mlx-examples

zhangyiss/mlx-examples

Fork 0

mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-08-27 21:49:44 +08:00

Commit Graph

Select branches

Hide Pull Requests

awq

awq-tq

dist-eval

distributed-layers

fix_whisper_temp

fix_wwdc_notebook_models

flux-dist-improv

flux-qlora

load-gguf

main

openlm

packed-quants

#1

#10

#1001

#1003

#1004

#1006

#1009

#1012

#1013

#1014

#1015

#1016

#102

#1020

#1023

#1024

#1026

#1027

#1028

#103

#1035

#1036

#1037

#1038

#1040

#1045

#1047

#1048

#1048

#1049

#105

#1050

#1054

#1055

#106

#1061

#1062

#1063

#1065

#1068

#1069

#107

#1070

#1072

#1074

#1075

#1078

#1079

#108

#1080

#1081

#1082

#1085

#1089

#1090

#1092

#1093

#1094

#1096

#1099

#110

#1100

#1103

#1105

#1113

#1114

#1115

#1117

#1118

#1119

#112

#1121

#1122

#1125

#1128

#1129

#113

#1131

#1132

#1133

#1135

#1137

#1140

#1141

#1143

#1144

#1145

#1146

#1148

#1149

#115

#1152

#1153

#1154

#1155

#1156

#1157

#1158

#1159

#116

#1163

#1164

#1166

#1173

#1174

#1176

#1178

#1180

#1189

#1191

#1192

#1193

#1194

#1196

#1197

#1199

#12

#1200

#1202

#1204

#1205

#1206

#1208

#1209

#121

#1210

#1211

#1212

#1213

#1214

#1215

#1216

#1217

#1220

#1222

#1225

#1228

#1229

#123

#1230

#1230

#1231

#1231

#1233

#1234

#1235

#1240

#1241

#1242

#1246

#1249

#1250

#1251

#1253

#1257

#1259

#1260

#1263

#1265

#1267

#1270

#1271

#1272

#1273

#1276

#1277

#1278

#1279

#1280

#1283

#1287

#129

#1291

#1294

#1295

#1297

#1298

#1299

#1300

#1301

#1302

#1304

#1305

#1308

#1311

#1312

#1314

#1315

#1316

#1319

#1321

#1322

#1323

#1324

#1325

#1326

#133

#1330

#1331

#1332

#1336

#1338

#1339

#134

#1340

#1342

#1346

#1348

#1349

#1350

#1353

#1358

#1359

#136

#1364

#1365

#1367

#1370

#1371

#1375

#1375

#1377

#1377

#1383

#1383

#1385

#1385

#1386

#1386

#14

#140

#141

#144

#145

#147

#149

#151

#152

#153

#154

#157

#158

#159

#160

#161

#162

#163

#164

#165

#166

#167

#169

#171

#172

#173

#174

#176

#177

#178

#180

#183

#184

#186

#187

#189

#19

#190

#191

#192

#193

#195

#197

#198

#2

#200

#201

#202

#203

#205

#208

#211

#213

#214

#215

#219

#22

#221

#222

#227

#229

#23

#231

#234

#235

#237

#238

#24

#240

#241

#242

#243

#245

#248

#250

#251

#252

#253

#254

#255

#257

#260

#263

#264

#265

#266

#269

#27

#270

#271

#272

#274

#275

#276

#278

#282

#284

#285

#287

#290

#291

#292

#293

#294

#295

#30

#300

#301

#302

#303

#306

#307

#308

#309

#310

#311

#312

#315

#318

#319

#32

#320

#321

#325

#326

#33

#331

#333

#335

#337

#338

#340

#342

#343

#347

#350

#351

#352

#353

#354

#358

#36

#360

#361

#363

#364

#365

#366

#369

#37

#373

#375

#377

#378

#379

#380

#386

#387

#388

#389

#391

#392

#393

#396

#397

#398

#399

#40

#401

#405

#408

#409

#41

#41

#411

#413

#414

#415

#417

#418

#419

#42

#420

#421

#424

#426

#427

#429

#43

#431

#432

#433

#439

#441

#443

#445

#446

#449

#45

#450

#451

#453

