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

Mono Color

• 9183fe8b6d
  fix (#1192) Awni Hannun 2025-01-06 10:12:07 -0800
• 975abdd8c2 ok Merge branch 'main' of github.com:ml-explore/mlx-examples into add_modelscope xingjun.wang 2025-01-07 02:04:32 +0800
• fb191d1150 fix Awni Hannun 2025-01-06 09:18:21 -0800
• f2619f507c
  Add support for fewshot and apply chat template lm_eval functionality (#1180) Chime Ogbuji 2025-01-06 10:58:43 -0500
• 070da54966 don't add duplicate bos Awni Hannun 2025-01-06 07:13:02 -0800
• e1072b5300 Add HF overrides for methods needed by added options Chime Ogbuji 2024-12-23 12:02:37 -0500
• d352074e73 Add support for multiturn fewshot examples and chat templates Chime Ogbuji 2024-12-23 10:45:17 -0500
• 7fed460146 comment Awni Hannun 2025-01-06 06:10:50 -0800
• 25ec2d8c44
  Change the eos-token argument for mlx_lm.generate (#1176) Angelos Katharopoulos 2025-01-05 22:26:05 -0800
• 22d4a20dc2 add pipeline generation and example Awni Hannun 2025-01-05 14:55:23 -0800
• 2954fc56dd update snapshot_download xingjun.wang 2025-01-06 00:40:25 +0800
• 5c535a28c0 update xingjun.wang 2025-01-06 00:25:52 +0800
• 9d86b5b744 add MLX_USE_MODELSCOPE env xingjun.wang 2025-01-06 00:04:06 +0800
• 18f380b177 use upload_large_file instead of deprecated multi comit Awni Hannun 2025-01-04 21:02:13 -0800
• 82e31968a2 deepseekv3 Awni Hannun 2025-01-04 11:25:50 -0800
• c4833a2f55
  fix encoding with special tokens + chat template (#1189) Awni Hannun 2025-01-03 10:50:59 -0800
• 1499796e92 fix encoding with special tokens + chat template Awni Hannun 2025-01-03 09:52:15 -0800
• 3a58c36109
  Improvements to mlx_lm.manage (#1178) Ivan Fioravanti 2025-01-01 16:25:57 +0100
• 32d8793583 nits Awni Hannun 2024-12-31 19:31:46 -0800
• b84b483e9f
  Fixing case for no case Ivan Fioravanti 2024-12-31 16:29:09 +0100
• 2541f13907
  format L Lllvvuu 2024-12-27 16:21:20 -0800
• 089480878f
  dtype fix L Lllvvuu 2024-12-27 16:01:52 -0800
• 30e98c85c1
  tweaks L Lllvvuu 2024-12-27 15:52:42 -0800
• fdd16caf7a
  mask dtype L Lllvvuu 2024-12-27 15:26:43 -0800
• 465eb79fff
  implement batch_generate L Lllvvuu 2024-12-27 13:47:09 -0800
• 8deada9d11 optimizations Goekdeniz-Guelmez 2024-12-27 17:52:14 +0100
• 4e94e87f57 nits Goekdeniz-Guelmez 2024-12-27 15:41:54 +0100
• 3384d38a83 nits Goekdeniz-Guelmez 2024-12-27 15:37:41 +0100
• 2ed51946ab still gibberish Goekdeniz-Guelmez 2024-12-27 15:36:37 +0100
• f4cbe27b0f new set but still gibberish Goekdeniz-Guelmez 2024-12-27 15:27:09 +0100
• d044db959d update Goekdeniz-Guelmez 2024-12-27 15:17:45 +0100
• cded14988c
  fix test_generate L Lllvvuu 2024-12-27 01:53:15 -0800
• a28ca03e04
  update generate_step callsites L Lllvvuu 2024-12-27 01:51:28 -0800
• 3082db0143
  WIP: most of the merge, minus llms/mlx_lm/utils.py L Lllvvuu 2024-12-25 22:17:35 -0800
