Hugging Face's logo

HuggingFaceM4
/
idefics2-8b

Image-Text-to-Text
Transformers
Safetensors
English
idefics2
image-to-text
multimodal
vision
text-generation-inference
Model card Files
xet
Community
83

add AIBOM

#83
by RiccardoDav - opened
base: refs/heads/main
←
from: refs/pr/83
Discussion Files changed
+1163
-0
Files changed (1) hide show
  1. HuggingFaceM4_idefics2-8b.json +1163 -0
HuggingFaceM4_idefics2-8b.json ADDED
@@ -0,0 +1,1163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bomFormat": "CycloneDX",
3
+ "specVersion": "1.6",
4
+ "serialNumber": "urn:uuid:f23c2a8d-7038-4272-957e-ca97df335610",
5
+ "version": 1,
6
+ "metadata": {
7
+ "timestamp": "2025-06-05T09:38:20.021414+00:00",
8
+ "component": {
9
+ "type": "machine-learning-model",
10
+ "bom-ref": "HuggingFaceM4/idefics2-8b-7bb21b56-dde0-500e-bf25-f4c32e64aa26",
11
+ "name": "HuggingFaceM4/idefics2-8b",
12
+ "externalReferences": [
13
+ {
14
+ "url": "https://huggingface.co/HuggingFaceM4/idefics2-8b",
15
+ "type": "documentation"
16
+ }
17
+ ],
18
+ "modelCard": {
19
+ "modelParameters": {
20
+ "task": "image-text-to-text",
21
+ "architectureFamily": "idefics2",
22
+ "modelArchitecture": "Idefics2ForConditionalGeneration",
23
+ "datasets": [
24
+ {
25
+ "ref": "HuggingFaceM4/OBELICS-54e0c87c-8ce6-51eb-af0d-52a7ddb63e49"
26
+ },
27
+ {
28
+ "ref": "laion/laion-coco-6e73f888-3348-5039-864c-d2250f312f2e"
29
+ },
30
+ {
31
+ "ref": "wikipedia-8c5eb686-d691-517b-aad7-040fa51febc3"
32
+ },
33
+ {
34
+ "ref": "facebook/pmd-71fff1f1-79e2-5837-818a-a847941edaff"
35
+ },
36
+ {
37
+ "ref": "pixparse/idl-wds-5ddb0bef-9a41-5fb6-acce-2d16b0053443"
38
+ },
39
+ {
40
+ "ref": "pixparse/pdfa-eng-wds-6e24c86a-28c2-50e7-80c1-b74796cd7222"
41
+ },
42
+ {
43
+ "ref": "wendlerc/RenderedText-2ea0375f-e9a2-55d0-aa1e-734edec2644e"
44
+ },
45
+ {
46
+ "ref": "HuggingFaceM4/the_cauldron-0b60b937-29a7-5f0c-9fa6-ec10bf894687"
47
+ },
48
+ {
49
+ "ref": "teknium/OpenHermes-2.5-1a7eb3be-7eaa-5577-91f6-d4ad0d639c6c"
50
+ },
51
+ {
52
+ "ref": "GAIR/lima-afa8f631-d0ed-59c0-a5a1-170c80a5117e"
53
+ },
54
+ {
55
+ "ref": "databricks/databricks-dolly-15k-1008cfb1-7624-5c5b-93cc-d856239b86ea"
56
+ },
57
+ {
58
+ "ref": "meta-math/MetaMathQA-c6cf810a-8b06-5552-a876-53681c5fe9a1"
59
+ },
60
+ {
61
+ "ref": "TIGER-Lab/MathInstruct-9d9c997d-f6c1-5029-96fd-6003c4f0ec06"
62
+ },
63
+ {
64
+ "ref": "microsoft/orca-math-word-problems-200k-611afa9f-b6db-5b9f-9a51-598e4ce79d0e"
65
+ },
66
+ {
67
+ "ref": "camel-ai/math-9f7ffeb0-2fb3-5b72-9ca4-1b461f022e61"
68
+ },
69
+ {
70
+ "ref": "AtlasUnified/atlas-math-sets-49141027-0c69-515d-8182-254cf889efae"
71
+ },
72
+ {
73
+ "ref": "tiedong/goat-38642401-79d7-541d-a92f-d3d7acdb8db8"
74
+ },
75
+ {
76
+ "ref": "Lin-Chen/ShareGPT4V-f6982603-3c10-5cd0-9d2d-83d573b61341"
77
+ },
78
+ {
79
+ "ref": "jxu124/llava_conversation_58k-7dcd95f0-d26a-5075-89f4-4afc13a5b93f"
80
+ }
81
+ ]
82
+ },
83
+ "properties": [
84
+ {
85
+ "name": "library_name",
86
+ "value": "transformers"
87
+ }
88
+ ],
89
+ "consideration": {
90
+ "useCases": "`idefics2-8b-base` and `idefics2-8b` can be used to perform inference on multimodal (image + text) tasks in which the input is composed of a text query along with one (or multiple) image(s). Text and images can be arbitrarily interleaved. That includes image captioning, visual question answering, etc. These model does not support image generation.For optimal results, we recommend fine-tuning `idefics2-8b` on one's specific use-case and data. In fact, the instruction-fine-tuned model (`idefics2-8b`) is significantly better at following instructions from users and thus should be preferred when using the models out-of-the-box or as a starting point for fine-tuning.`idefics2-8b` usually generates very short answers. For long generations, use `idefics2-8b-chatty`, which was further fine-tuned on long conversations.As a starting point, we provide fine-tuning codes that can be adapted for one's particular scenario:- With the [TRL library](https://github.com/huggingface/trl): [Script](https://gist.github.com/edbeeching/228652fc6c2b29a1641be5a5778223cb)- With the [Hugging Face Trainer](https://huggingface.co/docs/transformers/main/en/main_classes/trainer#api-reference%20][%20transformers.Trainer): [Tutorial notebook](https://colab.research.google.com/drive/1NtcTgRbSBKN7pYD3Vdx1j9m8pt3fhFDB?usp=sharing)"
91
+ }
92
+ },
93
+ "authors": [
94
+ {
95
+ "name": "HuggingFaceM4"
96
+ }
97
+ ],
98
+ "licenses": [
99
+ {
100
+ "license": {
101
+ "id": "Apache-2.0",
102
+ "url": "https://spdx.org/licenses/Apache-2.0.html"
103
+ }
104
+ }
105
+ ],
106
+ "description": "- **Developed by:** Hugging Face- **Model type:** Multi-modal model (image+text)- **Language(s) (NLP):** en- **License:** Apache 2.0- **Parent Models:** [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) and [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)- **Resources for more information:**- Description of [OBELICS](https://huggingface.co/datasets/HuggingFaceM4/OBELICS): [OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents](https://huggingface.co/papers/2306.16527)- Paper: [What matters when building vision-language models?](https://huggingface.co/papers/2405.02246)",
107
+ "tags": [
108
+ "transformers",
109
+ "safetensors",
110
+ "idefics2",
111
+ "image-text-to-text",
112
+ "multimodal",
113
+ "vision",
114
+ "en",
115
+ "dataset:HuggingFaceM4/OBELICS",
116
+ "dataset:laion/laion-coco",
117
+ "dataset:wikipedia",
118
+ "dataset:facebook/pmd",
119
+ "dataset:pixparse/idl-wds",
120
+ "dataset:pixparse/pdfa-eng-wds",
121
+ "dataset:wendlerc/RenderedText",
122
+ "dataset:HuggingFaceM4/the_cauldron",
123
+ "dataset:teknium/OpenHermes-2.5",