#455

#457

#458

#461

#462

#466

#467

#468

#469

#47

#470

#471

#472

#474

#475

#479

#48

#482

#483

#483

#486

#489

#491

#494

#495

#496

#497

#498

#5

#50

#501

#502

#503

#505

#506

#509

#51

#510

#514

#515

#516

#518

#519

#52

#520

#521

#522

#523

#528

#53

#530

#531

#534

#536

#539

#541

#544

#545

#546

#547

#548

#549

#55

#552

#555

#558

#562

#563

#565

#566

#569

#570

#571

#572

#573

#574

#577

#578

#580

#581

#585

#589

#590

#591

#592

#595

#596

#599

#602

#603

#604

#608

#609

#610

#611

#613

#614

#62

#621

#623

#628

#632

#633

#634

#636

#639

#64

#640

#643

#644

#645

#648

#650

#651

#654

#657

#66

#661

#665

#666

#667

#668

#670

#673

#674

#675

#676

#679

#680

#681

#682

#683

#684

#685

#687

#688

#69

#690

#691

#693

#694

#697

#698

#7

#701

#702

#703

#705

#707

#708

#711

#712

#715

#716

#717

#719

#720

#721

#729

#73

#731

#735

#736

#739

#74

#740

#743

#744

#746

#749

#75

#752

#753

#758

#76

#760

#763

#766

#77

#770

#773

#775

#778

#779

#78

#782

#789

#79

#790

#792

#793

#794

#797

#798

#8

#80

#800

#802

#803

#806

#807

#810

#813

#817

#818

#82

#821

#822

#824

#825

#827

#828

#830

#831

#833

#835

#837

#838

#839

#84

#840

#85

#851

#852

#853

#855

#856

#857

#86

#863

#867

#87

#871

#877

#879

#88

#882

#885

#886

#888

#889

#89

#890

#891

#895

#898

#899

#90

#902

#903

#904

#905

#906

#907

#911

#913

#914

#915

#915

#920

#923

#926

#93

#931

#932

#935

#936

#937

#94

#940

#942

#945

#946

#948

#949

#954

#955

#956

#957

#96

#960

#961

#962

#963

#965

#969

#97

#971

#971

#973

#979

#98

#981

#983

#984

#989

#99

#990

#991

#993

#995

#996

#998

3aaf2d6c9f

Merge branch 'main' into adding-dpo-training Gökdeniz Gülmez 2025-03-08 10:07:48 +0100
292979d447

Merge branch 'ml-explore:main' into main chaihahaha 2025-03-08 12:06:04 +0800
d2e02b3aae

fix mixed quant option (#1326) Awni Hannun 2025-03-07 08:35:48 -0800
c72811da57 fix mixed quant option Awni Hannun 2025-03-07 06:55:35 -0800
595f5da146

remove lm head if unused (#1324) Awni Hannun 2025-03-06 15:35:47 -0800
877d2a345b

Change DEFAULT_SEED to None for stochastic generation by default (#1323) cavit99 2025-03-06 14:49:35 +0000
bc2fcec230

Update llms/mlx_lm/generate.py Awni Hannun 2025-03-06 06:45:59 -0800
421b0219a9

Update llms/mlx_lm/chat.py Awni Hannun 2025-03-06 06:45:52 -0800
717e415ad4 remove lm head if unused Awni Hannun 2025-03-06 06:18:46 -0800
5a4252f290 Change DEFAULT_SEED to None for stochastic generation by default Cavit Erginsoy 2025-03-05 23:24:15 +0000
32d10036de

fix flaky test (#1322) Awni Hannun 2025-03-05 14:00:09 -0800
e150621095

Adding multiple optimizers to mlx lm (#1315) Gökdeniz Gülmez 2025-03-05 22:54:54 +0100
4d77043886 fix flaky test Awni Hannun 2025-03-05 13:53:35 -0800
56d2db23e1

adding OLMoE architecture (#1321) Gökdeniz Gülmez 2025-03-05 22:46:06 +0100
e7267d30f8

Distributed support cifar (#1301) Angelos Katharopoulos 2025-03-05 13:33:15 -0800
499a9f0758

