|
|
61
|
+
- [3D Arena Leaderboard](https://huggingface.co/spaces/dylanebert/3d-arena)
|
|
62
|
+
- [gsplat.js](https://github.com/huggingface/gsplat.js)
|
|
@@ -0,0 +1,75 @@
|
|
|
1
|
+
import type { TaskDataCustom } from "..";
|
|
2
|
+
|
|
3
|
+
const taskData: TaskDataCustom = {
|
|
4
|
+
datasets: [
|
|
5
|
+
{
|
|
6
|
+
description: "A large dataset of over 10 million 3D objects.",
|
|
7
|
+
id: "allenai/objaverse-xl",
|
|
8
|
+
},
|
|
9
|
+
{
|
|
10
|
+
description: "A dataset of isolated object images for evaluating image-to-3D models.",
|
|
11
|
+
id: "dylanebert/iso3d",
|
|
12
|
+
},
|
|
13
|
+
],
|
|
14
|
+
demo: {
|
|
15
|
+
inputs: [
|
|
16
|
+
{
|
|
17
|
+
filename: "image-to-3d-image-input.png",
|
|
18
|
+
type: "img",
|
|
19
|
+
},
|
|
20
|
+
],
|
|
21
|
+
outputs: [
|
|
22
|
+
{
|
|
23
|
+
label: "Result",
|
|
24
|
+
content: "image-to-3d-3d-output-filename.glb",
|
|
25
|
+
type: "text",
|
|
26
|
+
},
|
|
27
|
+
],
|
|
28
|
+
},
|
|
29
|
+
metrics: [],
|
|
30
|
+
models: [
|
|
31
|
+
{
|
|
32
|
+
description: "Fast image-to-3D mesh model by Tencent.",
|
|
33
|
+
id: "TencentARC/InstantMesh",
|
|
34
|
+
},
|
|
35
|
+
{
|
|
36
|
+
description: "Fast image-to-3D mesh model by StabilityAI",
|
|
37
|
+
id: "stabilityai/TripoSR",
|
|
38
|
+
},
|
|
39
|
+
{
|
|
40
|
+
description: "A scaled up image-to-3D mesh model derived from TripoSR.",
|
|
41
|
+
id: "hwjiang/Real3D",
|
|
42
|
+
},
|
|
43
|
+
{
|
|
44
|
+
description: "Generative 3D gaussian splatting model.",
|
|
45
|
+
id: "ashawkey/LGM",
|
|
46
|
+
},
|
|
47
|
+
],
|
|
48
|
+
spaces: [
|
|
49
|
+
{
|
|
50
|
+
description: "Leaderboard to evaluate image-to-3D models.",
|
|
51
|
+
id: "dylanebert/3d-arena",
|
|
52
|
+
},
|
|
53
|
+
{
|
|
54
|
+
description: "Image-to-3D demo with mesh outputs.",
|
|
55
|
+
id: "TencentARC/InstantMesh",
|
|
56
|
+
},
|
|
57
|
+
{
|
|
58
|
+
description: "Image-to-3D demo with mesh outputs.",
|
|
59
|
+
id: "stabilityai/TripoSR",
|
|
60
|
+
},
|
|
61
|
+
{
|
|
62
|
+
description: "Image-to-3D demo with mesh outputs.",
|
|
63
|
+
id: "hwjiang/Real3D",
|
|
64
|
+
},
|
|
65
|
+
{
|
|
66
|
+
description: "Image-to-3D demo with splat outputs.",
|
|
67
|
+
id: "dylanebert/LGM-mini",
|
|
68
|
+
},
|
|
69
|
+
],
|
|
70
|
+
summary: "Image-to-3D models take in image input and produce 3D output.",
|
|
71
|
+
widgetModels: [],
|
|
72
|
+
youtubeId: "",
|
|
73
|
+
};
|
|
74
|
+
|
|
75
|
+
export default taskData;
|
package/src/tasks/index.ts
CHANGED
|
@@ -37,6 +37,8 @@ import visualQuestionAnswering from "./visual-question-answering/data";
|
|
|
37
37
|
import zeroShotClassification from "./zero-shot-classification/data";
|
|
38
38
|
import zeroShotImageClassification from "./zero-shot-image-classification/data";
|
|
39
39
|
import zeroShotObjectDetection from "./zero-shot-object-detection/data";
|
|
40
|
+
import imageTo3D from "./image-to-3d/data";
|
|
41
