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

#1388

#1389

#1390

#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

• 2ba0e36683 [mlx-lm] Use top p in server (#1144) Awni Hannun 2024-12-12 11:12:21 -08:00
• 19abf3dcaa Replace unicode errors instead of raising exception (#1146) Angelos Katharopoulos 2024-12-12 11:10:41 -08:00
• 06af3c9b0e Add finish_reason in GenerationResponse (#1153) madroid 2024-12-13 02:37:40 +08:00
• 77b42b7c8b fix llava (#1149) Awni Hannun 2024-12-12 10:37:26 -08:00
• 135c5818c1 Fix max_tokens (#1148) Alex Barron 2024-12-10 11:26:04 -08:00
• 12083c4b7e Support for multiple EOS tokens (#1141) madroid 2024-12-10 00:53:58 +08:00
• 5687d5b99b Adds EXAONE architecture. (#1145) n8programs 2024-12-09 10:58:25 -05:00
• 893b3f085e Change Flux default max_shift to 1.15 to match the official one (#1137) hehua2008 2024-12-09 15:29:48 +08:00
• ed91bbc4dc Fix final message at end of flux training (#1143) Peter Sibley 2024-12-09 02:01:53 -05:00
• 1fd6aae871 Fix flux training with batch size (#1135) hehua2008 2024-12-09 14:09:04 +08:00
• 2211b27388 Mixed Quantizations (#1132) Alex Barron 2024-12-08 14:21:50 -08:00
• cd8cf28c39 mlx_lm.evaluate (#1140) Alex Barron 2024-12-08 12:20:10 -08:00
• 64ceb62674 load q4_k_m inefficiently load-gguf Alex Barron 2024-12-03 19:54:57 -08:00
• 1727959a27 Add mentions of MLX-my-repo. (#1129) vb 2024-12-04 04:21:39 +01:00
• 1963df8565 Allow prompt callback to generate_step (#1133) Awni Hannun 2024-12-03 16:17:14 -08:00
• 0ca162cfb2 Fix data_iter in prepare_dataset from speechcommands example (#1113) sakares saengkaew 2024-12-03 14:56:07 +07:00
• eb9277f574 Allow loading from diffusers ckpt (#1117) Angelos Katharopoulos 2024-12-02 13:15:50 -08:00
• 2a9294a5f0 Fix bug in FluxSampler.timesteps method (#1131) hehua2008 2024-12-03 05:15:19 +08:00
• 8801beb66f Add olmo2 (#1128) Awni Hannun 2024-12-02 11:42:58 -08:00
• cefe793ae0 Accept mx.array type for prompt argument for stream_generate (#1125) Neil Mehta 2024-11-26 19:51:55 -05:00
• cfc29c29f4 Put prompt processing in same stream (#1122) Awni Hannun 2024-11-25 09:47:00 -08:00
• a5e173802e docs: update stream_generate return type annotation (#1121) madroid 2024-11-26 00:10:14 +08:00
• adaab81029 Allow converting models from local directories (#1118) Remixer Dec 2024-11-25 04:41:06 +04:00
• 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 -08:00
• 0f135396ae Generation refactor: part 2 (#1099) Awni Hannun 2024-11-23 11:47:06 -08:00
• 004eb4cc9d Tencent HunYuan MOE model (#1100) Awni Hannun 2024-11-23 11:06:26 -08:00
• 042280ce50 Fix format (#1115) Angelos Katharopoulos 2024-11-20 16:15:53 -08:00
• 60c7b80350 Pass seed to sd img2img (#1114) Valentin Roussellet 2024-11-20 15:21:52 -08:00
• bd6d910ca3 [MLX LM] Fix f-string formatting in memory warning message (#1105) Alban Lecocq 2024-11-13 15:14:03 +01:00
• 1e07660184 FLUX: save train config (#1049) madroid 2024-11-09 09:15:19 +08:00
• 657b4cc0aa [MLX LM] Sampler refactor + a few improvements (#1094) Awni Hannun 2024-11-07 16:15:24 -08:00
• ed9e81dd58 Fix rotating kv cache size (#1093) Angelos Katharopoulos 2024-11-05 10:24:24 -08:00