Merge branch 'ml-explore:main' into adding-support-for-OLMoE Gökdeniz Gülmez 2025-03-05 18:38:43 +0100
cae3705109 udpate Goekdeniz-Guelmez 2025-03-05 15:32:58 +0100
f13a0d04ca seperate functions Goekdeniz-Guelmez 2025-03-05 15:28:12 +0100
d723ddfeda updates Goekdeniz-Guelmez 2025-03-05 14:49:56 +0100
9a36452519 updates Goekdeniz-Guelmez 2025-03-05 14:42:34 +0100
326935be49 updates Goekdeniz-Guelmez 2025-03-05 14:40:23 +0100
2d2f39f96e updates Goekdeniz-Guelmez 2025-03-05 14:25:55 +0100
1f89453295 eos token return fix Goekdeniz-Guelmez 2025-03-05 14:00:51 +0100
2bde97fe13 minor speed improvement Goekdeniz-Guelmez 2025-03-05 13:55:24 +0100
3dfb21267b updates Goekdeniz-Guelmez 2025-03-05 12:59:41 +0100
0df9491ff0 using default arguments Goekdeniz-Guelmez 2025-03-05 09:47:40 +0100
5b091daeec removing muon Goekdeniz-Guelmez 2025-03-05 09:41:47 +0100
64ed426518 Changed the switch to set opt_class Goekdeniz-Guelmez 2025-03-05 09:40:36 +0100
a1ff1bf72a formated Goekdeniz-Guelmez 2025-03-05 09:30:09 +0100
e4c56625f0 a little faster and adding norm_topk_prob Goekdeniz-Guelmez 2025-03-05 00:16:20 +0100
4ca2cd5759 clean up Goekdeniz-Guelmez 2025-03-05 00:12:29 +0100
140285080d adding SwitchGLU Goekdeniz-Guelmez 2025-03-05 00:09:17 +0100
f621218ff5

Tool use example (#1316) Awni Hannun 2025-03-04 13:53:20 -0800
230abad426 more clean ups Goekdeniz-Guelmez 2025-03-04 22:44:24 +0100
d828bc0c2d remove sanitize method Goekdeniz-Guelmez 2025-03-04 22:42:49 +0100
86c665f7b4 nits Awni Hannun 2025-03-04 13:38:48 -0800
65aa2ec849

use a bool mask for attention (#1319) Awni Hannun 2025-03-04 12:47:32 -0800
8b6beea3be faster generation Goekdeniz-Guelmez 2025-03-04 21:26:21 +0100
fd63c68280 clean up Goekdeniz-Guelmez 2025-03-04 21:24:13 +0100
bbde6ea4bc adding olmoe to training Goekdeniz-Guelmez 2025-03-04 21:08:55 +0100
ef8ec7a27a udpate ACKNOWLEDGMENTS.md Goekdeniz-Guelmez 2025-03-04 20:59:40 +0100
10ee8fd718 initial commit Goekdeniz-Guelmez 2025-03-04 20:56:42 +0100
a67213a01c use a bool mask for attention Awni Hannun 2025-03-04 08:14:29 -0800
c817743333

Merge branch 'ml-explore:main' into adding-GRPO-training Gökdeniz Gülmez 2025-03-03 22:13:42 +0100
2954398002

Merge branch 'ml-explore:main' into adding-dpo-training Gökdeniz Gülmez 2025-03-03 22:13:31 +0100
3023ae0cd3

Merge branch 'ml-explore:main' into adding-orpo-training Gökdeniz Gülmez 2025-03-03 22:13:14 +0100
1bc3476a46

chore(lora): Add real-time log buffering fix for nohup execution (#1311) Pierre-Louis 2025-03-03 09:12:33 -0500
269faa5fa4

Fix plamo2 model to use rms_norm (#1308) Shunta Saito 2025-03-03 23:12:02 +0900
925f5621b0 tool use example Awni Hannun 2025-03-01 11:33:49 -0800
132225a018 updates Goekdeniz-Guelmez 2025-03-01 22:23:33 +0100
60df71bcbc update YAML example file Goekdeniz-Guelmez 2025-03-01 15:01:52 +0100
eed093b0ec adding more customized YAML configuartion Goekdeniz-Guelmez 2025-03-01 15:00:29 +0100
b0a2edbcf3 initial commmit Goekdeniz-Guelmez 2025-03-01 14:56:06 +0100
c119a7a4a5 updates Goekdeniz-Guelmez 2025-03-01 12:47:13 +0100
bb261aadcb updates Goekdeniz-Guelmez 2025-03-01 12:42:39 +0100
c03dc8df1f

run pre-commit hooks chaihahaha 2025-03-01 09:54:08 +0800
0af315c8ea

format code chaihahaha 2025-03-01 09:50:40 +0800
66b630b4f6 Fix average_stats Angelos Katharopoulos 2025-02-28 16:00:06 -0800
8aeea10901

Merge branch 'main' into adding-dpo-training Gökdeniz Gülmez 2025-02-28 22:10:56 +0100
6a3912be7f

Merge branch 'main' into adding-orpo-training Gökdeniz Gülmez 2025-02-28 22:10:21 +0100
925e11439b updates Goekdeniz-Guelmez 2025-02-28 22:07:19 +0100
80e10a59d7

Merge branch 'main' into adding-GRPO-training Gökdeniz Gülmez 2025-02-28 21:16:02 +0100
845cd8c01e

support kimi + more options in chat mode (#1312) Awni Hannun 2025-02-28 11:33:18 -0800
b2108a0de6

