mlx-examples

zhangyiss/mlx-examples

Fork 0

mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-08-30 19:06:37 +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

f08a00716e use the same model structure and module names as HF Awni Hannun 2024-01-03 09:13:42 -0800
2e2acc4349 use the same model structure and module names as HF Awni Hannun 2024-01-03 08:26:46 -0800
3fefd2e8eb support hf direct models Awni Hannun 2024-01-02 13:41:23 -0800
b874f866d7 keep dtype on model conversion (#186) Daniel Strobusch 2024-01-02 20:20:29 +0100
1d09c4fecd

keep dtype on model conversion (#186) Daniel Strobusch 2024-01-02 20:20:29 +0100
b939c8b9a2

keep dtype on model conversion Daniel Strobusch 2023-12-24 10:05:03 +0100
32e88bc3c5 make parameter naming consistent with other examples. (#214) Daniel Strobusch 2024-01-02 17:18:12 +0100
85258b2be7

make parameter naming consistent with other examples. (#214) Daniel Strobusch 2024-01-02 17:18:12 +0100
507c161983

make parameter naming consistent with other examples. Daniel Strobusch 2024-01-02 17:14:26 +0100
ed7a80c14d added acknowledgements Leon Ericsson 2024-01-02 11:15:17 +0100
844b5e6664 removed erroneous lora_module.py file in root directory Mark Moussa 2024-01-01 22:14:24 -0500
a13772c524 added lora_module python file, so that lora process can be used for downstream processes, rather than just as a file on its own Mark Moussa 2024-01-01 22:11:48 -0500
52231dcc7c adding lora_module.py in order to have the lora process as a module. this way, it can be used in a downstream pipeline instead of strictly run on its own Mark Moussa 2024-01-01 22:06:38 -0500
7eb9762547 fix: deepseek coder tokenizer error (#211) Anchen 2024-01-02 01:10:37 +1100
e632d7aaaa

fix: deepseek coder tokenizer error (#211) Anchen 2024-01-02 01:10:37 +1100
7da89adef8 nist Leon Ericsson 2024-01-01 12:53:11 +0100
6f6c5842f5

fix: deepseek coder tokenizer error Anchen 2024-01-01 20:13:13 +1100
d81dcad68f chore: add workaround for quant Anchen 2024-01-01 14:56:21 +1100
b763ad3829 remove unused num_key_value_heads Anchen 2024-01-01 02:17:36 +1100
f4e38db123 feat: add yayi2-30b example Anchen 2024-01-01 01:49:12 +1100
b505fb788a chore: make the Deepseek example compatible with Yi models. (#205) Anchen 2023-12-31 01:11:33 +1100
ee3c44d231

chore: make the Deepseek example compatible with Yi models. (#205) Anchen 2023-12-31 01:11:33 +1100
925c0d9266

Update deepseek_coder.py Anchen 2023-12-30 19:37:01 +1100
cbf5237086

Update convert.py Anchen 2023-12-30 19:36:18 +1100
c687a4e02e

Update convert.py Anchen 2023-12-30 19:35:25 +1100
967cf23a87 [Whisper] Load customized MLX model & Quantization (#191) bofeng huang 2023-12-29 19:22:15 +0100
581a5733a1

[Whisper] Load customized MLX model & Quantization (#191) bofeng huang 2023-12-29 19:22:15 +0100
95c8459595 Improve doc bofenghuang 2023-12-29 19:09:54 +0100
fcacc57950 Add notes about conversion bofenghuang 2023-12-29 17:20:41 +0100
27e9c3de06 Fix benchmark bofenghuang 2023-12-29 17:07:41 +0100
695805c361 Update test bofenghuang 2023-12-29 16:43:47 +0100
21f28ccd55 Separate model conversion and loading bofenghuang 2023-12-29 16:36:51 +0100
81183c3091 Apply reviews bofenghuang 2023-12-29 11:19:05 +0100
39600eb383 Add quantization bofenghuang 2023-12-26 19:57:16 +0100
43a68ee5e3 Add option to load customized mlx model bofenghuang 2023-12-26 19:05:49 +0100
9aeadd40dc chore: fix the load quantization model for deepseek coder (#203) Anchen 2023-12-30 00:25:38 +1100
1cdbf9e886

chore: fix the load quantization model for deepseek coder (#203) Anchen 2023-12-30 00:25:38 +1100
3f750759d3 format Leon Ericsson 2023-12-29 13:19:28 +0100
b38ab8b911

change to explicitly check for quantization config Anchen 2023-12-29 23:12:06 +1100
a7da4ad7a3

chore: fix the load quantization model Anchen 2023-12-29 23:01:20 +1100
453ca97528 move code && small opt to find_draft Leon Ericsson 2023-12-29 12:18:09 +0100
d3ab663f4a add deepseek coder example (#172) Anchen 2023-12-29 16:42:22 +1100
31ddbd7806

add deepseek coder example (#172) Anchen 2023-12-29 16:42:22 +1100
2afa108567 one more typo Awni Hannun 2023-12-28 21:41:23 -0800
7d923b41f1 nits in README Awni Hannun 2023-12-28 21:40:18 -0800
9ff0a96ab0 style /consistency changes to ease future integration Awni Hannun 2023-12-28 21:31:29 -0800
a476d1909d feat: add repetition_penalty Anchen 2023-12-24 22:38:50 +1100
bd63a3e5ee chore: clean up the rope scalling factor param in create cos sin theta Anchen 2023-12-23 17:17:14 +1100
784149d699 chore: update readme Anchen 2023-12-22 21:51:32 +1100
195f0f0e4c feat: add quantization support Anchen 2023-12-22 21:43:10 +1100
6a62a8bca4 chore: remove hardcoded rope_scaling_factor Anchen 2023-12-22 18:03:20 +1100
e17e07002a feat: add example for deepseek coder Anchen 2023-12-22 17:51:06 +1100
1f1090023e Add an image2image example in the stable diffusion (#198) Angelos Katharopoulos 2023-12-28 18:31:45 -0800
37fd2464dc

