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

#1392

#1392

#1393

#1393

#1394

#1395

#1395

#1396

#1396

#1398

#1398

#1399

#14

#140

#1400

#1400

#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

• eff6690952 Fix CFG for SDXL (#667) Angelos Katharopoulos 2024-04-09 06:06:41 -07:00
• 1278994b56 Add streaming detokenizers (#651) Angelos Katharopoulos 2024-04-08 22:36:01 -07:00
• c68aa3c7c3 Stable lm 2 (#666) Awni Hannun 2024-04-08 14:18:55 -07:00
• 1e2f7f50b6 fix for empty initial string (#665) Awni Hannun 2024-04-08 10:40:05 -07:00
• c386dd5f5a Fix for cohere plus (#650) Awni Hannun 2024-04-05 14:11:24 -07:00
• 2bd64b78cf Save lora config (#636) Awni Hannun 2024-04-02 13:52:53 -07:00
• d661440dbb Add support for qwen2moe (#640) Prince Canuma 2024-04-02 20:33:29 +02:00
• 78c431dc25 cleanup whisper a little (#639) Awni Hannun 2024-03-30 13:13:58 -07:00
• f6283ef7ce Configurable LR schedulers (#604) Chime Ogbuji 2024-03-29 16:41:10 -04:00
• b80adbcc3e DBRX (#628) Awni Hannun 2024-03-28 21:03:53 -07:00
• 297a908e3d fix(mlx-lm): type hints in gguf.py (#621) Anchen 2024-03-27 01:56:01 +11:00
• 0ab01b4626 fix(mlx-lm): sorted probs in top_p implementation. (#610) Anchen 2024-03-26 09:07:55 +11:00
• bbfcc103d7 cast around lora adapters (#613) Awni Hannun 2024-03-24 19:34:51 -07:00
• 5a52899405 Partially stream de-tokenization (#609) Awni Hannun 2024-03-23 15:32:33 -07:00
• 494cdf8e96 chore: fix loar for moe model (#608) Anchen 2024-03-24 01:22:11 +11:00
• b8a348c1b8 Switch to fast RMS/LN Norm (#603) Awni Hannun 2024-03-23 07:13:51 -07:00
• fbed720d6f chore(mlx-lm): fix the top_p implementation. (#602) Anchen 2024-03-22 06:18:23 +11:00
• fe96ef342f feat(mlx-lm): export the GGUF (fp16) format model weights from fuse.py (#555) Anchen 2024-03-22 04:34:11 +11:00
• 8f906c859a chore(mlx-lm): enable to apply default chat template (#577) Anchen 2024-03-21 15:39:39 +11:00
• d2a99172a6 Add dropout parameter to lora configuration (#599) Ivan Fioravanti 2024-03-20 16:44:40 +01:00
• 949f63f309 chore(mlx-lm): fix print_trainable_parameters for quant models (#581) Anchen 2024-03-21 02:41:03 +11:00
• 373dd6f2a2 Set finish_reason in response (#592) Matt Wronkiewicz 2024-03-19 20:21:26 -07:00
• 6c3d4c8ba2 add dequantize option to mlx_lm/convert.py (#547) Alwin Arrasyid 2024-03-20 09:50:08 +07:00
• 6f2fd5daea Add mlx-lm version information to HF model card (#596) Chime Ogbuji 2024-03-19 22:42:03 -04:00
• 39d5ca6427 LoRA: report last train info (#595) madroid 2024-03-20 08:29:50 +08:00
• 4680ef4413 Enable more BERT models (#580) yzimmermann 2024-03-20 01:21:33 +01:00
• b0bcd86a40 Support for OpenAI’s fine-tuning dataset format (#548) madroid 2024-03-20 07:45:46 +08:00
• e05e502c34 Fix scaling when embeddings are tied (#591) Abdul Fatir 2024-03-18 21:41:07 +01:00
• e4b19bb9e1 Make attention faster for a some models (#574) Awni Hannun 2024-03-14 21:35:54 -07:00
• 3f3741d229 Fix requirements and image2image strength/steps mismatch (#585) Angelos Katharopoulos 2024-03-14 12:22:54 -07:00
• e2205beb66 Update server.py to add --trust-remote-code to server (#578) sweetcard 2024-03-14 22:05:19 +08:00
• 2cd793dd69 feat: add update_config functionality (#531) Sugato Ray 2024-03-14 09:36:05 -04:00
