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

2384a5696a up. Vaibhav Srivastav 2024-01-08 13:25:24 +0530
9affcbdeb8 Add HF Hub upload option. Vaibhav Srivastav 2024-01-08 13:19:09 +0530
ddf3f09f6e refactor: make the phi2 example can be directly load the model from hf without convert needed anchen 2024-01-07 22:03:30 -0800
0f6ef682fd Update README.md (#248) Nino Risteski 2024-01-08 05:13:58 +0100
9742ad0f51

Update README.md (#248) Nino Risteski 2024-01-08 05:13:58 +0100
0644926afb quantize linear (#250) Awni Hannun 2024-01-07 18:48:59 -0800
485fb9ac0f

quantize linear (#250) Awni Hannun 2024-01-07 18:48:59 -0800
649add3451

Merge branch 'ml-explore:main' into main Chime Ogbuji 2024-01-07 17:06:42 -0500
bde70c9e49 Update README.md (#251) Ikko Eltociear Ashimine 2024-01-08 04:35:39 +0900
737b4c81a3

Update README.md (#251) Ikko Eltociear Ashimine 2024-01-08 04:35:39 +0900
774449a128

Update README.md Ikko Eltociear Ashimine 2024-01-08 04:34:52 +0900
94d7bd2ac3 quantize linear Awni Hannun 2024-01-07 11:31:12 -0800
052d9c3bd8

Update README.md Nino Risteski 2024-01-07 20:08:56 +0100
3d0152f4f6 [Whisper] Add word timestamps and confidence scores (#201) bofeng huang 2024-01-07 19:01:29 +0100
bf9926489e

[Whisper] Add word timestamps and confidence scores (#201) bofeng huang 2024-01-07 19:01:29 +0100
d7f5bd4751 nit Awni Hannun 2024-01-07 10:00:50 -0800
05f4c3e5b0 format + readme Awni Hannun 2024-01-07 09:57:20 -0800
a90c60ab8d Fix typo in lora convert.py (#245) mc0ps 2024-01-07 06:30:30 -0500
25ebd36112

Fix typo in lora convert.py (#245) mc0ps 2024-01-07 06:30:30 -0500
1a0514c6c6 added --color argument Leon Ericsson 2024-01-07 12:02:00 +0100
692dd6c27c draft token coloring Leon Ericsson 2024-01-07 11:58:37 +0100
c8c2be0a77 fix typo in args.torch_path mc0ps 2024-01-07 02:56:48 -0500
2bb89da7b7

Merge branch 'ml-explore:main' into main Chime Ogbuji 2024-01-06 17:21:40 -0500
37c5555616 nits Leon Ericsson 2024-01-06 23:16:17 +0100
59d8feb424 Update README.md (#243) Nino Risteski 2024-01-06 20:44:49 +0100
b152d12d7b

Update README.md (#243) Nino Risteski 2024-01-06 20:44:49 +0100
5a458f0c85

Update README.md Nino Risteski 2024-01-06 20:30:12 +0100
32a7449c36

Update CODE_OF_CONDUCT.md Nino Risteski 2024-01-06 20:27:56 +0100
bfbcb5d55b Add test for word-level timestamps and confidence scores bofenghuang 2024-01-06 18:59:53 +0100
9cdf6388c7 Cast qk to fp32 bofenghuang 2024-01-06 18:59:10 +0100
e0a81d9283

Merge branch 'main' into main Chime Ogbuji 2024-01-06 12:52:00 -0500
57111100a2 Save alignment_heads bofenghuang 2024-01-06 17:47:46 +0100
441494b11a Move multiple ops from np to mlx, clean comments bofenghuang 2024-01-06 17:27:06 +0100
5512f8e6f0 Create a separate forward_with_cross_qk function bofenghuang 2024-01-06 17:25:41 +0100
a9641628de Add word timestamps and confidence scores bofenghuang 2023-12-28 20:01:10 +0100
396cf5654a refactor: merge deepseek coder example into hf_llm example (#234) Anchen 2024-01-06 07:53:46 -0800
758f05c09a

refactor: merge deepseek coder example into hf_llm example (#234) Anchen 2024-01-06 07:53:46 -0800
7baf6618b5 Rename requirements.txt for windows file name support Jonas Örnfelt 2024-01-06 16:38:21 +0100
947e6c2281 chore: fix lint anchen 2024-01-06 07:27:43 -0800
a30273f606

Update llms/hf_llm/models.py Anchen 2024-01-07 02:24:54 +1100
568c9739a7 update README Leon Ericsson 2024-01-06 14:20:15 +0100
79dfdd6c31 fix to generate_draft, --color removed for now Leon Ericsson 2024-01-06 14:07:24 +0100
35dcab90ef Merge branch 'chore/deepseek' of github.com:mzbac/mlx-examples into chore/deepseek anchen 2024-01-05 23:41:45 -0800
fa6ff4e517 chore: remove default rope_scaling dict and use get to access type and factor to avoid key error anchen 2024-01-05 23:39:49 -0800
a95e8f1587 force fp16 for quantized models (#240) Awni Hannun 2024-01-05 21:29:15 -0800
cf0ad26a89

force fp16 for quantized models (#240) Awni Hannun 2024-01-05 21:29:15 -0800
4f2483edc7 force fp16 for quantized models Awni Hannun 2024-01-05 21:21:09 -0800
91017ac223 add numpy as a requirement to run lora.py (#238) Lawrence Wu 2024-01-05 16:16:28 -0800
37856f70a8

