mlx-examples

zhangyiss/mlx-examples

Fork 0

mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-08-31 11:54:37 +08:00

Commit Graph

Select branches

Hide Pull Requests

awq

awq-tq

dist-eval

distributed-layers

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

#1386

#1387

#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

5a8ba492e7 changing lora layers back to 16 Goekdeniz-Guelmez 2024-09-05 09:48:07 +0200
74f743bc23 fix Goekdeniz-Guelmez 2024-09-05 09:44:57 +0200
b184700912 removing the unnesesairy files Goekdeniz-Guelmez 2024-09-05 09:36:43 +0200
f965aef271 clean up Goekdeniz-Guelmez 2024-09-05 09:36:14 +0200
e8f5a6b213 quick clean up Goekdeniz-Guelmez 2024-09-05 09:17:10 +0200
9d14ea57e3 removing the model_type if stuff in the _step loop in generate_step and adding MambaCache in base.py for training easier generations and removing mamba in tuner/utils. Goekdeniz-Guelmez 2024-09-04 23:23:59 +0200
290c1a4dda update ACKNOWLEDGEMENTS Goekdeniz-Guelmez 2024-09-04 23:03:19 +0200
fd3bd6d9aa Fixing the cache handling, generating works now trying training Goekdeniz-Guelmez 2024-09-04 23:00:25 +0200
107575133e Done! Goekdeniz-Guelmez 2024-09-04 22:58:55 +0200
de1fdc7fdf fixing generate and logits outputs Goekdeniz-Guelmez 2024-09-04 22:46:45 +0200
236acb16a8 Fixing the Batching Depfwise Comnvolution and multi token input Goekdeniz-Guelmez 2024-09-04 22:08:32 +0200
e6c96f2b7a update Goekdeniz-Guelmez 2024-09-04 20:43:55 +0200
95e1690fc3

Merge branch 'ml-explore:main' into adding-support-for-mamba Gökdeniz Gülmez 2024-09-04 20:23:19 +0200
974cfe7ef8

Merge branch 'ml-explore:main' into adding-full-finetuning Gökdeniz Gülmez 2024-09-04 20:23:08 +0200
bd29aec299

Support HuggingFace model tree (#957) madroid 2024-09-04 21:19:32 +0800
282304a87d fix mapping for sdxl turbo Pranav Veldurthi 2024-09-04 09:09:52 -0400
83a209e200

Add prompt piping (#962) Chime Ogbuji 2024-09-03 16:29:10 -0400
bf921afcbe

Make sure to import the correct "version" module when installing mlx_whisper and mlx_lm from local source code. (#969) James Zhao 2024-09-03 23:16:21 +0300
5be8b96014 fix Awni Hannun 2024-09-03 13:08:22 -0700
a57b470829 Update exception text Chime Ogbuji 2024-09-03 15:40:29 -0400
aa14faf22b Fix reference to changed option name Chime Ogbuji 2024-09-03 15:18:13 -0400
62655dfa2f Merge remote-tracking branch 'origin/generation_pipes' into generation_pipes Chime Ogbuji 2024-09-03 13:14:35 -0400
16d51590a3 Fix capitalization typo Chime Ogbuji 2024-09-03 13:14:29 -0400
f1dbe6424d Make sure to import the correct "version" module when installing the mlx_lm package from local source code zhaoyafei 2024-08-30 23:46:51 +0300
1fbc9361e4 Fix attention layers map for SD-2-1-Base Pranav Veldurthi 2024-09-01 14:34:35 -0400
f3733cf5f8 update Goekdeniz-Guelmez 2024-09-01 13:39:03 +0200
c9dc00b1a6 Merge branch 'adding-support-for-mamba' of https://github.com/Goekdeniz-Guelmez/mlx-examples into adding-support-for-mamba Goekdeniz-Guelmez 2024-09-01 13:38:33 +0200
d1a0ca0c30

Merge branch 'ml-explore:main' into adding-support-for-mamba Gökdeniz Gülmez 2024-08-31 12:09:02 +0200
9a5dc3716e

Merge branch 'ml-explore:main' into adding-full-finetuning Gökdeniz Gülmez 2024-08-31 12:08:48 +0200
4eaa36e994 Make sure to import the correct "version" module when installing the mlx_whisper package from local source code. zhaoyafei 2024-08-30 23:42:47 +0300
9b05bc2795

