mlx-examples

zhangyiss/mlx-examples

Fork 0

mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-08-29 13:36:07 +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

9318d99b9c Use config.json, add model_type Pedro Cuenca 2023-12-20 17:05:27 +0100
06b7c45c59 Add URLs to HF MLX-Community org. (#153) Vaibhav Srivastav 2023-12-20 20:27:13 +0530
4b7e11bd31

Add URLs to HF MLX-Community org. (#153) Vaibhav Srivastav 2023-12-20 20:27:13 +0530
040ef650d1 Standardise org name. Vaibhav Srivastav 2023-12-20 20:25:29 +0530
03720a270e Add --model_path to phi-2 example script (#152) Pedro Cuenca 2023-12-20 15:14:35 +0100
d8e14c858e

Add --model_path to phi-2 example script (#152) Pedro Cuenca 2023-12-20 15:14:35 +0100
bc3860b643 nit: language. Vaibhav Srivastav 2023-12-20 18:25:48 +0530
6de2db7bf4 Add ref to MLX org on the README. Vaibhav Srivastav 2023-12-20 18:21:39 +0530
ec15108bbe up Vaibhav Srivastav 2023-12-20 18:15:20 +0530
66d31c22c6 Add --model_path to phi-2 example script Pedro Cuenca 2023-12-20 13:22:00 +0100
0fb147650f Added Keyword Spotting Transformer + SpeechCommands example (#123) Sarthak Yadav 2023-12-19 23:17:48 +0100
b6e62caf2e

Added Keyword Spotting Transformer + SpeechCommands example (#123) Sarthak Yadav 2023-12-19 23:17:48 +0100
50d09620ae updated acknowledgements Sarthak Yadav 2023-12-19 23:09:22 +0100
a33c3095c4

Merge branch 'ml-explore:main' into main Sarthak Yadav 2023-12-19 23:05:20 +0100
f6835ebf4e readme + format Awni Hannun 2023-12-19 13:57:55 -0800
50a703eb3b T5: Change default dtype to bfloat16 (#147) Juarez Bochi 2023-12-19 16:44:36 -0500
ebbb7083cc

T5: Change default dtype to bfloat16 (#147) Juarez Bochi 2023-12-19 16:44:36 -0500
f59a36f94d fixed kwt skip connections Sarthak Yadav 2023-12-19 22:41:22 +0100
e39ad4cdf6

t5: Change convert.py default to float32 Juarez Bochi 2023-12-19 16:35:15 -0500
b439b96aa1 Add Qwen example (#134) Junyi Mei 2023-12-20 05:06:19 +0800
62b455f801

Add Qwen example (#134) Junyi Mei 2023-12-20 05:06:19 +0800
a54010c701 readme nit Awni Hannun 2023-12-19 13:03:25 -0800
0bf8de87a3 move to llm subdir Awni Hannun 2023-12-19 13:01:25 -0800
a476ed9f50 some updates / style consistency Awni Hannun 2023-12-19 12:58:59 -0800
3f91d8b9e8

Add myself to contributors Juarez Bochi 2023-12-19 14:54:25 -0500
6d5d8c6bca

T5: Change default to bfloat16 Juarez Bochi 2023-12-19 14:53:07 -0500
d4f7ecd851 nits Awni Hannun 2023-12-19 06:39:17 -0800
992f5cc0fa some updates / simplifications Awni Hannun 2023-12-18 21:54:19 -0800
b5ff25716f Add T5 and Flan-T5 example (#113) Juarez Bochi 2023-12-18 23:25:34 -0500
10a7b99e83

Add T5 and Flan-T5 example (#113) Juarez Bochi 2023-12-18 23:25:34 -0500
156cde3206 nit Awni Hannun 2023-12-18 20:23:09 -0800
c393149560 readme flan Awni Hannun 2023-12-18 20:18:42 -0800
6f4e33eff5

Update t5 docs on variant support Juarez Bochi 2023-12-18 22:59:36 -0500
930cd4d950

Adds support for flan-t5 Juarez Bochi 2023-12-18 18:05:40 -0500
9063f1a1e3 fix use for llama 2 from meta (#144) Awni Hannun 2023-12-18 19:33:17 -0800
1e7f4a5921

fix use for llama 2 from meta (#144) Awni Hannun 2023-12-18 19:33:17 -0800
4dfc8246d1 fix use for llama 2 from meta Awni Hannun 2023-12-18 19:10:05 -0800
688795c665 default to fp32 for now Awni Hannun 2023-12-18 17:15:49 -0800
05a8464d78 higher clipping, remove non-helpful casts Awni Hannun 2023-12-18 14:36:07 -0800
d2732a6478 clamp for low precision Awni Hannun 2023-12-18 14:25:58 -0800
60c3bd9bc7 Pass few shot file name to --few-shot arg(#141) Daniel Strobusch 2023-12-18 22:30:04 +0100
1d62b3ecc1

Pass few shot file name to --few-shot arg(#141) Daniel Strobusch 2023-12-18 22:30:04 +0100
fd351850e4 fp16, abstract tokenizer a bit, format Awni Hannun 2023-12-18 13:15:02 -0800
72581e5c1a

Fix attention for 3b model Juarez Bochi 2023-12-18 15:50:29 -0500
dbb4d6aea6

Fix example Juarez Bochi 2023-12-18 15:07:50 -0500
64e53e8415

Pass ln2 to cross attention Juarez Bochi 2023-12-18 15:05:05 -0500
e899271275 nits Awni Hannun 2023-12-18 11:01:16 -0800
29e642a482 readme updates Awni Hannun 2023-12-18 10:58:43 -0800
36fd88509e