124
+ "dataset:GAIR/lima",
125
+ "dataset:databricks/databricks-dolly-15k",
126
+ "dataset:meta-math/MetaMathQA",
127
+ "dataset:TIGER-Lab/MathInstruct",
128
+ "dataset:microsoft/orca-math-word-problems-200k",
129
+ "dataset:camel-ai/math",
130
+ "dataset:AtlasUnified/atlas-math-sets",
131
+ "dataset:tiedong/goat",
132
+ "dataset:Lin-Chen/ShareGPT4V",
133
+ "dataset:jxu124/llava_conversation_58k",
134
+ "arxiv:2306.16527",
135
+ "arxiv:2405.02246",
136
+ "arxiv:2307.06304",
137
+ "arxiv:2311.07575",
138
+ "arxiv:2103.03206",
139
+ "license:apache-2.0",
140
+ "text-generation-inference",
141
+ "endpoints_compatible",
142
+ "region:us"
143
+ ]
144
+ }
145
+ },
146
+ "components": [
147
+ {
148
+ "type": "data",
149
+ "bom-ref": "HuggingFaceM4/OBELICS-54e0c87c-8ce6-51eb-af0d-52a7ddb63e49",
150
+ "name": "HuggingFaceM4/OBELICS",
151
+ "data": [
152
+ {
153
+ "type": "dataset",
154
+ "bom-ref": "HuggingFaceM4/OBELICS-54e0c87c-8ce6-51eb-af0d-52a7ddb63e49",
155
+ "name": "HuggingFaceM4/OBELICS",
156
+ "contents": {
157
+ "url": "https://huggingface.co/datasets/HuggingFaceM4/OBELICS",
158
+ "properties": [
159
+ {
160
+ "name": "language",
161
+ "value": "en"
162
+ },
163
+ {
164
+ "name": "size_categories",
165
+ "value": "100M<n<1B"
166
+ },
167
+ {
168
+ "name": "pretty_name",
169
+ "value": "OBELICS"
170
+ },
171
+ {
172
+ "name": "configs",
173
+ "value": "Name of the dataset subset: default {\"split\": \"train\", \"path\": \"data/train-*\"}"
174
+ },
175
+ {
176
+ "name": "configs",
177
+ "value": "Name of the dataset subset: opt_out_docs_removed_2023_07_12 {\"split\": \"train\", \"path\": \"opt_out_docs_removed_2023_07_12/train-*\"}"
178
+ },
179
+ {
180
+ "name": "license",
181
+ "value": "cc-by-4.0"
182
+ }
183
+ ]
184
+ },
185
+ "governance": {
186
+ "owners": [
187
+ {
188
+ "organization": {
189
+ "name": "HuggingFaceM4",
190
+ "url": "https://huggingface.co/HuggingFaceM4"
191
+ }
192
+ }
193
+ ]
194
+ },
195
+ "description": "\n\t\n\t\t\n\t\tDataset Card for OBELICS\n\t\n\nOBELICS is an open, massive, and curated collection of interleaved image-text web documents, containing 141M English documents, 115B text tokens, and 353M images, extracted from Common Crawl dumps between February 2020 and February 2023. The collection and filtering steps are described in our paper.\nInterleaved image-text web documents are a succession of text paragraphs interleaved by images, such as web pages that contain images. Models trained on these\u2026 See the full description on the dataset page: https://huggingface.co/datasets/HuggingFaceM4/OBELICS."
196
+ }
197
+ ]
198
+ },
199
+ null,
200
+ {
201
+ "type": "data",
202
+ "bom-ref": "wikipedia-8c5eb686-d691-517b-aad7-040fa51febc3",
203
+ "name": "wikipedia",
204
+ "data": [
205
+ {
206
+ "type": "dataset",
207
+ "bom-ref": "wikipedia-8c5eb686-d691-517b-aad7-040fa51febc3",
208
+ "name": "wikipedia",
209
+ "contents": {
210
+ "url": "https://huggingface.co/datasets/wikipedia",
211
+ "properties": [
212
+ {
213
+ "name": "task_categories",
214
+ "value": "text-generation, fill-mask"
215
+ },
216
+ {
217
+ "name": "task_ids",
218
+ "value": "language-modeling, masked-language-modeling"
219
+ },
220
+ {
221
+ "name": "language",
222
+ "value": "aa, ab, ace, af, ak, als, am, an, ang, ar, arc, arz, as, ast, atj, av, ay, az, azb, ba, bar, bcl, be, bg, bh, bi, bjn, bm, bn, bo, bpy, br, bs, bug, bxr, ca, cbk, cdo, ce, ceb, ch, cho, chr, chy, ckb, co, cr, crh, cs, csb, cu, cv, cy, da, de, din, diq, dsb, dty, dv, dz, ee, el, eml, en, eo, es, et, eu, ext, fa, ff, fi, fj, fo, fr, frp, frr, fur, fy, ga, gag, gan, gd, gl, glk, gn, gom, gor, got, gu, gv, ha, hak, haw, he, hi, hif, ho, hr, hsb, ht, hu, hy, ia, id, ie, ig, ii, ik, ilo, inh, io, is, it, iu, ja, jam, jbo, jv, ka, kaa, kab, kbd, kbp, kg, ki, kj, kk, kl, km, kn, ko, koi, krc, ks, ksh, ku, kv, kw, ky, la, lad, lb, lbe, lez, lfn, lg, li, lij, lmo, ln, lo, lrc, lt, ltg, lv, lzh, mai, mdf, mg, mh, mhr, mi, min, mk, ml, mn, mr, mrj, ms, mt, mus, mwl, my, myv, mzn, na, nah, nan, nap, nds, ne, new, ng, nl, nn, no, nov, nrf, nso, nv, ny, oc, olo, om, or, os, pa, pag, pam, pap, pcd, pdc, pfl, pi, pih, pl, pms, pnb, pnt, ps, pt, qu, rm, rmy, rn, ro, ru, rue, rup, rw, sa, sah, sat, sc, scn, sco, sd, se, sg, sgs, sh, si, sk, sl, sm, sn, so, sq, sr, srn, ss, st, stq, su, sv, sw, szl, ta, tcy, tdt, te, tg, th, ti, tk, tl, tn, to, tpi, tr, ts, tt, tum, tw, ty, tyv, udm, ug, uk, ur, uz, ve, vec, vep, vi, vls, vo, vro, wa, war, wo, wuu, xal, xh, xmf, yi, yo, yue, za, zea, zh, zu"
223
+ },
224
+ {
225
+ "name": "size_categories",
226
+ "value": "n<1K, 1K<n<10K, 10K<n<100K, 100K<n<1M, 1M<n<10M"
227
+ },
228
+ {
229
+ "name": "annotations_creators",
230
+ "value": "no-annotation"
231
+ },
232
+ {
233
+ "name": "language_creators",
234
+ "value": "crowdsourced"
235
+ },
236
+ {
237
+ "name": "pretty_name",
238
+ "value": "Wikipedia"
239
+ },
240
+ {
241
+ "name": "source_datasets",
242
+ "value": "original"
243
+ },
244
+ {
245
+ "name": "paperswithcode_id",
246
+ "value": null
247
+ },
248
+ {
249
+ "name": "license",
250
+ "value": "cc-by-sa-3.0, gfdl"
251
+ }
252
+ ]
253
+ },
254
+ "governance": {
255
+ "owners": [
256
+ {
257
+ "organization": {
258
+ "name": "legacy-datasets",
259
+ "url": "https://huggingface.co/legacy-datasets"
260
+ }
261
+ }
262
+ ]
263
+ },
264
+ "description": "Wikipedia dataset containing cleaned articles of all languages.\nThe datasets are built from the Wikipedia dump\n(https://dumps.wikimedia.org/) with one split per language. Each example\ncontains the content of one full Wikipedia article with cleaning to strip\nmarkdown and unwanted sections (references, etc.)."