add numpy as a requirement to run lora.py (#238) Lawrence Wu 2024-01-05 16:16:28 -0800
aa79e8ec3c removed unused imports Lawrence Wu 2024-01-05 15:59:33 -0800
521ff0ba4b add numpy as a requirement to run lora.py Lawrence Wu 2024-01-05 15:53:42 -0800
fbf3956cdc merge lookup_decoding under speculative example Leon Ericsson 2024-01-05 22:46:03 +0100
d67aa16661 Updates from pre-commit run --all-files Chime Ogbuji 2024-01-05 15:13:34 -0500
119cadbd09 Minor fixes Fixed import path, iteration calculation, and creation of configuration namespace from YAML. Chime Ogbuji 2024-01-05 12:22:00 -0500
0dbc78ca65 Additional comment about YAML file format Chime Ogbuji 2024-01-05 11:59:37 -0500
4f7023ce19 Initial commit of configurable supervized lora training framework. Will need to sync with #213 when merged into main Chime Ogbuji 2024-01-05 11:55:14 -0500
cab36602e9

chore: fix format in readme Anchen 2024-01-05 23:59:45 +1100
c270881a85 remove deepseek example anchen 2024-01-05 03:18:42 -0800
632391284d refactor: merge deepseek coder example into hf_llm example anchen 2024-01-05 02:12:14 -0800
6b71e18a0a Qlora (#219) Awni Hannun 2024-01-04 21:05:59 -0800
37b41cec60

Qlora (#219) Awni Hannun 2024-01-04 21:05:59 -0800
f4ccff9a89 Handle receiving 0 tokens gracefully (#231) Christian Bieniak 2024-01-05 14:14:13 +1100
4fa659acbd

Handle receiving 0 tokens gracefully (#231) Christian Bieniak 2024-01-05 14:14:13 +1100
53ee382cf8 Move no token check to statistics section Christian Bieniak 2024-01-05 14:01:18 +1100
192782b27c Formatting Christian Bieniak 2024-01-05 13:23:26 +1100
a1a873109a handle 0 tokens gracefully Christian Bieniak 2024-01-05 13:20:42 +1100
972c83a49d one more fix Awni Hannun 2024-01-04 16:34:50 -0800
8b960fc3e6 fix loading adapters Awni Hannun 2024-01-04 11:54:49 -0800
0c140c9019 comments Awni Hannun 2024-01-03 16:37:10 -0800
7102738f46 include hf in readme Awni Hannun 2024-01-03 14:30:36 -0800
d8c711cfdd more helpful error message Awni Hannun 2024-01-03 14:27:26 -0800
b693e1b18d typo Awni Hannun 2024-01-03 13:53:04 -0800
d58f68ab1b section on quantizing for memory reduction Awni Hannun 2024-01-03 13:50:42 -0800
139fbf39bc update main readme Awni Hannun 2024-01-03 13:45:46 -0800
e81cab43e4 updates on 0.0.7 Awni Hannun 2024-01-03 13:38:45 -0800
837fcc2097 start of qlora Awni Hannun 2023-12-22 13:52:09 -0800
497adf5aba Update README.md to fix --hf-model param call. (#229) Andy Peatling 2024-01-04 11:53:51 -0800
12c9bafbf5

Update README.md to fix --hf-model param call. (#229) Andy Peatling 2024-01-04 11:53:51 -0800
39feb176c8

Update README.md to fix --hf-model param call. Andy Peatling 2024-01-04 11:26:37 -0800
7e7b817ddf fix to use actual prompt (#227) Awni Hannun 2024-01-04 11:12:05 -0800
e14afb3e77

fix to use actual prompt (#227) Awni Hannun 2024-01-04 11:12:05 -0800
caf314e703 fix to use actual prompt Awni Hannun 2024-01-04 11:07:36 -0800
a9ee883bf7 Fix upload to hub for HF LLMs conversion script. (#221) Vaibhav Srivastav 2024-01-04 19:36:05 +0530
f95cf30a31

Fix upload to hub for HF LLMs conversion script. (#221) Vaibhav Srivastav 2024-01-04 19:36:05 +0530
b2703f5406 reverting last commit. Vaibhav Srivastav 2024-01-04 15:55:48 +0530
24d74842a6 Weights -> model. Vaibhav Srivastav 2024-01-04 15:08:24 +0530
af957bff3f Fix upload to hub snippet. Vaibhav Srivastav 2024-01-04 13:34:56 +0530
fc9dde34c9 Support Hugging Face models (#215) Awni Hannun 2024-01-03 15:13:26 -0800
a5d6d0436c

Support Hugging Face models (#215) Awni Hannun 2024-01-03 15:13:26 -0800
f0aaab7d91 comment Awni Hannun 2024-01-03 15:01:02 -0800
99581115a0 format with later version of black Awni Hannun 2024-01-03 14:59:45 -0800
d097652adc model card Awni Hannun 2024-01-03 13:59:28 -0800
918973decf nit Awni Hannun 2024-01-03 12:13:20 -0800
76c8bdbb2a readme nits Awni Hannun 2024-01-03 11:58:27 -0800
7b3573113c nits Awni Hannun 2024-01-03 11:54:02 -0800
f124d627f4 hugs Awni Hannun 2024-01-03 11:52:15 -0800
2995a67486 comments + readme updates Awni Hannun 2024-01-03 11:50:34 -0800
384ad5792e address comments Awni Hannun 2024-01-03 11:33:41 -0800
9bb3b4bd77 upload to hub Awni Hannun 2024-01-03 09:42:43 -0800
1d80a686f8 work with hf repos Awni Hannun 2024-01-03 09:35:31 -0800