• 70e4a6e662 improvements to manage. Default value is N and size added to deletion confirmation. ivanfioravanti 2024-12-21 23:34:44 +0100
• 431cc268a8 Change the eos-token argument for mlx_lm.generate Angelos Katharopoulos 2024-12-20 13:57:23 -0800
• ae53ed9090 add TesseraQ rounding awq-tq Alex Barron 2024-12-19 19:35:26 -0800
• fc81342afe remove comment awq Alex Barron 2024-12-19 19:14:02 -0800
• 77d75f3ccc Add learned AWQ quantization Alex Barron 2024-12-19 19:13:22 -0800
• d4ef909d4a
  Length masking for batch inputs (#1173) Alex Barron 2024-12-18 19:43:52 -0800
• db109184b7
  Fix no template prompt + top_k sampling (#1166) Awni Hannun 2024-12-18 18:46:50 -0800
• 5b414dddf2 comment + fix Alex Barron 2024-12-18 18:39:14 -0800
• eb9452beb9 fix test: Alex Barron 2024-12-18 13:59:02 -0800
• ef895f6e5b remove lengths Alex Barron 2024-12-18 13:55:28 -0800
• cd9dcf0383 add mask to mlx_lm model interface Alex Barron 2024-12-18 13:54:14 -0800
• 0ae536c423 update: using einsum on som elines making it faster, but still generates Gibberish on Codestral Goekdeniz-Guelmez 2024-12-18 19:32:22 +0100
• 7996a6f4fd
  Merge branch 'ml-explore:main' into adding-support-for-mamba2 Gökdeniz Gülmez 2024-12-18 18:35:43 +0100
• c5ce9a31f2 length masking Alex Barron 2024-12-17 22:35:45 -0800
• bc08025f41 Add optional quantization types packed-quants Angelos Katharopoulos 2024-12-17 22:24:41 -0800
• 845efddc8c
  Fix decoding manually added tokens (#1164) Billel Mokeddem 2024-12-17 21:54:29 +0400
• 0007b019d9 no lag bpe Awni Hannun 2024-12-17 09:45:42 -0800
• 0fb0b6b4e6 nit Awni Hannun 2024-12-17 09:10:26 -0800
• eb81e97963 nit Awni Hannun 2024-12-17 09:10:01 -0800
• 34c9cfcc3c fix + test Awni Hannun 2024-12-17 09:09:17 -0800
• 68533e2a8f
  Merge branch 'ml-explore:main' into adding-support-for-mamba2 Gökdeniz Gülmez 2024-12-17 11:14:40 +0100
• d8dc7ae7d0 fix chinese Awni Hannun 2024-12-16 12:21:22 -0800
• 9e7c2c1ee7 add top_k sampling Awni Hannun 2024-12-16 10:04:12 -0800
• dfa4dd6c93
  Add support for cohere2 (#1157) Prince Canuma 2024-12-16 17:01:03 +0100
• 799dfde8a3 nits Awni Hannun 2024-12-16 07:55:06 -0800
• dec2acface style Awni Hannun 2024-12-16 07:53:07 -0800
• 4aee86243e some nits Awni Hannun 2024-12-16 07:45:15 -0800
• ae4fdfc2e7 fix no template prompt Awni Hannun 2024-12-16 06:53:39 -0800
• 8c67480050 Fix decoding manually added tokens Billel Mokeddem 2024-12-16 13:04:07 +0400
• fb3d0526a2 chore: update evaluate.py (#1159) Ikko Eltociear Ashimine 2024-12-15 23:06:29 +0900
• 46fd8b7c53 * rebase with main Awni Hannun 2024-12-12 13:13:50 -0800
• 1026cc5608 [mlx-lm] Use top p in server (#1144) Awni Hannun 2024-12-12 11:12:21 -0800
• 3858956c5f Replace unicode errors instead of raising exception (#1146) Angelos Katharopoulos 2024-12-12 11:10:41 -0800
• 3f895740e2 Add finish_reason in GenerationResponse (#1153) madroid 2024-12-13 02:37:40 +0800