Merge branch 'ml-explore:main' into generation_pipes Chime Ogbuji 2024-08-30 13:08:10 -0400
12603bb792 Switch to using --verbose instead of --prompt-only Chime Ogbuji 2024-08-30 13:07:55 -0400
3c6e8b11af

fix (#965) Awni Hannun 2024-08-30 05:56:27 -0700
9284682a1f fix Awni Hannun 2024-08-29 21:16:40 -0700
fc93c55723

feat(mlx_lm): Nemotron (#949) L 2024-08-29 21:08:57 -0700
8ba0a606cb nits Awni Hannun 2024-08-29 20:13:06 -0700
fac1f8b444 Hub: remove config print madroid 2024-08-30 09:53:07 +0800
d94187eb34 Hub: update quantization_config value madroid 2024-08-30 09:50:26 +0800
c14570a896 Hub: add quantization_config for model tree Quantized type madroid 2024-08-30 09:46:50 +0800
b1186e2a81

Docs on prompt scaling (#963) Awni Hannun 2024-08-29 15:05:17 -0700
b0ba935043

Merge branch 'ml-explore:main' into adding-support-for-mamba Gökdeniz Gülmez 2024-08-29 22:34:05 +0200
b30900f0ef

Merge branch 'ml-explore:main' into adding-full-finetuning Gökdeniz Gülmez 2024-08-29 22:33:36 +0200
d4b11f6d27 nits Awni Hannun 2024-08-29 13:06:32 -0700
8b7fcfbe9f remove unused var Awni Hannun 2024-08-29 12:55:34 -0700
afe143cd76 docs on prompt scaling Awni Hannun 2024-08-29 12:53:18 -0700
8dfc76be0f Initial commit of --prompt-only and prompt from STDIN feature Chime Ogbuji 2024-08-29 11:03:33 -0400
2caa8329c0

feat: show batch generation progress L Lllvvuu 2024-08-23 16:27:50 +0900
280b3784d4

feat: support batch input in generate() L Lllvvuu 2024-08-21 00:46:19 +0800
1003a8b2dd

Add the ability to load the KV cache from a file (#956) Angelos Katharopoulos 2024-08-28 22:11:45 -0700
7f8c961287

Fix setattr for the TokenizerWrapper (#961) Angelos Katharopoulos 2024-08-28 14:47:33 -0700
cbb4b78b03 Add metadata to the kv cache Angelos Katharopoulos 2024-08-28 14:24:37 -0700
45db052856 Fix setattr for the TokenizerWrapper Angelos Katharopoulos 2024-08-28 13:42:29 -0700
213a950e6e

feat(clip): add linear probe evaluation script Saurav Maheshkar 2024-08-28 20:54:38 +0100
7d0e1cc4e0

feat: basic speculative decoding support in mlx_lm.generate / mlx_lm.server L Lllvvuu 2024-08-26 01:36:10 -0700
01c8cbf71b Hub: add base_model metadata madroid 2024-08-27 15:04:55 +0800
8cdc91a92e Hub: Update quantization configuration fields madroid 2024-08-27 15:04:19 +0800
920efec17e Load kv cache from a file Angelos Katharopoulos 2024-08-23 18:33:26 -0700
6cf995cd32

Merge branch 'ml-explore:main' into adding-full-finetuning Gökdeniz Gülmez 2024-08-26 20:54:50 +0200
bf21789b17

chore: update black pre-commit hooks to latest versions (#955) Nripesh Niketan 2024-08-26 20:24:23 +0530
64a6b0383a

Merge branch 'main' into black-25.8 Nripesh Niketan 2024-08-26 20:07:23 +0530
0c34402c22 chore: update black pre-commit hooks to latest versions Nripesh Niketan 2024-08-26 20:06:33 +0530
b5e18ef1e3

Add Phi-3.5-MoE (#946) Prince Canuma 2024-08-24 15:52:33 +0200
0e7f44a875 nits Awni Hannun 2024-08-24 06:45:20 -0700
d76417197f fix SuScaled args Prince Canuma 2024-08-24 09:13:03 +0200
300fbc1c52