265
+ }
266
+ ]
267
+ },
268
+ {
269
+ "type": "data",
270
+ "bom-ref": "facebook/pmd-71fff1f1-79e2-5837-818a-a847941edaff",
271
+ "name": "facebook/pmd",
272
+ "data": [
273
+ {
274
+ "type": "dataset",
275
+ "bom-ref": "facebook/pmd-71fff1f1-79e2-5837-818a-a847941edaff",
276
+ "name": "facebook/pmd",
277
+ "contents": {
278
+ "url": "https://huggingface.co/datasets/facebook/pmd",
279
+ "properties": [
280
+ {
281
+ "name": "task_categories",
282
+ "value": "image-to-text"
283
+ },
284
+ {
285
+ "name": "task_ids",
286
+ "value": "image-captioning"
287
+ },
288
+ {
289
+ "name": "language",
290
+ "value": "en"
291
+ },
292
+ {
293
+ "name": "size_categories",
294
+ "value": "10M<n<100M"
295
+ },
296
+ {
297
+ "name": "annotations_creators",
298
+ "value": "found"
299
+ },
300
+ {
301
+ "name": "language_creators",
302
+ "value": "found"
303
+ },
304
+ {
305
+ "name": "pretty_name",
306
+ "value": "PMD"
307
+ },
308
+ {
309
+ "name": "source_datasets",
310
+ "value": "original"
311
+ },
312
+ {
313
+ "name": "paperswithcode_id",
314
+ "value": "pmd"
315
+ },
316
+ {
317
+ "name": "license",
318
+ "value": "cc-by-4.0"
319
+ }
320
+ ]
321
+ },
322
+ "governance": {
323
+ "owners": [
324
+ {
325
+ "organization": {
326
+ "name": "facebook",
327
+ "url": "https://huggingface.co/facebook"
328
+ }
329
+ }
330
+ ]
331
+ },
332
+ "description": "Introduced in FLAVA paper, Public Multimodal Dataset (PMD) is a collection of publicly-available image-text pairs datasets. PMD in total contains 70M image-text pairs with 68M unique images. The dataset contains pairs from Conceptual Captions, Conceptual Captions 12M, WIT, Localized Narratives, RedCaps, COCO, SBU Captions, Visual Genome and a subset of YFCC100M dataset."
333
+ }
334
+ ]
335
+ },
336
+ {
337
+ "type": "data",
338
+ "bom-ref": "pixparse/idl-wds-5ddb0bef-9a41-5fb6-acce-2d16b0053443",
339
+ "name": "pixparse/idl-wds",
340
+ "data": [
341
+ {
342
+ "type": "dataset",
343
+ "bom-ref": "pixparse/idl-wds-5ddb0bef-9a41-5fb6-acce-2d16b0053443",
344
+ "name": "pixparse/idl-wds",
345
+ "contents": {
346
+ "url": "https://huggingface.co/datasets/pixparse/idl-wds",
347
+ "properties": [
348
+ {
349
+ "name": "task_categories",
350
+ "value": "image-to-text"
351
+ },
352
+ {
353
+ "name": "size_categories",
354
+ "value": "10M<n<100M"
355
+ },
356
+ {
357
+ "name": "license",
358
+ "value": "other"
359
+ },
360
+ {
361
+ "name": "license_name",
362
+ "value": "idl-train"
363
+ },
364
+ {
365
+ "name": "license_link",
366
+ "value": "LICENSE"
367
+ }
368
+ ]
369
+ },
370
+ "governance": {
371
+ "owners": [
372
+ {
373
+ "organization": {
374
+ "name": "pixparse",
375
+ "url": "https://huggingface.co/pixparse"
376
+ }
377
+ }
378
+ ]
379
+ },
380
+ "description": "\n\t\n\t\t\n\t\tDataset Card for Industry Documents Library (IDL)\n\t\n\n\n\t\n\t\t\n\t\tDataset Summary\n\t\n\nIndustry Documents Library (IDL) is a document dataset filtered from UCSF documents library with 19 million pages kept as valid samples.\nEach document exists as a collection of a pdf, a tiff image with the same contents rendered, a json file containing extensive Textract OCR annotations from the idl_data project, and a .ocr file with the original, older OCR annotation. In each pdf, there may be from 1 to up\u2026 See the full description on the dataset page: https://huggingface.co/datasets/pixparse/idl-wds."
381
+ }
382
+ ]
383
+ },
384
+ {
385
+ "type": "data",
386
+ "bom-ref": "pixparse/pdfa-eng-wds-6e24c86a-28c2-50e7-80c1-b74796cd7222",
387
+ "name": "pixparse/pdfa-eng-wds",
388
+ "data": [
389
+ {
390
+ "type": "dataset",
391
+ "bom-ref": "pixparse/pdfa-eng-wds-6e24c86a-28c2-50e7-80c1-b74796cd7222",
392
+ "name": "pixparse/pdfa-eng-wds",
393
+ "contents": {
394
+ "url": "https://huggingface.co/datasets/pixparse/pdfa-eng-wds",
395
+ "properties": [
396
+ {
397
+ "name": "task_categories",
398
+ "value": "image-to-text"
399
+ },
400
+ {
401
+ "name": "language",
402
+ "value": "en"
403
+ },
404
+ {
405
+ "name": "size_categories",
406
+ "value": "10M<n<100M"
407
+ },
408
+ {
409
+ "name": "license",
410
+ "value": "other"
411
+ },
412
+ {
413
+ "name": "license_name",
414
+ "value": "pdfa-eng-wds"
415
+ },
416
+ {
417
+ "name": "license_link",
418
+ "value": "LICENSE"
419
+ }
420
+ ]
421
+ },
422
+ "governance": {
423
+ "owners": [
424
+ {
425
+ "organization": {
426
+ "name": "pixparse",
427
+ "url": "https://huggingface.co/pixparse"
428
+ }
429
+ }
430
+ ]
431
+ },
432
+ "description": "\n\t\n\t\t\n\t\tDataset Card for PDF Association dataset (PDFA)\n\t\n\n\n\t\n\t\t\n\t\tDataset Summary\n\t\n\nPDFA dataset is a document dataset filtered from the SafeDocs corpus, aka CC-MAIN-2021-31-PDF-UNTRUNCATED. The original purpose of that corpus is for comprehensive pdf documents analysis. The purpose of that subset differs in that regard, as focus has been done on making the dataset machine learning-ready for vision-language models. \n\n \n An example page of one pdf document, with added bounding boxes\u2026 See the full description on the dataset page: https://huggingface.co/datasets/pixparse/pdfa-eng-wds."