• 6fd1f70f73 fix spm decoder multi-byte (#1092) Awni Hannun 2024-11-05 06:06:26 -08:00
• 4394633ce0 mlx_whisper: add support for audio input from stdin (#1012) Anthony Wu 2024-11-04 14:02:13 -08:00
• 3b526f0aa1 Add support for falcon-mamba (#1074) ilyasch2 2024-11-05 00:23:30 +04:00
• 82e3338987 chore(mlx-lm): add max token arg for mlx_lm.chat (#1089) Anchen 2024-11-04 22:06:34 +08:00
• 331148d8ec Enable distributed LoRA training (#821) Angelos Katharopoulos 2024-11-02 18:02:31 -07:00
• 29c954f4cb fix (#1082) Awni Hannun 2024-11-02 13:51:38 -07:00
• 0f799947d0 fix (#1079) Awni Hannun 2024-11-01 16:30:32 -07:00
• e510987870 Clear cache every now and then (#1081) Awni Hannun 2024-11-01 14:15:32 -07:00
• 8160e0c4e5 Whisper improvements (#1080) Awni Hannun 2024-11-01 10:52:28 -07:00
• 85ffd2c96a Quantized KV Cache (#1075) Alex Barron 2024-10-31 16:59:52 -07:00
• 9f34fdbda4 Wire models in MLX LM (#1069) Awni Hannun 2024-10-31 08:17:14 -07:00
• 8fe9539af7 Fix detokenizer space match for quote (#1072) Awni Hannun 2024-10-27 15:06:07 -07:00
• ab4bf05c6e Update lora_config.yaml with new param: num_layers (#1068) hschaeufler 2024-10-26 19:34:46 +03:00
• 67607a8e13 Start memory-efficient flux finetuning branch flux-qlora Angelos Katharopoulos 2024-10-25 09:46:47 -07:00
• 4971462bf0 feat(clip): add linear probe evaluation script (#960) Saurav Maheshkar 2024-10-25 05:56:17 +01:00
• 9000e280ae fix mamba models conversion (#1065) Awni Hannun 2024-10-22 15:44:08 -07:00
• d1d480867b LoRA: update tools datasets docs (#1063) madroid 2024-10-23 03:19:11 +08:00
• 66e7bcb886 override dtype with quant (#1062) Awni Hannun 2024-10-22 09:56:45 -07:00
• 743763bc2e Handle empty string case in maybe_trim_space (#1055) aronson 2024-10-20 22:46:43 -05:00
• f491d473a3 FLUX: Optimize dataset loading logic (#1038) madroid 2024-10-16 01:37:45 +08:00
• 3d62b058a4 fix: typo on flux model preloading (#1050) Zak B. Elep 2024-10-16 00:13:01 +08:00
• bbd2003047 FLUX: update README.md (#1036) madroid 2024-10-15 02:21:41 +08:00
• 605c4854f1 Prompt caching in mlx_lm.server (#1026) Awni Hannun 2024-10-14 10:57:22 -07:00
• 8dca1a2f60 Tokenizer updates + tests (#1024) Awni Hannun 2024-10-14 10:48:46 -07:00
• 6c368f2124 bump mac tests to use py39 (#1047) Awni Hannun 2024-10-14 10:40:36 -07:00
• c799133998 Make llm async eval less brittle (#1040) Awni Hannun 2024-10-14 10:25:24 -07:00
• 1e0cda68c6 Update README.md (#1045) Seitaro Sugawara 2024-10-14 22:21:25 +09:00
• 7612c646f3 Fix PLaMo model to support Grouped Query Attention (#1037) Shunta Saito 2024-10-13 07:26:50 +09:00
• d8611dd69f Small typo fixed in flux README.md (#1035) Ivan Fioravanti 2024-10-12 15:14:01 +02:00
• a5f2bab070 Add FLUX finetuning (#1028) Angelos Katharopoulos 2024-10-11 21:17:41 -07:00
• d72fdeb4ee MusicGen (#1020) Alex Barron 2024-10-11 10:16:20 -07:00
• 4360e7ccec clear cache during prompt processing (#1027) Awni Hannun 2024-10-09 16:48:32 -07:00
• b7373cb44f fix long prompt generations (#1023) Awni Hannun 2024-10-09 11:09:36 -07:00
• fca087be49 More cache improvements (#1015) Awni Hannun 2024-10-07 20:45:51 -07:00
• 9bc53fc210 convert (#1006) Awni Hannun 2024-10-02 13:13:33 -07:00
