Hugging Face's logo

openchat
/
openchat_3.5

Text Generation
Transformers
PyTorch
mistral
openchat
C-RLFT
conversational
text-generation-inference
Model card Files Community
50

add AIBOM

#50
by sabato-nocera - opened
base: refs/heads/main
←
from: refs/pr/50
Discussion Files changed
+526
-0
Files changed (1) hide show
  1. openchat_openchat_3.5.json +526 -0
openchat_openchat_3.5.json ADDED
@@ -0,0 +1,526 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bomFormat": "CycloneDX",
3
+ "specVersion": "1.6",
4
+ "serialNumber": "urn:uuid:47a63261-3969-4c57-9e56-fb97f0d285a2",
5
+ "version": 1,
6
+ "metadata": {
7
+ "timestamp": "2025-06-05T09:41:28.741689+00:00",
8
+ "component": {
9
+ "type": "machine-learning-model",
10
+ "bom-ref": "openchat/openchat_3.5-7973a308-bdbf-59a9-9f73-be9d9f2b78c3",
11
+ "name": "openchat/openchat_3.5",
12
+ "externalReferences": [
13
+ {
14
+ "url": "https://huggingface.co/openchat/openchat_3.5",
15
+ "type": "documentation"
16
+ }
17
+ ],
18
+ "modelCard": {
19
+ "modelParameters": {
20
+ "task": "text-generation",
21
+ "architectureFamily": "mistral",
22
+ "modelArchitecture": "MistralForCausalLM",
23
+ "datasets": [
24
+ {
25
+ "ref": "openchat/openchat_sharegpt4_dataset-79a9a029-636a-5348-a67b-03818aca7f78"
26
+ },
27
+ {
28
+ "ref": "imone/OpenOrca_FLAN-56466c9b-33bb-5f23-ab7c-388f28f07644"
29
+ },
30
+ {
31
+ "ref": "LDJnr/LessWrong-Amplify-Instruct-fd396583-6aa0-5026-9748-4409738f0812"
32
+ },
33
+ {
34
+ "ref": "LDJnr/Pure-Dove-e5138f01-f77d-5510-9285-df11d660b143"
35
+ },
36
+ {
37
+ "ref": "LDJnr/Verified-Camel-6c954918-6150-534c-952b-ea2cff17c0b2"
38
+ },
39
+ {
40
+ "ref": "tiedong/goat-38642401-79d7-541d-a92f-d3d7acdb8db8"
41
+ },
42
+ {
43
+ "ref": "glaiveai/glaive-code-assistant-4cf9eb44-c4b0-5c31-b48c-ce95c2926a6d"
44
+ },
45
+ {
46
+ "ref": "meta-math/MetaMathQA-c6cf810a-8b06-5552-a876-53681c5fe9a1"
47
+ },
48
+ {
49
+ "ref": "OpenAssistant/oasst_top1_2023-08-25-10cff0b1-2289-5b35-8ea8-59253cea318a"
50
+ },
51
+ {
52
+ "ref": "TIGER-Lab/MathInstruct-9d9c997d-f6c1-5029-96fd-6003c4f0ec06"
53
+ }
54
+ ]
55
+ },
56
+ "properties": [
57
+ {
58
+ "name": "library_name",
59
+ "value": "transformers"
60
+ }
61
+ ]
62
+ },
63
+ "authors": [
64
+ {
65
+ "name": "openchat"
66
+ }
67
+ ],
68
+ "licenses": [
69
+ {
70
+ "license": {
71
+ "id": "Apache-2.0",
72
+ "url": "https://spdx.org/licenses/Apache-2.0.html"
73
+ }
74
+ }
75
+ ],
76
+ "tags": [
77
+ "transformers",
78
+ "pytorch",
79
+ "mistral",
80
+ "text-generation",
81
+ "openchat",
82
+ "C-RLFT",
83
+ "conversational",
84
+ "dataset:openchat/openchat_sharegpt4_dataset",
85
+ "dataset:imone/OpenOrca_FLAN",
86
+ "dataset:LDJnr/LessWrong-Amplify-Instruct",
87
+ "dataset:LDJnr/Pure-Dove",
88
+ "dataset:LDJnr/Verified-Camel",
89
+ "dataset:tiedong/goat",
90
+ "dataset:glaiveai/glaive-code-assistant",
91
+ "dataset:meta-math/MetaMathQA",
92