433
+ }
434
+ ]
435
+ },
436
+ {
437
+ "type": "data",
438
+ "bom-ref": "wendlerc/RenderedText-2ea0375f-e9a2-55d0-aa1e-734edec2644e",
439
+ "name": "wendlerc/RenderedText",
440
+ "data": [
441
+ {
442
+ "type": "dataset",
443
+ "bom-ref": "wendlerc/RenderedText-2ea0375f-e9a2-55d0-aa1e-734edec2644e",
444
+ "name": "wendlerc/RenderedText",
445
+ "contents": {
446
+ "url": "https://huggingface.co/datasets/wendlerc/RenderedText",
447
+ "properties": [
448
+ {
449
+ "name": "task_categories",
450
+ "value": "text-to-image, image-to-text"
451
+ },
452
+ {
453
+ "name": "language",
454
+ "value": "en"
455
+ },
456
+ {
457
+ "name": "size_categories",
458
+ "value": "10M<n<100M"
459
+ }
460
+ ]
461
+ },
462
+ "governance": {
463
+ "owners": [
464
+ {
465
+ "organization": {
466
+ "name": "wendlerc",
467
+ "url": "https://huggingface.co/wendlerc"
468
+ }
469
+ }
470
+ ]
471
+ },
472
+ "description": "This dataset has been created by Stability AI and LAION.\nThis dataset contains 12 million 1024x1024 images of handwritten text written on a digital 3D sheet of paper generated using Blender geometry nodes and rendered using Blender Cycles. The text has varying font size, color, and rotation, and the paper was rendered under random lighting conditions.\nNote that, the first 10 million examples are in the root folder of this dataset repository and the remaining 2 million are in ./remaining (due\u2026 See the full description on the dataset page: https://huggingface.co/datasets/wendlerc/RenderedText."
473
+ }
474
+ ]
475
+ },
476
+ {
477
+ "type": "data",
478
+ "bom-ref": "HuggingFaceM4/the_cauldron-0b60b937-29a7-5f0c-9fa6-ec10bf894687",
479
+ "name": "HuggingFaceM4/the_cauldron",
480
+ "data": [
481
+ {
482
+ "type": "dataset",
483
+ "bom-ref": "HuggingFaceM4/the_cauldron-0b60b937-29a7-5f0c-9fa6-ec10bf894687",
484
+ "name": "HuggingFaceM4/the_cauldron",
485
+ "contents": {
486
+ "url": "https://huggingface.co/datasets/HuggingFaceM4/the_cauldron",
487
+ "properties": [
488
+ {
489
+ "name": "configs",
490
+ "value": "Name of the dataset subset: ai2d {\"split\": \"train\", \"path\": \"ai2d/train-*\"}"
491
+ },
492
+ {
493
+ "name": "configs",
494
+ "value": "Name of the dataset subset: aokvqa {\"split\": \"train\", \"path\": \"aokvqa/train-*\"}"
495
+ },
496
+ {
497
+ "name": "configs",
498
+ "value": "Name of the dataset subset: chart2text {\"split\": \"train\", \"path\": \"chart2text/train-*\"}"
499
+ },
500
+ {
501
+ "name": "configs",
502
+ "value": "Name of the dataset subset: chartqa {\"split\": \"train\", \"path\": \"chartqa/train-*\"}"
503
+ },
504
+ {
505
+ "name": "configs",
506
+ "value": "Name of the dataset subset: clevr {\"split\": \"train\", \"path\": \"clevr/train-*\"}"
507
+ },
508
+ {
509
+ "name": "configs",
510
+ "value": "Name of the dataset subset: clevr_math {\"split\": \"train\", \"path\": \"clevr_math/train-*\"}"
511
+ },
512
+ {
513
+ "name": "configs",
514
+ "value": "Name of the dataset subset: cocoqa {\"split\": \"train\", \"path\": \"cocoqa/train-*\"}"
515
+ },
516
+ {
517
+ "name": "configs",
518
+ "value": "Name of the dataset subset: datikz {\"split\": \"train\", \"path\": \"datikz/train-*\"}"
519
+ },
520
+ {
521
+ "name": "configs",
522
+ "value": "Name of the dataset subset: diagram_image_to_text {\"split\": \"train\", \"path\": \"diagram_image_to_text/train-*\"}"
523
+ },
524
+ {
525
+ "name": "configs",
526
+ "value": "Name of the dataset subset: docvqa {\"split\": \"train\", \"path\": \"docvqa/train-*\"}"
527
+ },
528
+ {
529
+ "name": "configs",
530
+ "value": "Name of the dataset subset: dvqa {\"split\": \"train\", \"path\": \"dvqa/train-*\"}"
531
+ },
532
+ {
533
+ "name": "configs",
534
+ "value": "Name of the dataset subset: figureqa {\"split\": \"train\", \"path\": \"figureqa/train-*\"}"
535
+ },
536
+ {
537
+ "name": "configs",
538
+ "value": "Name of the dataset subset: finqa {\"split\": \"train\", \"path\": \"finqa/train-*\"}"
539
+ },
540
+ {
541
+ "name": "configs",
542
+ "value": "Name of the dataset subset: geomverse {\"split\": \"train\", \"path\": \"geomverse/train-*\"}"
543
+ },
544
+ {
545
+ "name": "configs",
546
+ "value": "Name of the dataset subset: hateful_memes {\"split\": \"train\", \"path\": \"hateful_memes/train-*\"}"
547
+ },
548
+ {
549
+ "name": "configs",
550
+ "value": "Name of the dataset subset: hitab {\"split\": \"train\", \"path\": \"hitab/train-*\"}"
551
+ },
552
+ {
553
+ "name": "configs",
554
+ "value": "Name of the dataset subset: iam {\"split\": \"train\", \"path\": \"iam/train-*\"}"
555
+ },
556
+ {
557
+ "name": "configs",
558
+ "value": "Name of the dataset subset: iconqa {\"split\": \"train\", \"path\": \"iconqa/train-*\"}"
559
+ },
560
+ {
561
+ "name": "configs",
562
+ "value": "Name of the dataset subset: infographic_vqa {\"split\": \"train\", \"path\": \"infographic_vqa/train-*\"}"
563
+ },
564
+ {
565
+ "name": "configs",
566
+ "value": "Name of the dataset subset: intergps {\"split\": \"train\", \"path\": \"intergps/train-*\"}"
567
+ },
568
+ {
569
+ "name": "configs",
570
+ "value": "Name of the dataset subset: localized_narratives {\"split\": \"train\", \"path\": \"localized_narratives/train-*\"}"
571
+ },
572
+ {
573
+ "name": "configs",
574
+ "value": "Name of the dataset subset: mapqa {\"split\": \"train\", \"path\": \"mapqa/train-*\"}"
575
+ },
576
+ {
577
+ "name": "configs",
578
+ "value": "Name of the dataset subset: mimic_cgd {\"split\": \"train\", \"path\": \"mimic_cgd/train-*\"}"
579
+ },
580
+ {
581
+ "name": "configs",
582
+ "value": "Name of the dataset subset: multihiertt {\"split\": \"train\", \"path\": \"multihiertt/train-*\"}"
583
+ },
584
+ {
585
+ "name": "configs",
586
+ "value": "Name of the dataset subset: nlvr2 {\"split\": \"train\", \"path\": \"nlvr2/train-*\"}"
587
+ },
588
+ {
589
+ "name": "configs",
590
+ "value": "Name of the dataset subset: ocrvqa {\"split\": \"train\", \"path\": \"ocrvqa/train-*\"}"
591
+ },
592
+ {
593