• 36c1d8e8dc Server: support function calling (#1003) madroid 2024-10-03 03:36:07 +08:00
• 0866e23a67 repetiton_penalty and logits_bias just using logits_processors (#1004) nathan 2024-09-30 17:49:03 +02:00
• 418d9a5511 Feature: QDoRA (#891) Zai Thottakath 2024-09-30 10:01:11 -05:00
• aa1c8abdc6 LoRA: Support HuggingFace dataset via data parameter (#996) madroid 2024-09-30 22:36:21 +08:00
• 50e5ca81a8 Adding full finetuning (#903) Gökdeniz Gülmez 2024-09-30 02:12:47 +02:00
• 7ec2021bb9 LoRA: support tools(function calling) format datasets (#995) madroid 2024-09-29 01:41:36 +08:00
• ace2bb5890 Add logits_processor option to generate_step function (#983) nathan 2024-09-28 19:08:49 +02:00
• d812516d3d Add /v1/models endpoint to mlx_lm.server (#984) jamesm131 2024-09-29 00:21:11 +10:00
• 76710f61af Adding support for mamba (#940) Gökdeniz Gülmez 2024-09-28 16:02:53 +02:00
• e776c970f7 Fix llava model when using text-only prompt (#998) Cheng 2024-09-25 23:19:41 +09:00
• 9bb2dd62f3 Encodec (#991) Awni Hannun 2024-09-23 11:39:25 -07:00
• 796d5e40e4 Fix export to gguf (#993) Angelos Katharopoulos 2024-09-20 13:33:45 -07:00
• f530f56df2 don't use internal exception (#990) Awni Hannun 2024-09-17 16:22:48 -07:00
• 6c2369e4b9 Fix bug in upload + docs nit (#981) Awni Hannun 2024-09-07 14:46:57 -07:00
• c3e3411756 Update LLM generation docs to use chat template (#973) Awni Hannun 2024-09-07 06:06:15 -07:00
• 324184d670 Fix the cache_prompt (#979) Angelos Katharopoulos 2024-09-06 20:19:27 -07:00
• bd29aec299 Support HuggingFace model tree (#957) madroid 2024-09-04 21:19:32 +08:00
• 83a209e200 Add prompt piping (#962) Chime Ogbuji 2024-09-03 16:29:10 -04:00
• bf921afcbe Make sure to import the correct "version" module when installing mlx_whisper and mlx_lm from local source code. (#969) James Zhao 2024-09-03 23:16:21 +03:00
• 3c6e8b11af fix (#965) Awni Hannun 2024-08-30 05:56:27 -07:00
• fc93c55723 feat(mlx_lm): Nemotron (#949) L 2024-08-29 21:08:57 -07:00
• b1186e2a81 Docs on prompt scaling (#963) Awni Hannun 2024-08-29 15:05:17 -07:00
• 1003a8b2dd Add the ability to load the KV cache from a file (#956) Angelos Katharopoulos 2024-08-28 22:11:45 -07:00
• 7f8c961287 Fix setattr for the TokenizerWrapper (#961) Angelos Katharopoulos 2024-08-28 14:47:33 -07:00
• bf21789b17 chore: update black pre-commit hooks to latest versions (#955) Nripesh Niketan 2024-08-26 20:24:23 +05:30
• b5e18ef1e3 Add Phi-3.5-MoE (#946) Prince Canuma 2024-08-24 15:52:33 +02:00
• 6731254e76 Use fast rope (#945) Awni Hannun 2024-08-23 13:18:51 -07:00
• 58591a1b41 fine tune deepseek (#932) Awni Hannun 2024-08-22 10:41:21 -07:00
• 0164d2058b feat: DeepSeek MoE v1 (#942) L 2024-08-17 23:18:09 +09:00
• 7be292c0c9 Handle longer prompt/generation (#931) Awni Hannun 2024-08-16 15:28:39 -07:00
• e196fa3208 Whisper: Support command line (#746) madroid 2024-08-17 01:35:44 +08:00
• 4e01700816 Allow the entire model to be targed for LoRA and DoRA fine tuning: LoRA and DoRA embeddings with small DoRALinear bug fix (#914) Zai Thottakath 2024-08-16 09:38:36 -05:00
• c50971e860 Min P implementation (#926) Chime Ogbuji 2024-08-15 18:45:02 -04:00