• 485180ae91 LoRA: some minor optimizations (#573) madroid 2024-03-14 11:26:30 +08:00
• d4e1de1d5b add peak_memory info to training callback (#572) madroid 2024-03-14 11:17:10 +08:00
• 376bb9cc44 bert encoder inherits from nn.Module now (#571) Race 2024-03-13 10:24:21 -07:00
• 14fe868825 version (#570) Awni Hannun 2024-03-13 10:09:36 -07:00
• 76c3244cc5 Add support for Cohere's Command-R (#565) Prince Canuma 2024-03-13 15:03:36 +01:00
• 3535408c99 chore(mlx-lm): fix tie_word_embeddings for qwen2 (#566) Anchen 2024-03-13 15:34:32 +11:00
• 39084e81c2 Some improvements to LoRA (#528) Awni Hannun 2024-03-12 20:02:03 -07:00
• e56d9015ef LoRA on all linear transformer block layers (#546) Chime Ogbuji 2024-03-12 10:37:40 -04:00
• fe5edee360 Fix image2image for SDXL (#563) devonthomas35 2024-03-11 12:18:47 -07:00
• d0fa6cfcae feat: stable-diffusion t2i add --seed (#558) zweifisch 2024-03-10 21:12:54 +08:00
• ad3cf5ed98 dropout 0 as default (#549) Awni Hannun 2024-03-08 13:07:10 -08:00
• 3a9e6c3f70 Stable diffusion XL (#516) Angelos Katharopoulos 2024-03-08 10:24:19 -08:00
• 8c2cf665ed YAML configuration for mlx_lm.lora (#503) Chime Ogbuji 2024-03-08 10:57:52 -05:00
• 8b05bb6d18 [mlx-lm] Use sdpa in llama / mistral model (#515) Awni Hannun 2024-03-07 17:41:23 -08:00
• 7cdd1b69ac Enable unit testing in Circle and start some MLX LM tests (#545) Awni Hannun 2024-03-07 09:31:57 -08:00
• ef32379bc6 Update README.md (#530) amcox886 2024-03-07 14:23:43 +00:00
• 8a178f8716 chore: enable tie_word_embeddings config for qwen2 (#544) Anchen 2024-03-08 01:11:35 +11:00
• b8e5eda4fd Refactoring of mlx_lm example (#501) Y4hL 2024-03-06 16:24:31 +02:00
• 710c552731 add huggingface repo url print (#534) Madroid Ma 2024-03-06 13:51:31 +08:00
• 5de7c2ac33 Add tips on porting LLMs from HuggingFace (#523) Muhtasham Oblokulov 2024-03-06 02:43:15 +01:00
• 3fdf85e79d Starcoder2: Update config and change GQA to use repeat (#520) Prince Canuma 2024-03-03 15:12:03 +01:00
• 1e3daea3bb chore(mlx-lm): add missing model_type for starcoder2 (#522) Anchen 2024-03-04 01:07:45 +11:00
• 3655bfc3bd chore(mlx-lm): fix broken server.py script (#519) Anchen 2024-03-04 01:04:54 +11:00
• 81e2a80026 Add Starcoder 2 (#502) Muhtasham Oblokulov 2024-03-03 04:39:23 +01:00
• 5b1043a458 llms: convert() add 'revision' argument (#506) Miller Liang 2024-03-02 22:28:26 +08:00
• a429263905 LlaVA in MLX (#461) Noah Kasmanoff 2024-03-01 13:28:35 -05:00
• 261f1280f6 Update to StableLM code (#514) Ashish 2024-03-01 10:53:38 -07:00
• 3acc1ec84e fix: string indentation with textwrap.dedent (#510) Sugato Ray 2024-03-01 01:23:01 -05:00
• f03c8a7b44 LoRA: adapter file Support path information (#505) Madroid Ma 2024-03-01 14:20:49 +08:00
• ae48563378 Remove gc (#509) Awni Hannun 2024-02-29 09:40:04 -08:00
• 13794a05da chore(mlx-lm): add adapter support in generate.py (#494) Anchen 2024-02-29 02:49:25 +11:00
• ab0f1dd1b6 Add metadata when saving safetensors (#496) Alex Ishida 2024-02-29 00:29:00 +09:00
• ea92f623d6 Prevent llms/mlx_lm from serving the local directory as a webserver (#498) Y4hL 2024-02-28 05:40:42 +02:00
• 676e574eff Add missing import (#497) Y4hL 2024-02-27 23:27:08 +02:00
• 95f82e67a2 Fix import warning (#479) Awni Hannun 2024-02-27 08:47:56 -08:00