+ "name": "configs",
594
+ "value": "Name of the dataset subset: okvqa {\"split\": \"train\", \"path\": \"okvqa/train-*\"}"
595
+ },
596
+ {
597
+ "name": "configs",
598
+ "value": "Name of the dataset subset: plotqa {\"split\": \"train\", \"path\": \"plotqa/train-*\"}"
599
+ },
600
+ {
601
+ "name": "configs",
602
+ "value": "Name of the dataset subset: raven {\"split\": \"train\", \"path\": \"raven/train-*\"}"
603
+ },
604
+ {
605
+ "name": "configs",
606
+ "value": "Name of the dataset subset: rendered_text {\"split\": \"train\", \"path\": \"rendered_text/train-*\"}"
607
+ },
608
+ {
609
+ "name": "configs",
610
+ "value": "Name of the dataset subset: robut_sqa {\"split\": \"train\", \"path\": \"robut_sqa/train-*\"}"
611
+ },
612
+ {
613
+ "name": "configs",
614
+ "value": "Name of the dataset subset: robut_wikisql {\"split\": \"train\", \"path\": \"robut_wikisql/train-*\"}"
615
+ },
616
+ {
617
+ "name": "configs",
618
+ "value": "Name of the dataset subset: robut_wtq {\"split\": \"train\", \"path\": \"robut_wtq/train-*\"}"
619
+ },
620
+ {
621
+ "name": "configs",
622
+ "value": "Name of the dataset subset: scienceqa {\"split\": \"train\", \"path\": \"scienceqa/train-*\"}"
623
+ },
624
+ {
625
+ "name": "configs",
626
+ "value": "Name of the dataset subset: screen2words {\"split\": \"train\", \"path\": \"screen2words/train-*\"}"
627
+ },
628
+ {
629
+ "name": "configs",
630
+ "value": "Name of the dataset subset: spot_the_diff {\"split\": \"train\", \"path\": \"spot_the_diff/train-*\"}"
631
+ },
632
+ {
633
+ "name": "configs",
634
+ "value": "Name of the dataset subset: st_vqa {\"split\": \"train\", \"path\": \"st_vqa/train-*\"}"
635
+ },
636
+ {
637
+ "name": "configs",
638
+ "value": "Name of the dataset subset: tabmwp {\"split\": \"train\", \"path\": \"tabmwp/train-*\"}"
639
+ },
640
+ {
641
+ "name": "configs",
642
+ "value": "Name of the dataset subset: tallyqa {\"split\": \"train\", \"path\": \"tallyqa/train-*\"}"
643
+ },
644
+ {
645
+ "name": "configs",
646
+ "value": "Name of the dataset subset: tat_qa {\"split\": \"train\", \"path\": \"tat_qa/train-*\"}"
647
+ },
648
+ {
649
+ "name": "configs",
650
+ "value": "Name of the dataset subset: textcaps {\"split\": \"train\", \"path\": \"textcaps/train-*\"}"
651
+ },
652
+ {
653
+ "name": "configs",
654
+ "value": "Name of the dataset subset: textvqa {\"split\": \"train\", \"path\": \"textvqa/train-*\"}"
655
+ },
656
+ {
657
+ "name": "configs",
658
+ "value": "Name of the dataset subset: tqa {\"split\": \"train\", \"path\": \"tqa/train-*\"}"
659
+ },
660
+ {
661
+ "name": "configs",
662
+ "value": "Name of the dataset subset: vistext {\"split\": \"train\", \"path\": \"vistext/train-*\"}"
663
+ },
664
+ {
665
+ "name": "configs",
666
+ "value": "Name of the dataset subset: visual7w {\"split\": \"train\", \"path\": \"visual7w/train-*\"}"
667
+ },
668
+ {
669
+ "name": "configs",
670
+ "value": "Name of the dataset subset: visualmrc {\"split\": \"train\", \"path\": \"visualmrc/train-*\"}"
671
+ },
672
+ {
673
+ "name": "configs",
674
+ "value": "Name of the dataset subset: vqarad {\"split\": \"train\", \"path\": \"vqarad/train-*\"}"
675
+ },
676
+ {
677
+ "name": "configs",
678
+ "value": "Name of the dataset subset: vqav2 {\"split\": \"train\", \"path\": \"vqav2/train-*\"}"
679
+ },
680
+ {
681
+ "name": "configs",
682
+ "value": "Name of the dataset subset: vsr {\"split\": \"train\", \"path\": \"vsr/train-*\"}"
683
+ },
684
+ {
685
+ "name": "configs",
686
+ "value": "Name of the dataset subset: websight {\"split\": \"train\", \"path\": \"websight/train-*\"}"
687
+ }
688
+ ]
689
+ },
690
+ "governance": {
691
+ "owners": [
692
+ {
693
+ "organization": {
694
+ "name": "HuggingFaceM4",
695
+ "url": "https://huggingface.co/HuggingFaceM4"
696
+ }
697
+ }
698
+ ]
699
+ },
700
+ "description": "\n\t\n\t\t\n\t\tDataset Card for The Cauldron\n\t\n\n\n\n\t\n\t\t\n\t\tDataset description\n\t\n\nThe Cauldron is part of the Idefics2 release.\nIt is a massive collection of 50 vision-language datasets (training sets only) that were used for the fine-tuning of the vision-language model Idefics2.\n\n\t\n\t\t\n\t\tLoad the dataset\n\t\n\nTo load the dataset, install the library datasets with pip install datasets. Then,\nfrom datasets import load_dataset\nds = load_dataset(\"HuggingFaceM4/the_cauldron\", \"ai2d\")\n\nto download and load the\u2026 See the full description on the dataset page: https://huggingface.co/datasets/HuggingFaceM4/the_cauldron."
701
+ }
702
+ ]
703
+ },
704
+ {
705
+ "type": "data",
706
+ "bom-ref": "teknium/OpenHermes-2.5-1a7eb3be-7eaa-5577-91f6-d4ad0d639c6c",
707
+ "name": "teknium/OpenHermes-2.5",
708
+ "data": [
709
+ {
710
+ "type": "dataset",
711
+ "bom-ref": "teknium/OpenHermes-2.5-1a7eb3be-7eaa-5577-91f6-d4ad0d639c6c",
712
+ "name": "teknium/OpenHermes-2.5",
713
+ "contents": {
714
+ "url": "https://huggingface.co/datasets/teknium/OpenHermes-2.5",
715
+ "properties": [
716
+ {
717
+ "name": "language",
718
+ "value": "eng"
719
+ },
720
+ {
721
+ "name": "pretty_name",
722
+ "value": "OpenHermes 2.5"
723
+ }
724
+ ]
725
+ },
726
+ "governance": {
727
+ "owners": [
728
+ {
729
+ "organization": {
730
+ "name": "teknium",
731
+ "url": "https://huggingface.co/teknium"
732
+ }
733
+ }
734
+ ]
735
+ },
736
+ "description": "\n\n\t\n\t\t\n\t\tDataset Card for Dataset Name\n\t\n\nThis is the dataset that made OpenHermes 2.5 and Nous Hermes 2 series of models.\nSupport me on GitHub sponsors <3 : https://github.com/sponsors/teknium1\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\n\t\n\t\t\n\t\tDataset Description\n\t\n\nThe Open Hermes 2/2.5 and Nous Hermes 2 models have made significant advancements of SOTA LLM's over recent months, and are underpinned by this exact compilation and curation of many open source datasets and custom created synthetic datasets.\u2026 See the full description on the dataset page: https://huggingface.co/datasets/teknium/OpenHermes-2.5."