+ "dataset:OpenAssistant/oasst_top1_2023-08-25",
93
+ "dataset:TIGER-Lab/MathInstruct",
94
+ "arxiv:2309.11235",
95
+ "arxiv:2303.08774",
96
+ "license:apache-2.0",
97
+ "autotrain_compatible",
98
+ "text-generation-inference",
99
+ "endpoints_compatible",
100
+ "region:us"
101
+ ]
102
+ }
103
+ },
104
+ "components": [
105
+ {
106
+ "type": "data",
107
+ "bom-ref": "openchat/openchat_sharegpt4_dataset-79a9a029-636a-5348-a67b-03818aca7f78",
108
+ "name": "openchat/openchat_sharegpt4_dataset",
109
+ "data": [
110
+ {
111
+ "type": "dataset",
112
+ "bom-ref": "openchat/openchat_sharegpt4_dataset-79a9a029-636a-5348-a67b-03818aca7f78",
113
+ "name": "openchat/openchat_sharegpt4_dataset",
114
+ "contents": {
115
+ "url": "https://huggingface.co/datasets/openchat/openchat_sharegpt4_dataset",
116
+ "properties": [
117
+ {
118
+ "name": "task_categories",
119
+ "value": "conversational, text-generation"
120
+ },
121
+ {
122
+ "name": "language",
123
+ "value": "en"
124
+ },
125
+ {
126
+ "name": "size_categories",
127
+ "value": "1K<n<10K"
128
+ },
129
+ {
130
+ "name": "pretty_name",
131
+ "value": "OpenChat"
132
+ }
133
+ ]
134
+ },
135
+ "governance": {
136
+ "owners": [
137
+ {
138
+ "organization": {
139
+ "name": "openchat",
140
+ "url": "https://huggingface.co/openchat"
141
+ }
142
+ }
143
+ ]
144
+ },
145
+ "description": "This repository contains cleaned and filtered ShareGPT GPT-4 data used to train OpenChat. Details can be found in the OpenChat repository.\n"
146
+ }
147
+ ]
148
+ },
149
+ {
150
+ "type": "data",
151
+ "bom-ref": "imone/OpenOrca_FLAN-56466c9b-33bb-5f23-ab7c-388f28f07644",
152
+ "name": "imone/OpenOrca_FLAN",
153
+ "data": [
154
+ {
155
+ "type": "dataset",
156
+ "bom-ref": "imone/OpenOrca_FLAN-56466c9b-33bb-5f23-ab7c-388f28f07644",
157
+ "name": "imone/OpenOrca_FLAN",
158
+ "contents": {
159
+ "url": "https://huggingface.co/datasets/imone/OpenOrca_FLAN",
160
+ "properties": [
161
+ {
162
+ "name": "license",
163
+ "value": "mit"
164
+ }
165
+ ]
166
+ },
167
+ "governance": {
168
+ "owners": [
169
+ {
170
+ "organization": {
171
+ "name": "imone",
172
+ "url": "https://huggingface.co/imone"
173
+ }
174
+ }
175
+ ]
176
+ },
177
+ "description": "This is the OpenOrca GPT4 subset with the original FLAN answers. Each even row (indexed starting from 0) contains the OpenOrca GPT4 answer, while each odd row contains the corresponding FLAN answer.\n"
178
+ }
179
+ ]
180
+ },
181
+ {
182
+ "type": "data",
183
+ "bom-ref": "LDJnr/LessWrong-Amplify-Instruct-fd396583-6aa0-5026-9748-4409738f0812",
184
+ "name": "LDJnr/LessWrong-Amplify-Instruct",
185
+ "data": [
186
+ {
187
+ "type": "dataset",
188
+ "bom-ref": "LDJnr/LessWrong-Amplify-Instruct-fd396583-6aa0-5026-9748-4409738f0812",
189
+ "name": "LDJnr/LessWrong-Amplify-Instruct",
190
+ "contents": {
191
+ "url": "https://huggingface.co/datasets/LDJnr/LessWrong-Amplify-Instruct",
192
+ "properties": [
193