• 82f3f31d93 chore(mlx-lm): refactor server.py to utilize generate_step from utils for consistency (#491) Anchen 2024-02-28 01:25:24 +11:00
• 19a21bfce4 chore: add /v1/completions for server (#489) Anchen 2024-02-27 15:59:33 +11:00
• e5dfef5d9a LoRA: Extract the run function for easy use in scripts file (#482) Madroid Ma 2024-02-27 11:35:04 +08:00
• ccb278bcbd Add top-p sampling for text generation (#486) peterjc123 2024-02-26 22:18:11 +08:00
• 47dd6bd17f chore(clip): update the clip example to make it compatible with HF format (#472) Anchen 2024-02-24 01:49:53 +11:00
• f24edfa9dc [mlx-lm] Add precompiled normalizations (#451) Awni Hannun 2024-02-22 12:40:55 -08:00
• 97c09a863d bump version and include in package (#475) Awni Hannun 2024-02-21 09:40:36 -08:00
• ab9172baac Gemma support (#474) Awni Hannun 2024-02-21 08:47:13 -08:00
• cfeef6d9d2 Typo: SGD->AdamW (#471) Kosti 2024-02-20 23:47:17 +00:00
• 838990b33b fix: remove custom rope (#470) Juan B. Rodriguez 2024-02-20 16:46:16 -05:00
• dc4f2e0a6b Lazy loading models for faster convert and merge (#462) Angelos Katharopoulos 2024-02-20 13:36:55 -08:00
• 8eee4399f4 LoRA: Add printing and callbacks for learning rate during training (#457) Madroid Ma 2024-02-21 05:07:21 +08:00
• 15ecf692b9 Bug fix in lora.py (#468) Sergey Shumov 2024-02-20 12:53:30 -08:00
• 20b39c7fee update protobuf (#467) Awni Hannun 2024-02-20 11:46:36 -08:00
• 8fd953ee2b Support for slerp merging models (#455) Awni Hannun 2024-02-19 20:37:15 -08:00
• 8c9148a8fd Make it easier to know in which file we have bad JSON data (#458) Ovid 2024-02-20 05:11:45 +01:00
• 88458c4e40 feat(mlx-lm): add openAI like api server (#429) Anchen 2024-02-19 09:01:28 +11:00
• cc671cd1c7 Mixtral: Fix non-default arg follows default exception (#450) devonthomas35 2024-02-18 13:30:26 -08:00
• b05907c87e Change argument name in lora.py (#453) Ivan Fioravanti 2024-02-18 15:04:49 +01:00
• e4d5630698 Basic CircleCI (#449) Awni Hannun 2024-02-16 22:13:55 -08:00
• 21e19b5b5a Add Repetitive penalty to LLM inference - mlx-lm (#399) vishal-14069 2024-02-17 00:58:17 -05:00
• 0ba466369f LoRA: add training callbacks (#414) Madroid Ma 2024-02-16 22:04:57 +08:00
• 726b1ddec0 fix: check LoRA layers number error (#446) Madroid Ma 2024-02-16 22:03:33 +08:00
• 837a02092d Update black version to 24.2.0 (#445) Nripesh Niketan 2024-02-16 18:02:52 +04:00
• f71e965d57 Change gqa to use repeat instead of concatenate (#443) Angelos Katharopoulos 2024-02-14 17:40:11 -08:00
• 06ddb8414d Fix Qwen2 and SD (#441) Awni Hannun 2024-02-14 13:43:12 -08:00
• e446598f62 Passing parameterized loss and batching to trainer (#391) Chime Ogbuji 2024-02-13 10:03:25 -05:00
• 954aa50c54 LoRA: Improve validation error for LoRA layer count exceeding model layer (#427) Madroid Ma 2024-02-13 22:56:27 +08:00
• d4666615bb Lazy import + refactor Lora layer addition (#426) Awni Hannun 2024-02-12 10:51:02 -08:00
• 4576946151 Add checkpoints directory for adapter weights (#431) Ivan Fioravanti 2024-02-12 19:50:05 +01:00
• 70465b8cda clean up loss function extraction (#433) Lee Harrold 2024-02-12 08:46:00 -05:00
• f1ef378a58 Feat: update pre-commit rev (#432) Nripesh Niketan 2024-02-11 19:23:27 +04:00
• f45a1ab83c Update a few examples to use compile (#420) Awni Hannun 2024-02-08 13:00:41 -08:00