• 6eb95c63c8 fix llava (#1149) Awni Hannun 2024-12-12 10:37:26 -0800
• b83a73049d Fix max_tokens (#1148) Alex Barron 2024-12-10 11:26:04 -0800
• 64781fddf1 Support for multiple EOS tokens (#1141) madroid 2024-12-10 00:53:58 +0800
• f1d730a9aa Adds EXAONE architecture. (#1145) n8programs 2024-12-09 10:58:25 -0500
• 5d561f1113 Change Flux default max_shift to 1.15 to match the official one (#1137) hehua2008 2024-12-09 15:29:48 +0800
• 2932980786 Fix final message at end of flux training (#1143) Peter Sibley 2024-12-09 02:01:53 -0500
• 21f5f66b74 Fix flux training with batch size (#1135) hehua2008 2024-12-09 14:09:04 +0800
• 1bf8129206 Mixed Quantizations (#1132) Alex Barron 2024-12-08 14:21:50 -0800
• e61847ed7b mlx_lm.evaluate (#1140) Alex Barron 2024-12-08 12:20:10 -0800
• 7bb129893b Add mentions of MLX-my-repo. (#1129) vb 2024-12-04 04:21:39 +0100
• e08c470d29 Allow prompt callback to generate_step (#1133) Awni Hannun 2024-12-03 16:17:14 -0800
• a73de93247 Fix data_iter in prepare_dataset from speechcommands example (#1113) sakares saengkaew 2024-12-03 14:56:07 +0700
• a0e7965a4f Allow loading from diffusers ckpt (#1117) Angelos Katharopoulos 2024-12-02 13:15:50 -0800
• 7ee0a55705 Fix bug in FluxSampler.timesteps method (#1131) hehua2008 2024-12-03 05:15:19 +0800
• 278884f6ca Add olmo2 (#1128) Awni Hannun 2024-12-02 11:42:58 -0800
• 5d841fd708 Accept mx.array type for prompt argument for stream_generate (#1125) Neil Mehta 2024-11-26 19:51:55 -0500
• 149fdcc523 Put prompt processing in same stream (#1122) Awni Hannun 2024-11-25 09:47:00 -0800
• 47456f9cb0 docs: update stream_generate return type annotation (#1121) madroid 2024-11-26 00:10:14 +0800
• a0c11fe91d Allow converting models from local directories (#1118) Remixer Dec 2024-11-25 04:41:06 +0400
• 9960d47d10 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
• ad9948b895 Generation refactor: part 2 (#1099) Awni Hannun 2024-11-23 11:47:06 -0800
• 54020c7751 Tencent HunYuan MOE model (#1100) Awni Hannun 2024-11-23 11:06:26 -0800
• 20e87fe35f Fix format (#1115) Angelos Katharopoulos 2024-11-20 16:15:53 -0800
• 6497a5dfbb Pass seed to sd img2img (#1114) Valentin Roussellet 2024-11-20 15:21:52 -0800
• f5af47204b [MLX LM] Fix f-string formatting in memory warning message (#1105) Alban Lecocq 2024-11-13 15:14:03 +0100
• fc0674d2d8
  chore: update evaluate.py (#1159) Ikko Eltociear Ashimine 2024-12-15 23:06:29 +0900
• 29d3b7d6e3
  chore: update evaluate.py Ikko Eltociear Ashimine 2024-12-15 22:43:46 +0900
• 20d792576c
  Merge pull request #1 from N8python/add-cohere2-arch-rotating-kv-cache Prince Canuma 2024-12-14 23:29:32 +0100
• ac58a95fbd Add rotating kvcache to save space N8 2024-12-14 17:08:06 -0500
• 4823f279d5 rollback OTHER changes (oopsy) N8 2024-12-14 15:23:19 -0500
• 75fbb7ed34 Add Cohere2 N8 2024-12-14 15:17:12 -0500
• 406c7f300f add coauthor :) Prince Canuma 2024-12-14 17:12:49 +0100