mlx-examples

zhangyiss/mlx-examples

Fork 0

mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-08-28 11:42:26 +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

d7d70487eb fix sliding window Prince Canuma 2024-12-14 17:06:57 +0100
0337646b4e add to tuner Prince Canuma 2024-12-14 16:39:55 +0100
2f443cc6d7 add tests Prince Canuma 2024-12-14 16:39:46 +0100
52595dafae fix tests and sliding window attention Prince Canuma 2024-12-14 16:39:22 +0100
5d8b36ce7c revert to act_fn to silu Prince Canuma 2024-12-14 16:22:00 +0100
d7c64c621a add support for cohere2 Prince Canuma 2024-12-14 16:15:24 +0100
e5ff577dab add support for cohere2 Prince Canuma 2024-12-14 16:03:45 +0100
dff4e52910 adding the modelnames in the LORA.md file and removing unused functions from mamba2.py Goekdeniz-Guelmez 2024-12-12 22:52:00 +0100
9f2ea5892e

Bpe stream without space (#1154) Awni Hannun 2024-12-12 13:13:50 -0800
88693bf162 version bump Awni Hannun 2024-12-12 12:33:56 -0800
e2ba4ceaab bpe streaming detokenization without space Awni Hannun 2024-12-12 12:33:36 -0800
a883e39f41 optimizing the code for faster inference but still generates giberish Goekdeniz-Guelmez 2024-12-12 21:08:33 +0100
2ba0e36683

[mlx-lm] Use top p in server (#1144) Awni Hannun 2024-12-12 11:12:21 -0800
19abf3dcaa

Replace unicode errors instead of raising exception (#1146) Angelos Katharopoulos 2024-12-12 11:10:41 -0800
62391bec30 Fix bug Angelos Katharopoulos 2024-12-12 11:08:23 -0800
2024181b7c couple other fixes Awni Hannun 2024-12-12 10:51:38 -0800
2277033a24 use top p in server Awni Hannun 2024-12-08 20:16:44 -0800
6ef5ca4ce5 Change the last_segment logic in tokenizer utils Angelos Katharopoulos 2024-12-12 10:37:29 -0800
06af3c9b0e

Add finish_reason in GenerationResponse (#1153) madroid 2024-12-13 02:37:40 +0800
77b42b7c8b

fix llava (#1149) Awni Hannun 2024-12-12 10:37:26 -0800
f67631679d Add finish_reason in GenerationResponse madroid 2024-12-11 20:56:24 +0800
1fd2bfa5f5 Fix for stream_generate() takes 3 positional arguments but 4 were given Ivan Fioravanti 2024-12-11 06:17:33 +0100
aac5116347 fix llava Awni Hannun 2024-12-10 12:57:17 -0800
c1d9ec329c

Merge branch 'ml-explore:main' into adding-support-for-mamba2 Gökdeniz Gülmez 2024-12-10 20:43:11 +0100
135c5818c1

Fix max_tokens (#1148) Alex Barron 2024-12-10 11:26:04 -0800
e294f06acc

Fix max_tokens Alex Barron 2024-12-10 11:00:49 -0800
184d3d3267 clean up Goekdeniz-Guelmez 2024-12-10 18:20:13 +0100
80e88b4f4d nits Goekdeniz-Guelmez 2024-12-10 18:18:59 +0100
b10afe3662 nits Goekdeniz-Guelmez 2024-12-10 18:15:12 +0100
9f8a6a3509 inference on codestral works but is giberish Goekdeniz-Guelmez 2024-12-10 17:34:44 +0100
ddad2105ef

Merge branch 'main' into adding-support-for-mamba2 Gökdeniz Gülmez 2024-12-10 14:32:44 +0100
b444acfd69 Replace unicode errors instead of raising exception Angelos Katharopoulos 2024-12-09 09:16:51 -0800
12083c4b7e

Support for multiple EOS tokens (#1141) madroid 2024-12-10 00:53:58 +0800
9b53599e6c nits Awni Hannun 2024-12-09 08:51:22 -0800
5687d5b99b

Adds EXAONE architecture. (#1145) n8programs 2024-12-09 10:58:25 -0500
9f3531c814 clean up and fix rope Awni Hannun 2024-12-09 07:44:55 -0800
d90c6af11a clean up and fix rope Awni Hannun 2024-12-09 07:44:32 -0800
b2b16500fb format Awni Hannun 2024-12-09 06:50:16 -0800
aa3defcfb0 nits + format Awni Hannun 2024-12-09 06:46:28 -0800
893b3f085e

Change Flux default max_shift to 1.15 to match the official one (#1137) hehua2008 2024-12-09 15:29:48 +0800
ed91bbc4dc

Fix final message at end of flux training (#1143) Peter Sibley 2024-12-09 02:01:53 -0500
25f423eef8 Remove the message with the missing filename Angelos Katharopoulos 2024-12-08 22:58:26 -0800
1fa3a10e3d Revert "fix missing --final-adapter-file crash in dreambooth.py" Angelos Katharopoulos 2024-12-08 22:56:55 -0800
1fd6aae871

Fix flux training with batch size (#1135) hehua2008 2024-12-09 14:09:04 +0800
68538a6e1d

Adds EXAONE architecture. n8programs 2024-12-09 00:52:05 -0500
ceb0ae3416 Revert "Fix shapes mismatch error in FluxPipeline.training_loss when batch-size >= 2" Angelos Katharopoulos 2024-12-08 21:36:16 -0800
d50ad3ec27 Fix batched add_noise Angelos Katharopoulos 2024-12-08 21:35:16 -0800
2211b27388