|
+
import textTo3D from "./text-to-3d/data";
|
|
40
42
|
|
|
41
43
|
export type * from "./audio-classification/inference";
|
|
42
44
|
export type * from "./automatic-speech-recognition/inference";
|
|
@@ -169,8 +171,8 @@ export const TASKS_MODEL_LIBRARIES: Record<PipelineType, ModelLibraryKey[]> = {
|
|
|
169
171
|
"zero-shot-classification": ["transformers", "transformers.js"],
|
|
170
172
|
"zero-shot-image-classification": ["transformers", "transformers.js"],
|
|
171
173
|
"zero-shot-object-detection": ["transformers", "transformers.js"],
|
|
172
|
-
"text-to-3d": [],
|
|
173
|
-
"image-to-3d": [],
|
|
174
|
+
"text-to-3d": ["diffusers"],
|
|
175
|
+
"image-to-3d": ["diffusers"],
|
|
174
176
|
};
|
|
175
177
|
|
|
176
178
|
/**
|
|
@@ -239,8 +241,8 @@ export const TASKS_DATA: Record<PipelineType, TaskData | undefined> = {
|
|
|
239
241
|
"zero-shot-classification": getData("zero-shot-classification", zeroShotClassification),
|
|
240
242
|
"zero-shot-image-classification": getData("zero-shot-image-classification", zeroShotImageClassification),
|
|
241
243
|
"zero-shot-object-detection": getData("zero-shot-object-detection", zeroShotObjectDetection),
|
|
242
|
-
"text-to-3d": getData("text-to-3d",
|
|
243
|
-
"image-to-3d": getData("image-to-3d",
|
|
244
|
+
"text-to-3d": getData("text-to-3d", textTo3D),
|
|
245
|
+
"image-to-3d": getData("image-to-3d", imageTo3D),
|
|
244
246
|
} as const;
|
|
245
247
|
|
|
246
248
|
export interface ExampleRepo {
|
|
@@ -0,0 +1,62 @@
|
|
|
1
|
+
## Use Cases
|
|
2
|
+
|
|
3
|
+
Text-to-3D models can be used in a wide variety of applications that require 3D, such as games, animation, design, architecture, engineering, marketing, and more.
|
|
4
|
+
|
|
5
|
+

|
|
6
|
+
|
|
7
|
+
This task is similar to the [image-to-3d](https://huggingface.co/tasks/image-to-3d) task, but takes text input instead of image input. In practice, this is often equivalent to a combination of [text-to-image](https://huggingface.co/tasks/text-to-image) and [image-to-3d](https://huggingface.co/tasks/image-to-3d). That is, the text is first converted to an image, then the image is converted to 3D.
|
|
8
|
+
|
|
9
|
+
### Generating Meshes
|
|
10
|
+
|
|
11
|
+
Meshes are the standard representation of 3D in industry.
|
|
12
|
+
|
|
13
|
+
### Generating Gaussian Splats
|
|
14
|
+
|
|
15
|
+
[Gaussian Splatting](https://huggingface.co/blog/gaussian-splatting) is a rendering technique that represents scenes as fuzzy points.
|
|
16
|
+
|
|
17
|
+
### Inference
|
|
18
|
+
|
|
19
|
+
Inference for this task typically leverages the [Diffusers](https://huggingface.co/docs/diffusers/index) library for inference, using [Custom Pipelines](https://huggingface.co/docs/diffusers/v0.6.0/en/using-diffusers/custom_pipelines).
|
|
20
|
+
|
|
21
|
+
These are unstandardized and depend on the model. More details can be found in each model repository.