Merge branch 'ml-explore:main' into pc/phimoe Prince Canuma 2024-08-24 09:04:34 +0200
e3df32430e add switch_mlp Prince Canuma 2024-08-24 08:48:10 +0200
0b20d08d1b add phimoe to tunner Prince Canuma 2024-08-24 08:47:11 +0200
6731254e76

Use fast rope (#945) Awni Hannun 2024-08-23 13:18:51 -0700
5105b31cf7

feat: show batch generation progress L Lllvvuu 2024-08-23 16:27:50 +0900
9aabf08b23 hard code freqs Awni Hannun 2024-08-22 16:48:46 -0700
d87293428b

Merge branch 'ml-explore:main' into adding-support-for-mamba Gökdeniz Gülmez 2024-08-22 21:37:47 +0200
327eb0d257

Merge branch 'ml-explore:main' into adding-full-finetuning Gökdeniz Gülmez 2024-08-22 21:37:36 +0200
58591a1b41

fine tune deepseek (#932) Awni Hannun 2024-08-22 10:41:21 -0700
01e1f3c9e4

fixup! feat: Nemotron L Lllvvuu 2024-08-23 00:21:23 +0900
0eaec79dfb

Merge branch 'main' into adding-full-finetuning Gökdeniz Gülmez 2024-08-21 22:00:30 +0200
9c86658aff

feat: Nemotron L Lllvvuu 2024-08-21 09:25:30 +0800
ef92993abb

feat: support batch input in generate() L Lllvvuu 2024-08-21 00:46:19 +0800
0a52a9d55a fix Awni Hannun 2024-08-20 17:24:05 -0700
6b1d27a39f add phimoe Prince Canuma 2024-08-20 23:47:13 +0200
15975697d2 nit Awni Hannun 2024-08-20 06:33:53 -0700
b35b086278 only one of base or freqs Awni Hannun 2024-08-19 17:32:03 -0700
3f8c1aca20 fix deepseek v2 Awni Hannun 2024-08-19 16:09:17 -0700
a3431ccc25 fix su Awni Hannun 2024-08-19 16:02:25 -0700
fdc1c707c3 requires unreleased mlx Awni Hannun 2024-08-19 14:17:36 -0700
3822d6bfc3 use fast rope for llama3.1 Awni Hannun 2024-08-19 14:15:39 -0700
8b5c9ce6d2 fix llama Awni Hannun 2024-08-19 14:13:18 -0700
9ac9fa6798 use fast rope Awni Hannun 2024-08-19 14:11:17 -0700
6c79ceb452

Merge branch 'ml-explore:main' into adding-support-for-mamba Gökdeniz Gülmez 2024-08-19 17:59:40 +0200
c02d462a94 update Goekdeniz-Guelmez 2024-08-19 17:59:25 +0200
0164d2058b

feat: DeepSeek MoE v1 (#942) L 2024-08-17 23:18:09 +0900
6e1dc51e9a nits Awni Hannun 2024-08-17 07:17:53 -0700
102a0bb7ac nits Awni Hannun 2024-08-17 06:56:24 -0700
7bb77fd5bd nits Awni Hannun 2024-08-17 06:55:30 -0700
8af5fc0315 Merge branch 'adding-support-for-mamba' of https://github.com/Goekdeniz-Guelmez/mlx-examples into adding-support-for-mamba Goekdeniz-Guelmez 2024-08-17 14:33:31 +0200
3d3dfa39f1 utils.py logits = logits[:, -1, :] TypeError: tuple indices must be integers or slices, not tuple Goekdeniz-Guelmez 2024-08-17 14:32:19 +0200
ea6b9467e0

feat: deepseek v1 L Lllvvuu 2024-08-17 01:38:19 +0900
7be292c0c9

Handle longer prompt/generation (#931) Awni Hannun 2024-08-16 15:28:39 -0700
67c8f802fc

Merge branch 'ml-explore:main' into adding-support-for-mamba Gökdeniz Gülmez 2024-08-16 23:02:36 +0200
d42893eebc

Merge branch 'ml-explore:main' into adding-full-finetuning Gökdeniz Gülmez 2024-08-16 23:02:26 +0200
df04e0c03b update version Awni Hannun 2024-08-16 13:52:26 -0700