mlx-examples

zhangyiss/mlx-examples

Fork 0

mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-08-31 03:19:23 +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

418d9a5511

Feature: QDoRA (#891) Zai Thottakath 2024-09-30 10:01:11 -0500
7526da7754 some simplifications and fixes Awni Hannun 2024-09-30 07:46:45 -0700
aa1c8abdc6

LoRA: Support HuggingFace dataset via data parameter (#996) madroid 2024-09-30 22:36:21 +0800
7ecec3b7ea feat: QDoRA with tests and a small bug fix for recalculation of self.m Zai Thottakath 2024-07-15 17:42:23 -0500
3b1c70ea2d nits and doc Awni Hannun 2024-09-29 19:21:53 -0700
50e5ca81a8

Adding full finetuning (#903) Gökdeniz Gülmez 2024-09-30 02:12:47 +0200
636cc0c375 some consistency changes Awni Hannun 2024-09-29 13:21:20 -0700
39e5152ed8

refactor of repetition_penalty and logits_bias to use logits_processor Nathan Ranchin 2024-09-29 18:01:37 +0200
cdb2d29d4b Server: support function calling madroid 2024-09-29 15:46:22 +0800
6d46cbb4a6 update data argument help madroid 2024-09-29 14:44:12 +0800
a83ca489a4 fix pre-commit lint madroid 2024-09-29 14:22:38 +0800
32a0bc903a handle load hf dataset error madroid 2024-09-29 14:21:24 +0800
c265cb08f0 resolve merge Awni Hannun 2024-09-28 15:03:42 -0700
1c5eed70e3 nits Awni Hannun 2024-09-28 14:23:11 -0700
09fd091ea6

Merge branch 'main' into adding-full-finetuning Gökdeniz Gülmez 2024-09-28 19:54:37 +0200
7ec2021bb9

LoRA: support tools(function calling) format datasets (#995) madroid 2024-09-29 01:41:36 +0800
e80d1f4b20 nit in readme Awni Hannun 2024-09-28 10:38:00 -0700
bdad0cd4a6 nit in readme Awni Hannun 2024-09-28 10:36:54 -0700
f01dbe89e8 nit in readme Awni Hannun 2024-09-28 10:25:56 -0700
ace2bb5890

Add logits_processor option to generate_step function (#983) nathan 2024-09-28 19:08:49 +0200
83aaf0c98b add back logit bias + test Awni Hannun 2024-09-28 09:55:43 -0700
c8216caa61 test Awni Hannun 2024-09-28 08:32:09 -0700
824f7fda58 nits + test Awni Hannun 2024-09-28 08:28:37 -0700
50e4665c1d fix the variable name Nathan Ranchin 2024-09-28 16:20:26 +0200
917cdb4ae3 remove the logit_bias argument from generate_step method Nathan Ranchin 2024-09-28 15:20:00 +0200
3d27dbf304 Rename the tokens variable for clarity Nathan Ranchin 2024-09-10 22:10:28 +0200
92ba4b2bf5 concatenation correction Nathan Ranchin 2024-09-10 22:05:03 +0200
67a9325603 Add logits_processor option for the generation as in huggingface transformers library Nathan Ranchin 2024-09-10 21:24:48 +0200
d812516d3d

Add /v1/models endpoint to mlx_lm.server (#984) jamesm131 2024-09-29 00:21:11 +1000
92e30b71a0 doc Awni Hannun 2024-09-28 07:16:45 -0700
b96a64c343 simplify test Awni Hannun 2024-09-28 07:11:22 -0700
76710f61af

Adding support for mamba (#940) Gökdeniz Gülmez 2024-09-28 16:02:53 +0200
1738a06c33 nits Awni Hannun 2024-09-28 06:36:47 -0700
a10f20654a nits Awni Hannun 2024-09-28 06:35:27 -0700
03d3d19e6a fix test Awni Hannun 2024-09-27 17:49:48 -0700
ae9cc8c862 some speedups and cleanups Awni Hannun 2024-09-27 17:37:34 -0700
97257511c4 modified mlx_lm.server.py to support prompt caching. nath1295 2024-09-27 17:49:51 +0100
7e98499ee3 Better support for rotating KV-cache and add stop word list as an argument for generate and stream_generate nath1295 2024-09-27 13:43:45 +0100
d6cd23de16

Update README.md mark 2024-09-26 17:21:03 +0100
bb433e2b78

Update generate.py mark 2024-09-26 16:59:01 +0100
e5c98f4715

Update utils.py mark 2024-09-26 16:58:02 +0100
1b6440f4ae

Merge branch 'ml-explore:main' into adding-support-for-mamba Gökdeniz Gülmez 2024-09-26 17:56:02 +0200
45865cbaee

Merge branch 'ml-explore:main' into adding-full-finetuning Gökdeniz Gülmez 2024-09-26 17:55:52 +0200
dafda90980

Update README.md mark 2024-09-26 16:52:46 +0100
26cb8f444c

Update README.md mark 2024-09-26 16:52:37 +0100
03332d863b fix spelling errors madroid 2024-09-26 11:41:42 +0800
e776c970f7

Fix llava model when using text-only prompt (#998) Cheng 2024-09-25 23:19:41 +0900
5731995652 Fix llava model when using text-only prompt Cheng 2024-09-25 15:31:43 +0900
fe0de13a9d

Merge branch 'ml-explore:main' into adding-support-for-mamba Gökdeniz Gülmez 2024-09-24 14:51:03 +0200
3857a77093