Add an image2image example in the stable diffusion (#198) Angelos Katharopoulos 2023-12-28 18:31:45 -0800
1844163061 Typo fix Angelos Katharopoulos 2023-12-28 18:31:02 -0800
59e56296e9 Update the readme Angelos Katharopoulos 2023-12-28 18:29:17 -0800
381d3353e1 Fix multiple image generation and cli description Angelos Katharopoulos 2023-12-28 18:02:03 -0800
f18730dec1 add speculative decoding example for llama (#149) Benjamin Anderson 2023-12-28 17:20:43 -0600
09566c7257

add speculative decoding example for llama (#149) Benjamin Anderson 2023-12-28 17:20:43 -0600
e13a4e6333 nits Awni Hannun 2023-12-28 15:20:26 -0800
253cc31815 nits Awni Hannun 2023-12-28 15:18:40 -0800
ef773beab6 nits Awni Hannun 2023-12-28 15:10:51 -0800
f1cf9380a7 readme nit Awni Hannun 2023-12-28 15:04:02 -0800
a65d452ffd update readme Awni Hannun 2023-12-28 15:01:00 -0800
34a62ddc49 switch to t5 Awni Hannun 2023-12-28 14:55:25 -0800
ccd69f70ed [Whisper] Large-v3 requires 128 Mel frequency bins (#193) Dimo 2023-12-28 22:50:35 +0100
07c163d9d9

[Whisper] Large-v3 requires 128 Mel frequency bins (#193) Dimo 2023-12-28 22:50:35 +0100
0177419f41 format Awni Hannun 2023-12-28 13:50:17 -0800
d1ca6919af format Awni Hannun 2023-12-28 13:49:12 -0800
c73bec5598 pre_commit formatting Leon Ericsson 2023-12-28 22:23:29 +0100
cb4464bb7b

Merge branch 'ml-explore:main' into prompt_lookup LeonEricsson 2023-12-28 22:17:53 +0100
a04b0fb444 code clean and update readme Leon Ericsson 2023-12-28 22:14:57 +0100
3c7e28dd61 updated implementation to match #149 Leon Ericsson 2023-12-28 22:13:47 +0100
41ab0cd055 Fix benchmark (#200) bofeng huang 2023-12-28 20:29:39 +0100
e1e56a625b

Fix benchmark (#200) bofeng huang 2023-12-28 20:29:39 +0100
bc5034b889

Fix benchmark bofeng huang 2023-12-28 20:16:39 +0100
42378e5861 use accept reject criteria Awni Hannun 2023-12-28 09:14:39 -0800
df706b0814 rebase Awni Hannun 2023-12-28 09:04:07 -0800
19ecb00bce spec decode gives same results as regular decode Awni Hannun 2023-12-27 21:16:07 -0800
761e61480e add sample 0 Awni Hannun 2023-12-27 10:24:32 -0800
a436d198ec speculative decoding Benjamin Anderson 2023-12-20 00:25:49 -0600
d2d3b1fbf0 inital version Leon Ericsson 2023-12-28 15:56:10 +0100
ba01b969ce extract correct model dimensions and use argparse dimopep 2023-12-27 23:57:32 +0100
3da3af8b2d Add an image2image example in the stable diffusion Angelos Katharopoulos 2023-12-27 14:12:31 -0800
ab576be362 Fix generate example in README (#197) Sunbir Gill 2023-12-27 16:11:10 -0500
78d207fe27

Fix generate example in README (#197) Sunbir Gill 2023-12-27 16:11:10 -0500
7a64a28456

Fix generate example in README Sunbir Gill 2023-12-27 15:46:22 -0500
77ab988a72 fix load model in lora/lora.py pjh6818 2023-12-27 22:33:09 +0900
000b15d563 Large-v3 requires 128 Mel frequency bins dimopep 2023-12-27 02:37:16 +0100
de759fc6b1 fix: Add numpy to CIFAR's requirements.txt (#192) Jiří Moravčík 2023-12-27 00:18:59 +0100
50fceb1a28

fix: Add numpy to CIFAR's requirements.txt (#192) Jiří Moravčík 2023-12-27 00:18:59 +0100
413f8f82d2 fix: Add numpy to CIFAR's requirements.txt Jiří Moravčík 2023-12-26 22:15:35 +0100
89757a7f8a Fixed the return type for the __call__ method in Attention (#190) Sushant 2023-12-26 23:02:43 +0530
a516f4635d

Fixed the return type for the __call__ method in Attention (#190) Sushant 2023-12-26 23:02:43 +0530
0618a400a2

Fixed the return type for the __call__ method in Attention Sushant 2023-12-26 23:00:01 +0530
c63517bbb3 shard llama model after conversion and unshard on loading (#174) Daniel Strobusch 2023-12-25 20:19:43 +0100
2bd20ef0e0

shard llama model after conversion and unshard on loading (#174) Daniel Strobusch 2023-12-25 20:19:43 +0100
a11e3f89ae

shard llama model after conversion and unshard on loading Daniel Strobusch 2023-12-24 14:13:30 +0100
26aefc7489 Merge branch 'main' of https://github.com/madroidmaq/mlx-examples madroid 2023-12-26 01:15:09 +0800
fb87609252 Update lora readme.md, add stupid simple command example madroid 2023-12-26 01:11:46 +0800