+ {
194
+ "name": "task_categories",
195
+ "value": "conversational, question-answering, text-generation"
196
+ },
197
+ {
198
+ "name": "language",
199
+ "value": "en"
200
+ },
201
+ {
202
+ "name": "size_categories",
203
+ "value": "n<1K"
204
+ },
205
+ {
206
+ "name": "pretty_name",
207
+ "value": "LessWrong-Amplify-Instruct"
208
+ },
209
+ {
210
+ "name": "license",
211
+ "value": "apache-2.0"
212
+ }
213
+ ]
214
+ },
215
+ "governance": {
216
+ "owners": [
217
+ {
218
+ "organization": {
219
+ "name": "LDJnr",
220
+ "url": "https://huggingface.co/LDJnr"
221
+ }
222
+ }
223
+ ]
224
+ },
225
+ "description": "\n\t\n\t\t\n\t\tThis is the Official LessWrong-Amplify-Instruct dataset. Over 500 multi-turn examples, and many more coming soon!\n\t\n\n\nThis leverages Amplify-Instruct method to extend thousands of scraped Less-Wrong posts into advanced in-depth multi-turn conversations.\n\nComprised of over 500 highly filtered multi-turn synthetic conversations.\n\nAverage context length per conversation is over 2,000 tokens. (will measure this more accurately soon)\n\nSynthetically created using a newly developed pipeline\u2026 See the full description on the dataset page: https://huggingface.co/datasets/LDJnr/LessWrong-Amplify-Instruct."
226
+ }
227
+ ]
228
+ },
229
+ {
230
+ "type": "data",
231
+ "bom-ref": "LDJnr/Pure-Dove-e5138f01-f77d-5510-9285-df11d660b143",
232
+ "name": "LDJnr/Pure-Dove",
233
+ "data": [
234
+ {
235
+ "type": "dataset",
236
+ "bom-ref": "LDJnr/Pure-Dove-e5138f01-f77d-5510-9285-df11d660b143",
237
+ "name": "LDJnr/Pure-Dove",
238
+ "contents": {
239
+ "url": "https://huggingface.co/datasets/LDJnr/Pure-Dove",
240
+ "properties": [
241
+ {
242
+ "name": "task_categories",
243
+ "value": "conversational, question-answering, text-generation"
244
+ },
245
+ {
246
+ "name": "language",
247
+ "value": "en"
248
+ },
249
+ {
250
+ "name": "size_categories",
251
+ "value": "1K<n<10K"
252
+ },
253
+ {
254
+ "name": "pretty_name",
255
+ "value": "Pure-Dove"
256
+ },
257
+ {
258
+ "name": "license",
259
+ "value": "apache-2.0"
260
+ }
261
+ ]
262
+ },
263
+ "governance": {
264
+ "owners": [
265
+ {
266
+ "organization": {
267
+ "name": "LDJnr",
268
+ "url": "https://huggingface.co/LDJnr"
269
+ }
270
+ }
271
+ ]
272
+ },
273
+ "description": "\n\t\n\t\t\n\t\tThis is the Official Pure-Dove dataset. Over 3K multi-turn examples, and many more coming soon!\n\t\n\nThis dataset aims to be the largest highest quality cluster of real human back and forth conversations with GPT-4.\nSteps have even been done to ensure that only the best GPT-4 conversations in comparisons are kept, there are many instances where two GPT-4 responses are rated as equal to eachother or as both bad. We exclude all such responses from Pure Dove and make sure to only include\u2026 See the full description on the dataset page: https://huggingface.co/datasets/LDJnr/Pure-Dove."