Mixed Quantizations (#1132) Alex Barron 2024-12-08 14:21:50 -0800
4345c7c8bb count bias too Alex Barron 2024-12-08 14:05:12 -0800
46109e4141 more concise bpw Alex Barron 2024-12-08 12:44:29 -0800
cd8cf28c39

mlx_lm.evaluate (#1140) Alex Barron 2024-12-08 12:20:10 -0800
facaf01b8d Remove model_config & add eos_token_id madroid 2024-12-08 12:08:09 +0800
1cfb005647 Change _eos_token_ids type from list to set madroid 2024-12-08 11:59:12 +0800
f00ca80fdb fix missing --final-adapter-file crash in dreambooth.py Peter Sibley 2024-12-06 22:23:55 -0500
f8379fb3ef Support for multiple EOS tokens madroid 2024-12-07 11:19:20 +0800
74e5b48e8f comment Alex Barron 2024-12-06 17:49:08 -0800
47cbc418e2 relative import Alex Barron 2024-12-06 16:33:25 -0800
b1a4ba0827 create output dir Alex Barron 2024-12-06 16:31:34 -0800
c3e51fcf02 typo Alex Barron 2024-12-06 16:26:26 -0800
80590f5ec2 add lm eval version Alex Barron 2024-12-06 16:21:20 -0800
dc56226bf8 only write top level results Alex Barron 2024-12-06 15:54:29 -0800
04412c2edd Add evaluation script Alex Barron 2024-12-06 15:52:55 -0800
76fac6eee0 Add a fix for special added tokens Billel Mokeddem 2024-12-05 22:56:49 +0400
76ba80316f Chang Flux's default max_shift to 1.15 to match the official one hehua2008 2024-12-05 19:30:55 +0800
3b5cd401d8 add bits per weight Alex Barron 2024-12-04 08:31:40 -0800
67c68452bb Fix shapes mismatch error in FluxPipeline.training_loss when batch-size >= 2 hehua2008 2024-12-04 22:37:04 +0800
64ceb62674 load q4_k_m inefficiently load-gguf Alex Barron 2024-12-03 19:54:57 -0800
1727959a27

Add mentions of MLX-my-repo. (#1129) vb 2024-12-04 04:21:39 +0100
b365d22785 move Awni Hannun 2024-12-03 19:21:06 -0800
02649b30e5 move Awni Hannun 2024-12-03 19:20:02 -0800
feb7f10888 simplify Awni Hannun 2024-12-03 17:10:41 -0800
1963df8565

Allow prompt callback to generate_step (#1133) Awni Hannun 2024-12-03 16:17:14 -0800
2c8d49dfcc bump version Awni Hannun 2024-12-03 07:01:46 -0800
3c63be8c55 comments Awni Hannun 2024-12-03 06:28:21 -0800
0ca162cfb2

Fix data_iter in prepare_dataset from speechcommands example (#1113) sakares saengkaew 2024-12-03 14:56:07 +0700
43d023948f

add reset() Sakares Saengkaew 2024-12-03 15:53:00 +0800
eb9277f574

Allow loading from diffusers ckpt (#1117) Angelos Katharopoulos 2024-12-02 13:15:50 -0800
2a9294a5f0

Fix bug in FluxSampler.timesteps method (#1131) hehua2008 2024-12-03 05:15:19 +0800
21a05d14d2 nit Awni Hannun 2024-12-02 12:19:53 -0800
1036798dac allow prompt callback and use in cache_prompt Awni Hannun 2024-12-02 12:16:46 -0800
8801beb66f

Add olmo2 (#1128) Awni Hannun 2024-12-02 11:42:58 -0800
5828703a5a comment Alex Barron 2024-12-02 11:11:23 -0800
80e5c37bb9 saving/loading mixed quantizations Alex Barron 2024-12-02 10:19:39 -0800
4c55e92523 mlx_lm.server --model mlx-community/Qwen2.5-Coder-14B-Instruct-8bit --trust-remote-code --port 8722 chenguangjian.jk 2024-12-02 16:49:11 +0800
aef79523a2

Merge branch 'ml-explore:main' into main chenguangjian 2024-12-02 16:42:30 +0800
d459cabea4 Fix bug in FluxSampler.timesteps method hehua2008 2024-12-01 13:07:48 +0800
7c59bfeff2 Add mentions of MLX-my-repo. Vaibhav Srivastav 2024-11-29 14:51:23 +0100
fde4b4dc42 add olmo2 Awni Hannun 2024-11-27 12:15:45 -0800
b0ef3a4c9e add olmo2 Awni Hannun 2024-11-27 11:50:09 -0800
cefe793ae0

Accept mx.array type for prompt argument for stream_generate (#1125) Neil Mehta 2024-11-26 19:51:55 -0500
83bc764e78 Fix formatting Neil Mehta 2024-11-26 16:46:08 -0500
152d6b1e1e Accept mx.array type for prompt argument for stream_generate Neil Mehta 2024-11-26 13:53:03 -0500
cfc29c29f4

Put prompt processing in same stream (#1122) Awni Hannun 2024-11-25 09:47:00 -0800
63e582a058 patch Awni Hannun 2024-11-25 08:11:59 -0800
a5e173802e

docs: update stream_generate return type annotation (#1121) madroid 2024-11-26 00:10:14 +0800
3586c876aa put prompt processing in same stream Awni Hannun 2024-11-25 08:06:12 -0800
5cd7531c22 docs: update stream_generate return type annotation madroid 2024-11-25 14:31:35 +0800
adaab81029

Allow converting models from local directories (#1118) Remixer Dec 2024-11-25 04:41:06 +0400
0ffdb6dd20

Fix object property value in mlx_lm.server chat completions response to match OpenAI spec (#1119) Kevin Conner 2024-11-24 16:37:37 -0800
ec494a97ec Fix object property value in mlx_lm.server chat completions response to match OpenAI spec Kevin Conner 2024-11-24 14:19:12 -0800