Allow mask prompt in config (#1314) Awni Hannun 2025-02-28 11:33:04 -0800
f96a25c7d8

chore(lora): running pre-commit hook Pierre-Louis Létoquart 2025-02-28 14:12:21 -0500
c1aca340b2 support kimi + more options in chat mode Awni Hannun 2025-02-28 07:54:00 -0800
a42122d85d Allow mask prompt in config Awni Hannun 2025-02-28 09:33:48 -0800
3ddd41e288

chore(lora): remove python 3.7+ check Pierre-Louis 2025-02-28 11:26:54 -0500
ae0a39d1b4

chore(lora): Add real-time log buffering fix for nohup execution Pierre-Louis 2025-02-28 10:54:16 -0500
15d53279ae batching fix Goekdeniz-Guelmez 2025-02-28 16:02:40 +0100
313d4a2ac9 summarize segsum Goekdeniz-Guelmez 2025-02-28 15:04:03 +0100
a04eb02257

Merge branch 'ml-explore:main' into adding-GRPO-training Gökdeniz Gülmez 2025-02-28 11:18:32 +0100
71d7e99199 Remove unused imports Shunta Saito 2025-02-28 04:05:27 +0900
8924bdc546 Remove sliding window attention impl. cause it should be done by using RotatingKVCache Shunta Saito 2025-02-28 03:55:52 +0900
ab960f80dd Fix missing variable Shunta Saito 2025-02-28 01:31:15 +0900
08a8dd2507 Fix plamo2 model to use rms_norm and enable sliding window attention Shunta Saito 2025-02-28 01:17:35 +0900
eb73549631

Generate: Support Prefill Response (#1299) madroid 2025-02-27 23:44:00 +0800
109eb4e942 nits Awni Hannun 2025-02-27 07:39:15 -0800
f27ed26b32

Merge branch 'ml-explore:main' into adding-GRPO-training Gökdeniz Gülmez 2025-02-27 11:23:20 +0100
9f9da6af23 Generate: rename prefill-prompt to prefill-response madroid 2025-02-27 12:27:08 +0800
00a7379070

Fixes for phi4 mini (#1305) Awni Hannun 2025-02-26 16:21:54 -0800
92daef882b Fixes for phi4 mini Awni Hannun 2025-02-26 16:11:47 -0800
0f240a4c7e

Use max tokens from options in mlx_lm evaluate (#1302) Awni Hannun 2025-02-26 15:46:16 -0800
56e60ad5a6

fix manage for new transformers (#1304) Awni Hannun 2025-02-26 15:44:57 -0800
953c8bf369 fix manage for new transformers Awni Hannun 2025-02-26 15:41:31 -0800
87036dcfc4 Use max tokens from options in mlx_lm evaluate Awni Hannun 2025-02-26 12:34:36 -0800
b7f742ef56

Mixed quant recipes (#1300) Pedro Cuenca 2025-02-26 20:32:36 +0100
3862581d57 format / nits Awni Hannun 2025-02-26 11:22:58 -0800
932b196b48 updates Goekdeniz-Guelmez 2025-02-26 16:51:18 +0100
fab2dc2688 smoll fix Goekdeniz-Guelmez 2025-02-26 15:21:57 +0100
61fad00892 updates Goekdeniz-Guelmez 2025-02-26 15:16:45 +0100
a683344450 correct segsum function Goekdeniz-Guelmez 2025-02-26 14:46:46 +0100
d20413a54d Add it to the readme and fix the rank printing in main Angelos Katharopoulos 2025-02-25 17:40:24 -0800
14faec4ca2 Fix the throughput calculation Angelos Katharopoulos 2025-02-25 17:20:15 -0800
8a76b421a0 Add distributed support in the CIFAR example Angelos Katharopoulos 2025-02-25 17:07:30 -0800
216265bbb5 Mixed 3/6 and 2/6 recipes based on Alex Barron's Pedro Cuenca 2025-02-25 21:25:50 +0100
b7c0bdfd49 adding pytorch implementation Goekdeniz-Guelmez 2025-02-25 16:31:19 +0100
42c3cd2084

Merge branch 'ml-explore:main' into adding-support-for-mamba2 Gökdeniz Gülmez 2025-02-25 13:27:45 +0100
a1c2ac2903

Merge branch 'ml-explore:main' into adding-orpo-training Gökdeniz Gülmez 2025-02-25 13:27:20 +0100
3387e06ccd

Merge branch 'ml-explore:main' into adding-dpo-training Gökdeniz Gülmez 2025-02-25 13:27:08 +0100