|
|
22
|
+
|
|
23
|
+
```python
|
|
24
|
+
import torch
|
|
25
|
+
import requests
|
|
26
|
+
import numpy as np
|
|
27
|
+
from io import BytesIO
|
|
28
|
+
from diffusers import DiffusionPipeline
|
|
29
|
+
from PIL import Image
|
|
30
|
+
|
|
31
|
+
pipeline = DiffusionPipeline.from_pretrained(
|
|
32
|
+
"dylanebert/LGM-full",
|
|
33
|
+
custom_pipeline="dylanebert/LGM-full",
|
|
34
|
+
torch_dtype=torch.float16,
|
|
35
|
+
trust_remote_code=True,
|
|
36
|
+
).to("cuda")
|
|
37
|
+
|
|
38
|
+
input_prompt = "a cat statue"
|
|
39
|
+
result = pipeline(input_prompt, None)
|
|
40
|
+
result_path = "/tmp/output.ply"
|
|
41
|
+
pipeline.save_ply(result, result_path)
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
In the code above, we:
|
|
45
|
+
|
|
46
|
+
1. Import the necessary libraries
|
|
47
|
+
2. Load the `LGM-full` model and custom pipeline
|
|
48
|
+
3. Define the input prompt
|
|
49
|
+
4. Run the pipeline on the input prompt
|
|
50
|
+
5. Save the output to a file
|
|
51
|
+
|
|
52
|
+
### Output Formats
|
|
53
|
+
|
|
54
|
+
Meshes can be in `.obj`, `.glb`, `.stl`, or `.gltf` format. Other formats are allowed, but won't be rendered in the gradio [Model3D](https://www.gradio.app/docs/gradio/model3d) component.
|
|
55
|
+
|
|
56
|
+
Splats can be in `.ply` or `.splat` format. They can be rendered in the gradio [Model3D](https://www.gradio.app/docs/gradio/model3d) component using the [gsplat.js](https://github.com/huggingface/gsplat.js) library.
|
|
57
|
+
|
|
58
|
+
## Useful Resources
|
|
59
|
+
|
|
60
|
+
- [ML for 3D Course](https://huggingface.co/learn/ml-for-3d-course)
|
|
61
|
+
- [3D Arena Leaderboard](https://huggingface.co/spaces/dylanebert/3d-arena)
|
|
62
|
+
- [gsplat.js](https://github.com/huggingface/gsplat.js)
|
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
import type { TaskDataCustom } from "..";
|
|
2
|
+
|
|
3
|
+
const taskData: TaskDataCustom = {
|
|
4
|
+
datasets: [
|
|
5
|
+
{
|
|
6
|
+
description: "A large dataset of over 10 million 3D objects.",
|
|
7
|
+
id: "allenai/objaverse-xl",
|
|
8
|
+
},
|
|
9
|
+
{
|
|
10
|
+
description: "Descriptive captions for 3D objects in Objaverse.",
|
|
11
|
+
id: "tiange/Cap3D",
|
|
12
|
+
},
|
|
13
|
+
],
|
|
14
|
+
demo: {
|
|
15
|
+
inputs: [
|
|
16
|
+
{
|
|
17
|
+
label: "Prompt",
|
|
18
|
+
content: "a cat statue",
|
|
19
|
+
type: "text",
|
|
20
|
+
},
|
|
21
|
+
],
|
|
22
|
+
outputs: [
|
|
23
|
+
{
|
|
24
|
+
label: "Result",
|
|
25
|
+
content: "text-to-3d-3d-output-filename.glb",
|
|
26
|
+
type: "text",
|
|
27
|
+
},
|
|
28
|
+
],
|
|
29
|
+
},
|
|
30
|
+
metrics: [],
|
|
31
|
+
models: [
|
|
32
|
+
{
|
|
33
|
+
description: "Text-to-3D mesh model by OpenAI",
|
|
34
|
+
id: "openai/shap-e",
|
|
35
|
+
},
|
|
36
|
+
{
|
|
37
|
+
description: "Generative 3D gaussian splatting model.",
|
|
38
|
+
id: "ashawkey/LGM",
|
|
39
|
+
},
|
|
40
|
+
],
|
|
41
|
+
spaces: [
|
|
42
|
+
{
|
|
43
|
+
description: "Text-to-3D demo with mesh outputs.",
|
|
44
|
+
id: "hysts/Shap-E",
|
|
45
|
+
},
|
|
46
|
+
{
|
|
47
|
+
description: "Text/image-to-3D demo with splat outputs.",
|
|
48
|
+
id: "ashawkey/LGM",
|
|
49
|
+
},
|
|
50
|
+
],
|
|
51
|
+
summary: "Text-to-3D models take in text input and produce 3D output.",
|
|
52
|
+
widgetModels: [],
|
|
53
|
+
youtubeId: "",
|
|
54
|
+
};
|
|
55
|
+
|
|
56
|
+
export default taskData;
|