737
+ }
738
+ ]
739
+ },
740
+ {
741
+ "type": "data",
742
+ "bom-ref": "GAIR/lima-afa8f631-d0ed-59c0-a5a1-170c80a5117e",
743
+ "name": "GAIR/lima",
744
+ "data": [
745
+ {
746
+ "type": "dataset",
747
+ "bom-ref": "GAIR/lima-afa8f631-d0ed-59c0-a5a1-170c80a5117e",
748
+ "name": "GAIR/lima",
749
+ "contents": {
750
+ "url": "https://huggingface.co/datasets/GAIR/lima",
751
+ "properties": [
752
+ {
753
+ "name": "license",
754
+ "value": "other"
755
+ }
756
+ ]
757
+ },
758
+ "governance": {
759
+ "owners": [
760
+ {
761
+ "organization": {
762
+ "name": "GAIR",
763
+ "url": "https://huggingface.co/GAIR"
764
+ }
765
+ }
766
+ ]
767
+ },
768
+ "description": "A high-quality dataset for efficient instruction tuning."
769
+ }
770
+ ]
771
+ },
772
+ {
773
+ "type": "data",
774
+ "bom-ref": "databricks/databricks-dolly-15k-1008cfb1-7624-5c5b-93cc-d856239b86ea",
775
+ "name": "databricks/databricks-dolly-15k",
776
+ "data": [
777
+ {
778
+ "type": "dataset",
779
+ "bom-ref": "databricks/databricks-dolly-15k-1008cfb1-7624-5c5b-93cc-d856239b86ea",
780
+ "name": "databricks/databricks-dolly-15k",
781
+ "contents": {
782
+ "url": "https://huggingface.co/datasets/databricks/databricks-dolly-15k",
783
+ "properties": [
784
+ {
785
+ "name": "task_categories",
786
+ "value": "question-answering, summarization"
787
+ },
788
+ {
789
+ "name": "language",
790
+ "value": "en"
791
+ },
792
+ {
793
+ "name": "size_categories",
794
+ "value": "10K<n<100K"
795
+ },
796
+ {
797
+ "name": "license",
798
+ "value": "cc-by-sa-3.0"
799
+ }
800
+ ]
801
+ },
802
+ "governance": {
803
+ "owners": [
804
+ {
805
+ "organization": {
806
+ "name": "databricks",
807
+ "url": "https://huggingface.co/databricks"
808
+ }
809
+ }
810
+ ]
811
+ },
812
+ "description": "\n\t\n\t\t\n\t\tSummary\n\t\n\ndatabricks-dolly-15k is an open source dataset of instruction-following records generated by thousands of Databricks employees in several \nof the behavioral categories outlined in the InstructGPT paper, including brainstorming, classification, \nclosed QA, generation, information extraction, open QA, and summarization.\nThis dataset can be used for any purpose, whether academic or commercial, under the terms of the \nCreative Commons Attribution-ShareAlike 3.0 Unported\u2026 See the full description on the dataset page: https://huggingface.co/datasets/databricks/databricks-dolly-15k."
813
+ }
814
+ ]
815
+ },
816
+ {
817
+ "type": "data",
818
+ "bom-ref": "meta-math/MetaMathQA-c6cf810a-8b06-5552-a876-53681c5fe9a1",
819
+ "name": "meta-math/MetaMathQA",
820
+ "data": [
821
+ {
822
+ "type": "dataset",
823
+ "bom-ref": "meta-math/MetaMathQA-c6cf810a-8b06-5552-a876-53681c5fe9a1",
824
+ "name": "meta-math/MetaMathQA",
825
+ "contents": {
826
+ "url": "https://huggingface.co/datasets/meta-math/MetaMathQA",
827
+ "properties": [
828
+ {
829
+ "name": "license",
830
+ "value": "mit"
831
+ }
832
+ ]
833
+ },
834
+ "governance": {
835
+ "owners": [
836
+ {
837
+ "organization": {
838
+ "name": "meta-math",
839
+ "url": "https://huggingface.co/meta-math"
840
+ }
841
+ }
842
+ ]
843
+ },
844
+ "description": "View the project page:\nhttps://meta-math.github.io/\nsee our paper at https://arxiv.org/abs/2309.12284\n\n\t\n\t\t\n\t\tNote\n\t\n\nAll MetaMathQA data are augmented from the training sets of GSM8K and MATH. \nNone of the augmented data is from the testing set.\nYou can check the original_question in meta-math/MetaMathQA, each item is from the GSM8K or MATH train set.\n\n\t\n\t\t\n\t\tModel Details\n\t\n\nMetaMath-Mistral-7B is fully fine-tuned on the MetaMathQA datasets and based on the powerful Mistral-7B model. It is\u2026 See the full description on the dataset page: https://huggingface.co/datasets/meta-math/MetaMathQA."
845
+ }
846
+ ]
847
+ },
848
+ {
849
+ "type": "data",
850
+ "bom-ref": "TIGER-Lab/MathInstruct-9d9c997d-f6c1-5029-96fd-6003c4f0ec06",
851
+ "name": "TIGER-Lab/MathInstruct",
852
+ "data": [
853
+ {
854
+ "type": "dataset",
855
+ "bom-ref": "TIGER-Lab/MathInstruct-9d9c997d-f6c1-5029-96fd-6003c4f0ec06",
856
+ "name": "TIGER-Lab/MathInstruct",
857
+ "contents": {
858
+ "url": "https://huggingface.co/datasets/TIGER-Lab/MathInstruct",
859
+ "properties": [
860
+ {
861
+ "name": "task_categories",
862
+ "value": "text-generation"
863
+ },
864
+ {
865
+ "name": "language",
866
+ "value": "en"
867
+ },
868
+ {
869
+ "name": "size_categories",
870
+ "value": "100K<n<1M"
871
+ },
872
+ {
873
+ "name": "pretty_name",
874
+ "value": "MathInstruct"
875
+ },
876
+ {
877
+ "name": "license",
878
+ "value": "mit"
879
+ }
880
+ ]
881
+ },
882
+ "governance": {
883
+ "owners": [
884
+ {
885
+ "organization": {
886
+ "name": "TIGER-Lab",
887
+ "url": "https://huggingface.co/TIGER-Lab"
888
+ }
889
+ }
890
+ ]
891
+ },
892
+ "description": "\n\t\n\t\t\n\t\t\ud83e\udda3 MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning\n\t\n\nMathInstruct is a meticulously curated instruction tuning dataset that is lightweight yet generalizable. MathInstruct is compiled from 13 math rationale datasets, six of which are newly curated by this work. It uniquely focuses on the hybrid use of chain-of-thought (CoT) and program-of-thought (PoT) rationales, and ensures extensive coverage of diverse mathematical fields. \nProject Page:\u2026 See the full description on the dataset page: https://huggingface.co/datasets/TIGER-Lab/MathInstruct."