Rescale output before projecting on vocab Juarez Bochi 2023-12-18 13:43:03 -0500
511f572b6c

Increase hf max_length Juarez Bochi 2023-12-18 13:35:44 -0500
01d1c4c384

pass few shot file name to --few-shot to avoid interpreting --prompt once a string and once as filename. Daniel Strobusch 2023-12-18 19:29:37 +0100
fd00c22224 Citation + contributor acknowledgments section (#136) Awni Hannun 2023-12-18 10:12:35 -0800
517f5808fc

Citation + contributor acknowledgments section (#136) Awni Hannun 2023-12-18 10:12:35 -0800
ca5a8ec273 fix renamed arg (#140) Daniel Strobusch 2023-12-18 19:11:51 +0100
f0e14b6341

fix renamed arg (#140) Daniel Strobusch 2023-12-18 19:11:51 +0100
ad91fd073a

fix renamed arg Daniel Strobusch 2023-12-18 19:09:07 +0100
5f1c3bf677 nits Awni Hannun 2023-12-18 10:08:11 -0800
66e1c0f050

Fix type for attention mask Juarez Bochi 2023-12-18 11:39:17 -0500
5ae339f6d2

Add hf generation for comparison Juarez Bochi 2023-12-18 11:35:16 -0500
305a52dde8

Run hf_t5 with any model Juarez Bochi 2023-12-18 11:25:14 -0500
0779417903

Fix --encode-only Juarez Bochi 2023-12-18 11:19:44 -0500
83b68a5bdb

Fix relative position scale Juarez Bochi 2023-12-18 11:13:44 -0500
109a017b6e citation + acks section Awni Hannun 2023-12-18 07:55:25 -0800
17d2efaebe support for tiny llama (#129) Awni Hannun 2023-12-18 07:47:55 -0800
44b546d446

support for tiny llama (#129) Awni Hannun 2023-12-18 07:47:55 -0800
5206c2740f Remove trailing commas in function arguments for unified formatting in flows example Siddharth Mishra-Sharma 2023-12-18 10:03:09 -0500
9d3ee016c9

Add readme.md for t5 Juarez Bochi 2023-12-18 08:50:36 -0500
4bc8f49043

Add gitignore Juarez Bochi 2023-12-18 08:42:45 -0500
54b82198d0

Uncomment bidirectional param Juarez Bochi 2023-12-18 08:42:27 -0500
55f204dd3a

Load config from HF to support any model Juarez Bochi 2023-12-18 08:42:06 -0500
b2a3782a96

Add argument to generate float16 npz Juarez Bochi 2023-12-18 08:21:20 -0500
09e851499a

Stream output Juarez Bochi 2023-12-18 08:09:56 -0500
689eda9937

Fix T5.__call__ Juarez Bochi 2023-12-18 08:00:01 -0500
2a9c5e8a8c Fix convert and tokenizer Juni May 2023-12-18 16:59:51 +0800
702ecbb671 Add model and tokenizer options Juni May 2023-12-18 15:30:36 +0800
a8ef549546 Add readme and requirements for qwen example Juni May 2023-12-18 15:29:06 +0800
ec94fcf430 Add qwen model draft Juni May 2023-12-18 15:04:21 +0800
18f9646d56 Minor changes to README in normalizing flow example Siddharth Mishra-Sharma 2023-12-18 01:57:53 -0500
e7879beb6e Add requirements and basic usage to normalizing flow example Siddharth Mishra-Sharma 2023-12-18 01:01:47 -0500
5370d70122 Implement normalizing flow Real NVP example Siddharth Mishra-Sharma 2023-12-18 00:48:25 -0500
34843ddeb2 format Awni Hannun 2023-12-17 21:30:28 -0800
c468edc4e3 bug fix with bidirectional only for encoder, add offset to position bias Awni Hannun 2023-12-17 21:22:00 -0800
688a6e1e78 with cache Awni Hannun 2023-12-17 17:35:53 -0800
a7e6590b91 support for tiny llama Awni Hannun 2023-12-17 15:42:35 -0800
29bfb93455

Measure tokens/s Juarez Bochi 2023-12-17 10:53:49 -0500
90d3a15ba2

Stop on eos Juarez Bochi 2023-12-17 08:58:09 -0500
61fda57eba

Remove prints Juarez Bochi 2023-12-17 08:52:54 -0500
152e85fade

Concatenate tokens Juarez Bochi 2023-12-17 08:51:16 -0500
daea1dcddf

Use position bias in decoder Juarez Bochi 2023-12-17 08:40:10 -0500
7dcf2b688d

Fix decoder mask Juarez Bochi 2023-12-17 08:34:21 -0500
f26e81ccc9

Fix layer norm Juarez Bochi 2023-12-17 07:47:52 -0500
4ec2b6eec3

Utils to compare encoder output Juarez Bochi 2023-12-17 07:20:24 -0500
7e42349f4c

Use position bias in all layers Juarez Bochi 2023-12-17 07:19:32 -0500
b4ac7cc1df minor fixes in README Sarthak Yadav 2023-12-16 23:42:21 +0100
3e24277ba3 Added Keyword Transformer + SpeechCommands Sarthak Yadav 2023-12-16 23:30:33 +0100
203f550ef9

Decode (broken after 1st token) Juarez Bochi 2023-12-16 14:53:50 -0500
31da1b0dab

LM head Juarez Bochi 2023-12-16 14:44:15 -0500
d12db65eeb

No scaling, no encoder mask Juarez Bochi 2023-12-16 14:24:13 -0500
64e7eaccb8

Fix relative_attention_max_distance config Juarez Bochi 2023-12-16 11:18:17 -0500
2a8ee32b02

Fix default prompt Juarez Bochi 2023-12-16 08:17:08 -0500