274
+ }
275
+ ]
276
+ },
277
+ {
278
+ "type": "data",
279
+ "bom-ref": "LDJnr/Verified-Camel-6c954918-6150-534c-952b-ea2cff17c0b2",
280
+ "name": "LDJnr/Verified-Camel",
281
+ "data": [
282
+ {
283
+ "type": "dataset",
284
+ "bom-ref": "LDJnr/Verified-Camel-6c954918-6150-534c-952b-ea2cff17c0b2",
285
+ "name": "LDJnr/Verified-Camel",
286
+ "contents": {
287
+ "url": "https://huggingface.co/datasets/LDJnr/Verified-Camel",
288
+ "properties": [
289
+ {
290
+ "name": "task_categories",
291
+ "value": "conversational, question-answering, text-generation"
292
+ },
293
+ {
294
+ "name": "language",
295
+ "value": "en"
296
+ },
297
+ {
298
+ "name": "size_categories",
299
+ "value": "n<1K"
300
+ },
301
+ {
302
+ "name": "pretty_name",
303
+ "value": "Verified-Camel"
304
+ },
305
+ {
306
+ "name": "license",
307
+ "value": "apache-2.0"
308
+ }
309
+ ]
310
+ },
311
+ "governance": {
312
+ "owners": [
313
+ {
314
+ "organization": {
315
+ "name": "LDJnr",
316
+ "url": "https://huggingface.co/LDJnr"
317
+ }
318
+ }
319
+ ]
320
+ },
321
+ "description": "\n\t\n\t\t\n\t\tThis is the Official Verified Camel dataset. Just over 100 verified examples, and many more coming soon!\n\t\n\n\nComprised of over 100 highly filtered and curated examples from specific portions of CamelAI stem datasets. \n\nThese examples are verified to be true by experts in the specific related field, with atleast a bachelors degree in the subject.\n\nRoughly 30-40% of the originally curated data from CamelAI was found to have atleast minor errors and/or incoherent questions(as determined\u2026 See the full description on the dataset page: https://huggingface.co/datasets/LDJnr/Verified-Camel."
322
+ }
323
+ ]
324
+ },
325
+ {
326
+ "type": "data",
327
+ "bom-ref": "tiedong/goat-38642401-79d7-541d-a92f-d3d7acdb8db8",
328
+ "name": "tiedong/goat",
329
+ "data": [
330
+ {
331
+ "type": "dataset",
332
+ "bom-ref": "tiedong/goat-38642401-79d7-541d-a92f-d3d7acdb8db8",
333
+ "name": "tiedong/goat",
334
+ "contents": {
335
+ "url": "https://huggingface.co/datasets/tiedong/goat",
336
+ "properties": [
337
+ {
338
+ "name": "task_categories",
339
+ "value": "question-answering"
340
+ },
341
+ {
342
+ "name": "language",
343
+ "value": "en"
344
+ },
345
+ {
346
+ "name": "size_categories",
347
+ "value": "1M<n<10M"
348
+ },
349
+ {
350
+ "name": "license",
351
+ "value": "apache-2.0"
352
+ }
353
+ ]
354
+ },
355
+ "governance": {
356
+ "owners": [
357
+ {
358
+ "organization": {
359
+ "name": "tiedong",
360
+ "url": "https://huggingface.co/tiedong"
361
+ }
362
+ }
363
+ ]
364
+ },
365
+ "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."
366
+ }
367
+ ]
368
+ },
369
+ {
370
+ "type": "data",
371
+ "bom-ref": "glaiveai/glaive-code-assistant-4cf9eb44-c4b0-5c31-b48c-ce95c2926a6d",
372
+ "name": "glaiveai/glaive-code-assistant",
373
+ "data": [
374
+ {
375
+ "type": "dataset",
376
+ "bom-ref": "glaiveai/glaive-code-assistant-4cf9eb44-c4b0-5c31-b48c-ce95c2926a6d",
377
+ "name": "glaiveai/glaive-code-assistant",
378
+ "contents": {
379
+ "url": "https://huggingface.co/datasets/glaiveai/glaive-code-assistant",
380
+ "properties": [
381
+ {
382
+ "name": "size_categories",
383
+ "value": "100K<n<1M"
384
+ },
385
+ {
386
+ "name": "license",
387
+ "value": "apache-2.0"
388
+ }
389
+ ]
390
+ },
391
+ "governance": {
392
+ "owners": [
393
+ {
394
+ "organization": {
395
+ "name": "glaiveai",
396
+ "url": "https://huggingface.co/glaiveai"
397
+ }
398
+ }
399
+ ]
400
+ },
401
+ "description": "\n\t\n\t\t\n\t\tGlaive-code-assistant\n\t\n\nGlaive-code-assistant is a dataset of ~140k code problems and solutions generated using Glaive\u2019s synthetic data generation platform.\nThe data is intended to be used to make models act as code assistants, and so the data is structured in a QA format where the questions are worded similar to how real users will ask code related questions.\nThe data has ~60% python samples.\nTo report any problems or suggestions in the data, join the Glaive discord\n"
402
+ }
403
+ ]
404
+ },
405
+ {
406
+ "type": "data",
407
+ "bom-ref": "meta-math/MetaMathQA-c6cf810a-8b06-5552-a876-53681c5fe9a1",
408
+ "name": "meta-math/MetaMathQA",
409
+ "data": [
410
+ {
411
+ "type": "dataset",
412
+ "bom-ref": "meta-math/MetaMathQA-c6cf810a-8b06-5552-a876-53681c5fe9a1",
413
+ "name": "meta-math/MetaMathQA",
414
+ "contents": {
415
+ "url": "https://huggingface.co/datasets/meta-math/MetaMathQA",
416
+ "properties": [
417
+ {
418
+ "name": "license",
419
+ "value": "mit"
420
+ }
421
+ ]
422
+ },
423
+ "governance": {
424
+ "owners": [
425
+ {
426
+ "organization": {
427
+ "name": "meta-math",
428
+ "url": "https://huggingface.co/meta-math"
429
+ }
430
+ }
431
+ ]
432
+ },
433
+ "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."