893
+ }
894
+ ]
895
+ },
896
+ {
897
+ "type": "data",
898
+ "bom-ref": "microsoft/orca-math-word-problems-200k-611afa9f-b6db-5b9f-9a51-598e4ce79d0e",
899
+ "name": "microsoft/orca-math-word-problems-200k",
900
+ "data": [
901
+ {
902
+ "type": "dataset",
903
+ "bom-ref": "microsoft/orca-math-word-problems-200k-611afa9f-b6db-5b9f-9a51-598e4ce79d0e",
904
+ "name": "microsoft/orca-math-word-problems-200k",
905
+ "contents": {
906
+ "url": "https://huggingface.co/datasets/microsoft/orca-math-word-problems-200k",
907
+ "properties": [
908
+ {
909
+ "name": "task_categories",
910
+ "value": "question-answering"
911
+ },
912
+ {
913
+ "name": "language",
914
+ "value": "en"
915
+ },
916
+ {
917
+ "name": "size_categories",
918
+ "value": "100K<n<1M"
919
+ },
920
+ {
921
+ "name": "configs",
922
+ "value": "Name of the dataset subset: default {\"split\": \"train\", \"path\": \"data/train-*\"}"
923
+ },
924
+ {
925
+ "name": "license",
926
+ "value": "mit"
927
+ }
928
+ ]
929
+ },
930
+ "governance": {
931
+ "owners": [
932
+ {
933
+ "organization": {
934
+ "name": "microsoft",
935
+ "url": "https://huggingface.co/microsoft"
936
+ }
937
+ }
938
+ ]
939
+ },
940
+ "description": "\n\t\n\t\t\n\t\tDataset Card\n\t\n\n\n\nThis dataset contains ~200K grade school math word problems. All the answers in this dataset is generated using Azure GPT4-Turbo. Please refer to Orca-Math: Unlocking the potential of\nSLMs in Grade School Math for details about the dataset construction. \n\n\t\n\t\t\n\t\tDataset Sources\n\t\n\n\n\n\nRepository: microsoft/orca-math-word-problems-200k\nPaper: Orca-Math: Unlocking the potential of\nSLMs in Grade School Math\n\n\n\t\n\t\t\n\t\tDirect Use\n\t\n\n\n\nThis dataset has been designed to\u2026 See the full description on the dataset page: https://huggingface.co/datasets/microsoft/orca-math-word-problems-200k."
941
+ }
942
+ ]
943
+ },
944
+ {
945
+ "type": "data",
946
+ "bom-ref": "camel-ai/math-9f7ffeb0-2fb3-5b72-9ca4-1b461f022e61",
947
+ "name": "camel-ai/math",
948
+ "data": [
949
+ {
950
+ "type": "dataset",
951
+ "bom-ref": "camel-ai/math-9f7ffeb0-2fb3-5b72-9ca4-1b461f022e61",
952
+ "name": "camel-ai/math",
953
+ "contents": {
954
+ "url": "https://huggingface.co/datasets/camel-ai/math",
955
+ "properties": [
956
+ {
957
+ "name": "task_categories",
958
+ "value": "text-generation"
959
+ },
960
+ {
961
+ "name": "language",
962
+ "value": "en"
963
+ },
964
+ {
965
+ "name": "pretty_name",
966
+ "value": "CAMEL Math"
967
+ },
968
+ {
969
+ "name": "license",
970
+ "value": "cc-by-nc-4.0"
971
+ }
972
+ ]
973
+ },
974
+ "governance": {
975
+ "owners": [
976
+ {
977
+ "organization": {
978
+ "name": "camel-ai",
979
+ "url": "https://huggingface.co/camel-ai"
980
+ }
981
+ }
982
+ ]
983
+ },
984
+ "description": "\n\t\n\t\t\n\t\tCAMEL: Communicative Agents for \u201cMind\u201d Exploration of Large Scale Language Model Society\n\t\n\n\nGithub: https://github.com/lightaime/camel\nWebsite: https://www.camel-ai.org/\nArxiv Paper: https://arxiv.org/abs/2303.17760\n\n\n\t\n\t\t\n\t\n\t\n\t\tDataset Summary\n\t\n\nMath dataset is composed of 50K problem-solution pairs obtained using GPT-4. The dataset problem-solutions pairs generating from 25 math topics, 25 subtopics for each topic and 80 problems for each \"topic,subtopic\" pairs.\nWe provide the data\u2026 See the full description on the dataset page: https://huggingface.co/datasets/camel-ai/math."
985
+ }
986
+ ]
987
+ },
988
+ {
989
+ "type": "data",
990
+ "bom-ref": "AtlasUnified/atlas-math-sets-49141027-0c69-515d-8182-254cf889efae",
991
+ "name": "AtlasUnified/atlas-math-sets",
992
+ "data": [
993
+ {
994
+ "type": "dataset",
995
+ "bom-ref": "AtlasUnified/atlas-math-sets-49141027-0c69-515d-8182-254cf889efae",
996
+ "name": "AtlasUnified/atlas-math-sets",
997
+ "contents": {
998
+ "url": "https://huggingface.co/datasets/AtlasUnified/atlas-math-sets",
999
+ "properties": [
1000
+ {
1001
+ "name": "task_categories",
1002
+ "value": "question-answering"
1003
+ },
1004
+ {
1005
+ "name": "language",
1006
+ "value": "en"
1007
+ },
1008
+ {
1009
+ "name": "size_categories",
1010
+ "value": "10M<n<100M"
1011
+ },
1012
+ {
1013
+ "name": "pretty_name",
1014
+ "value": "Atlas Math Sets"
1015
+ },
1016
+ {
1017
+ "name": "license",
1018
+ "value": "mit"
1019
+ }
1020
+ ]
1021
+ },
1022
+ "governance": {
1023
+ "owners": [
1024
+ {
1025
+ "organization": {
1026
+ "name": "AtlasUnified",
1027
+ "url": "https://huggingface.co/AtlasUnified"
1028
+ }
1029
+ }
1030
+ ]
1031
+ },
1032
+ "description": "\n\t\n\t\t\n\t\tATLAS MATH SETS\n\t\n\n\nThis set of data consists of mathematical computations. Simple in nature as it derived from python scripts, this dataset contains addition, subtraction, multiplication, division, fractions, decimals, square roots, cube roots, exponents, and factors.\nFormat of the JSONL is as follows:\n{\"answer\": \"[num]\", \"input\": \"[equation]\", \"output\": \"[num]\", \"instruction\": \"[pre-generated_instruction] [equation]\"}\n"
1033
+ }
1034
+ ]
1035
+ },
1036
+ {
1037
+ "type": "data",
1038
+ "bom-ref": "tiedong/goat-38642401-79d7-541d-a92f-d3d7acdb8db8",
1039
+ "name": "tiedong/goat",
1040
+ "data": [
1041
+ {
1042
+ "type": "dataset",
1043
+ "bom-ref": "tiedong/goat-38642401-79d7-541d-a92f-d3d7acdb8db8",
1044
+ "name": "tiedong/goat",
1045
+ "contents": {
1046
+ "url": "https://huggingface.co/datasets/tiedong/goat",
1047
+ "properties": [
1048
+ {
1049
+ "name": "task_categories",
1050
+ "value": "question-answering"
1051
+ },
1052
+ {
1053
+ "name": "language",
1054
+ "value": "en"
1055
+ },
1056
+ {
1057
+ "name": "size_categories",
1058
+ "value": "1M<n<10M"
1059
+ },
1060
+ {
1061
+ "name": "license",
1062
+ "value": "apache-2.0"
1063
+ }
1064
+ ]
1065
+ },
1066
+ "governance": {
1067
+ "owners": [
1068
+ {
1069
+ "organization": {
1070
+ "name": "tiedong",
1071
+ "url": "https://huggingface.co/tiedong"
1072
+ }
1073
+ }
1074
+ ]
1075
+ },
1076
+ "description": "\n\t\n\t\t\n\t\tDataset Card for Dataset Name\n\t\n\n\n\t\n\t\t\n\t\tDataset Summary\n\t\n\nThe dataset.json file contains ~1.7 million synthetic data for arithmetic tasks, generated by dataset.ipynb.\n\n\t\n\t\t\n\t\tSupported Tasks and Leaderboards\n\t\n\n[More Information Needed]\n\n\t\n\t\t\n\t\tLanguages\n\t\n\n[More Information Needed]\n\n\t\n\t\t\n\t\tDataset Structure\n\t\n\n\n\t\n\t\t\n\t\tData Instances\n\t\n\n[More Information Needed]\n\n\t\n\t\t\n\t\tData Fields\n\t\n\n[More Information Needed]\n\n\t\n\t\t\n\t\tData Splits\n\t\n\n[More Information Needed]\n\n\t\n\t\t\n\t\tDataset Creation\u2026 See the full description on the dataset page: https://huggingface.co/datasets/tiedong/goat."