Merge branch 'ml-explore:main' into adding-full-finetuning Gökdeniz Gülmez 2024-09-24 14:50:54 +0200
9bb2dd62f3

Encodec (#991) Awni Hannun 2024-09-23 11:39:25 -0700
4111473f9d nits Awni Hannun 2024-09-23 11:38:00 -0700
b101182853 update tests to check hf_cache for models jamesm131 2024-09-22 20:11:23 +1000
e17a7dc443 Check hf_cache for mlx models jamesm131 2024-09-22 20:10:56 +1000
e4eb4e29b7 Add test for new 'models' server endpoint jamesm131 2024-09-12 20:09:36 +1000
a599190a8b Add 'models' endpoint to server jamesm131 2024-09-12 20:08:24 +1000
eb016aea9c

Merge branch 'ml-explore:main' into adding-full-finetuning Gökdeniz Gülmez 2024-09-21 23:59:50 +0200
d5ff17c407

Merge branch 'ml-explore:main' into adding-support-for-mamba Gökdeniz Gülmez 2024-09-21 23:59:40 +0200
dcad8339e1 LoRA: split small functions madroid 2024-09-22 01:49:12 +0800
aed1a0fcac LoRA: Extract the load_custom_hf_dataset function madroid 2024-09-22 01:46:44 +0800
fee252aa4f LoRA: support huggingface dataset via data argument madroid 2024-09-22 01:02:09 +0800
59e29ba6bf LoRA: remove ToolsDataset madroid 2024-09-22 00:50:12 +0800
1034aa4af1 Revert "LoRA: Split small function" madroid 2024-09-22 00:44:59 +0800
03390a7e52 Revert "LoRA: pre-commit fix" madroid 2024-09-22 00:44:21 +0800
796d5e40e4

Fix export to gguf (#993) Angelos Katharopoulos 2024-09-20 13:33:45 -0700
b94b7e0fe7 LoRA: pre-commit fix madroid 2024-09-20 12:10:25 +0800
30b39c7115 LoRA: add tools format to lora docs madroid 2024-09-20 11:34:27 +0800
3f6a5f19fd LoRA: Split small function madroid 2024-09-20 11:06:06 +0800
bfd4ba2347 LoRA: support fine-tuning tools datasets madroid 2024-09-20 10:58:11 +0800
9457329ed3 reformat and big clean up, final commit Goekdeniz-Guelmez 2024-09-19 18:13:40 +0200
f3c6ed99c8 fix example, support batched inference Awni Hannun 2024-09-18 06:01:04 -0700
30e58ccf10 audio encodec Awni Hannun 2024-09-17 17:08:22 -0700
c0afcb7a5d use custom LSTM kernel Awni Hannun 2024-09-17 17:02:31 -0700
a6516b100f fix mlx version Awni Hannun 2024-09-16 16:21:04 -0700
82e5c66385 fix for rnn layer Awni Hannun 2024-09-16 16:20:37 -0700
0a73862430 use fast group norm Awni Hannun 2024-09-15 08:47:10 -0700
c3209fd29a nits Awni Hannun 2024-09-14 17:03:59 -0700
cead1541c5 works Awni Hannun 2024-09-14 16:35:51 -0700
2d82579bc8 initial encodec Awni Hannun 2024-09-13 14:22:39 -0700
13af75d88a clean up, reformating will come later Goekdeniz-Guelmez 2024-09-18 14:44:49 +0200
399de78f51 removing extra mamba-infer.py file Goekdeniz-Guelmez 2024-09-18 13:37:43 +0200
40f9e83306 Forther update to trainer/utils for correct layer selection. Successfull training Goekdeniz-Guelmez 2024-09-18 13:24:39 +0200
602c9f18bd clean up Goekdeniz-Guelmez 2024-09-18 11:13:22 +0200
511cdf89b1 update trainer/utils for right initialisation of the layers for LoRA, but not working. Goekdeniz-Guelmez 2024-09-18 11:04:01 +0200
407bdefc76 Fix export to gguf Angelos Katharopoulos 2024-09-17 22:34:10 -0700
f530f56df2

don't use internal exception (#990) Awni Hannun 2024-09-17 16:22:48 -0700
b0ba2342b1 don't use internal exception Awni Hannun 2024-09-17 16:19:38 -0700
3ef1011aff modify generate_step in utils for cache history restoration with python api nath1295 2024-09-17 20:49:46 +0100
dee703eacf

feat: simplify data handling Saurav Maheshkar 2024-09-14 23:31:17 +0100
6c2369e4b9

Fix bug in upload + docs nit (#981) Awni Hannun 2024-09-07 14:46:57 -0700
29023ea61d nit Awni Hannun 2024-09-07 08:25:35 -0700
11a2daebf3 fix bug in upload + docs nit Awni Hannun 2024-09-07 08:23:49 -0700
c3e3411756

Update LLM generation docs to use chat template (#973) Awni Hannun 2024-09-07 06:06:15 -0700
0a0ededeb0 version Awni Hannun 2024-09-06 20:21:14 -0700
c32f689f94 revert Awni Hannun 2024-09-06 20:20:30 -0700
19144e892c add template to model cards as well Awni Hannun 2024-09-03 13:34:58 -0700
ae62c7f429 fix docs Awni Hannun 2024-09-03 13:25:37 -0700
324184d670

Fix the cache_prompt (#979) Angelos Katharopoulos 2024-09-06 20:19:27 -0700
e568161b75 Fix the cache_prompt Angelos Katharopoulos 2024-09-06 18:08:48 -0700
9868743762 removed max file size Goekdeniz-Guelmez 2024-09-05 10:01:58 +0200