434
+ }
435
+ ]
436
+ },
437
+ {
438
+ "type": "data",
439
+ "bom-ref": "OpenAssistant/oasst_top1_2023-08-25-10cff0b1-2289-5b35-8ea8-59253cea318a",
440
+ "name": "OpenAssistant/oasst_top1_2023-08-25",
441
+ "data": [
442
+ {
443
+ "type": "dataset",
444
+ "bom-ref": "OpenAssistant/oasst_top1_2023-08-25-10cff0b1-2289-5b35-8ea8-59253cea318a",
445
+ "name": "OpenAssistant/oasst_top1_2023-08-25",
446
+ "contents": {
447
+ "url": "https://huggingface.co/datasets/OpenAssistant/oasst_top1_2023-08-25",
448
+ "properties": [
449
+ {
450
+ "name": "task_categories",
451
+ "value": "conversational"
452
+ },
453
+ {
454
+ "name": "size_categories",
455
+ "value": "10K<n<100K"
456
+ },
457
+ {
458
+ "name": "license",
459
+ "value": "apache-2.0"
460
+ }
461
+ ]
462
+ },
463
+ "governance": {
464
+ "owners": [
465
+ {
466
+ "organization": {
467
+ "name": "OpenAssistant",
468
+ "url": "https://huggingface.co/OpenAssistant"
469
+ }
470
+ }
471
+ ]
472
+ },
473
+ "description": "\n\t\n\t\t\n\t\tOpenAssistant TOP-1 Conversation Threads\n\t\n\n\nGuanacco style export of the best conversation threads from the open-assistant.io database\nexported August 25, 2023\njsonl files with chatml formatted conversations\ntrain: 12,947 samples / valid: 680 samples\n\n"
474
+ }
475
+ ]
476
+ },
477
+ {
478
+ "type": "data",
479
+ "bom-ref": "TIGER-Lab/MathInstruct-9d9c997d-f6c1-5029-96fd-6003c4f0ec06",
480
+ "name": "TIGER-Lab/MathInstruct",
481
+ "data": [
482
+ {
483
+ "type": "dataset",
484
+ "bom-ref": "TIGER-Lab/MathInstruct-9d9c997d-f6c1-5029-96fd-6003c4f0ec06",
485
+ "name": "TIGER-Lab/MathInstruct",
486
+ "contents": {
487
+ "url": "https://huggingface.co/datasets/TIGER-Lab/MathInstruct",
488
+ "properties": [
489
+ {
490
+ "name": "task_categories",
491
+ "value": "text-generation"
492
+ },
493
+ {
494
+ "name": "language",
495
+ "value": "en"
496
+ },
497
+ {
498
+ "name": "size_categories",
499
+ "value": "100K<n<1M"
500
+ },
501
+ {
502
+ "name": "pretty_name",
503
+ "value": "MathInstruct"
504
+ },
505
+ {
506
+ "name": "license",
507
+ "value": "mit"
508
+ }
509
+ ]
510
+ },
511
+ "governance": {
512
+ "owners": [
513
+ {
514
+ "organization": {
515
+ "name": "TIGER-Lab",
516
+ "url": "https://huggingface.co/TIGER-Lab"
517
+ }
518
+ }
519
+ ]
520
+ },
521
+ "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."
522
+ }
523
+ ]
524
+ }
525
+ ]
526
+ }