1077
+ }
1078
+ ]
1079
+ },
1080
+ {
1081
+ "type": "data",
1082
+ "bom-ref": "Lin-Chen/ShareGPT4V-f6982603-3c10-5cd0-9d2d-83d573b61341",
1083
+ "name": "Lin-Chen/ShareGPT4V",
1084
+ "data": [
1085
+ {
1086
+ "type": "dataset",
1087
+ "bom-ref": "Lin-Chen/ShareGPT4V-f6982603-3c10-5cd0-9d2d-83d573b61341",
1088
+ "name": "Lin-Chen/ShareGPT4V",
1089
+ "contents": {
1090
+ "url": "https://huggingface.co/datasets/Lin-Chen/ShareGPT4V",
1091
+ "properties": [
1092
+ {
1093
+ "name": "task_categories",
1094
+ "value": "visual-question-answering, question-answering"
1095
+ },
1096
+ {
1097
+ "name": "language",
1098
+ "value": "en"
1099
+ },
1100
+ {
1101
+ "name": "size_categories",
1102
+ "value": "1M<n"
1103
+ },
1104
+ {
1105
+ "name": "pretty_name",
1106
+ "value": "ShareGPT4V Captions 1.2M Dataset Card"
1107
+ },
1108
+ {
1109
+ "name": "configs",
1110
+ "value": "Name of the dataset subset: ShareGPT4V \"s\", \"h\", \"a\", \"r\", \"e\", \"g\", \"p\", \"t\", \"4\", \"v\", \"_\", \"i\", \"n\", \"s\", \"t\", \"r\", \"u\", \"c\", \"t\", \"_\", \"g\", \"p\", \"t\", \"4\", \"-\", \"v\", \"i\", \"s\", \"i\", \"o\", \"n\", \"_\", \"c\", \"a\", \"p\", \"1\", \"0\", \"0\", \"k\", \".\", \"j\", \"s\", \"o\", \"n\""
1111
+ },
1112
+ {
1113
+ "name": "configs",
1114
+ "value": "Name of the dataset subset: ShareGPT4V-PT \"s\", \"h\", \"a\", \"r\", \"e\", \"-\", \"c\", \"a\", \"p\", \"t\", \"i\", \"o\", \"n\", \"e\", \"r\", \"_\", \"c\", \"o\", \"c\", \"o\", \"_\", \"l\", \"c\", \"s\", \"_\", \"s\", \"a\", \"m\", \"_\", \"1\", \"2\", \"4\", \"6\", \"k\", \"_\", \"1\", \"1\", \"0\", \"7\", \".\", \"j\", \"s\", \"o\", \"n\""
1115
+ },
1116
+ {
1117
+ "name": "license",
1118
+ "value": "cc-by-nc-4.0"
1119
+ }
1120
+ ]
1121
+ },
1122
+ "governance": {
1123
+ "owners": [
1124
+ {
1125
+ "organization": {
1126
+ "name": "Lin-Chen",
1127
+ "url": "https://huggingface.co/Lin-Chen"
1128
+ }
1129
+ }
1130
+ ]
1131
+ },
1132
+ "description": "\n\t\n\t\t\n\t\tNews\n\t\n\n[2024/5/8] We released ShareGPT4Video, a large-scale video-caption dataset, with 40K captions annotated by GPT4V and 4.8M captions annotated by our ShareCaptioner-Video. The total videos last with 300 hours and 3000 hours separately!\n\n\t\n\t\t\n\t\tShareGPT4V 1.2M Dataset Card\n\t\n\n\n\t\n\t\t\n\t\tDataset details\n\t\n\nDataset type:\nShareGPT4V Captions 1.2M is a set of GPT4-Vision-powered multi-modal captions data.\nIt is constructed to enhance modality alignment and fine-grained visual concept\u2026 See the full description on the dataset page: https://huggingface.co/datasets/Lin-Chen/ShareGPT4V."
1133
+ }
1134
+ ]
1135
+ },
1136
+ {
1137
+ "type": "data",
1138
+ "bom-ref": "jxu124/llava_conversation_58k-7dcd95f0-d26a-5075-89f4-4afc13a5b93f",
1139
+ "name": "jxu124/llava_conversation_58k",
1140
+ "data": [
1141
+ {
1142
+ "type": "dataset",
1143
+ "bom-ref": "jxu124/llava_conversation_58k-7dcd95f0-d26a-5075-89f4-4afc13a5b93f",
1144
+ "name": "jxu124/llava_conversation_58k",
1145
+ "contents": {
1146
+ "url": "https://huggingface.co/datasets/jxu124/llava_conversation_58k"
1147
+ },
1148
+ "governance": {
1149
+ "owners": [
1150
+ {
1151
+ "organization": {
1152
+ "name": "jxu124",
1153
+ "url": "https://huggingface.co/jxu124"
1154
+ }
1155
+ }
1156
+ ]
1157
+ },
1158
+ "description": "\n\t\n\t\t\n\t\tDataset Card for \"llava_conversation_58k\"\n\t\n\nMore Information needed\n"
1159
+ }
1160
+ ]
1161
+ }
1162
+ ]
1163
+ }