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

• 8071aacd98 fix-mistral-download-link (#418) Long Sha 2024-02-06 22:56:56 -05:00
• 2303238e44 Update olmo.py (#419) Chris McMaster 2024-02-07 11:16:46 +11:00
• 8b77677c05 chore(mlx-lm): add model weight index in save_weights (#413) Anchen 2024-02-07 00:32:15 +11:00
• a7d139f484 fix(mlx-lm): olmo 1b model (#417) Anchen 2024-02-07 00:27:05 +11:00
• aa7447efa2 Olmo in MLX LM (#415) Awni Hannun 2024-02-05 21:13:49 -08:00
• 7fbca214b1 Add max sequence length argument in lora.py (#408) Ivan Fioravanti 2024-02-04 21:28:21 +01:00
• 9d0dd34403 add qwen2 (#411) Junyang Lin 2024-02-05 00:31:38 +08:00
• e9b32747b4 Add grad checkpointing and PE in the transformer example (#387) Angelos Katharopoulos 2024-02-01 13:04:03 -08:00
• ec14583c2a work with tuple shape (#393) Awni Hannun 2024-02-01 13:03:47 -08:00
• 0340113e02 BUG FIX: Decoding results in garbled text when multiple tokens represent a single character (e.g., Chinese). (#398) ZHAOKAI WANG 2024-02-01 11:27:29 +08:00
• 94358219cf CLIP (ViT) (#315) Gabrijel Boduljak 2024-01-31 23:19:53 +01:00
• ba3a9355d1 LoRA: Remove unnecessary model type judgments (#388) Madroid Ma 2024-02-01 03:55:27 +08:00
• 0a49ba0697 fix(mlx-lm): apply lora layer doesn't update the lora weights (#396) Anchen 2024-02-01 06:51:26 +11:00
• ab8bde1590 Add py.typed to support PEP-561 (type-hinting) (#389) Sugato Ray 2024-01-31 00:17:38 -05:00
• f8fadf7a17 Fix token count computation to fix tps measurements (#392) David Koski 2024-01-30 11:24:16 -08:00
• 614de6652f chore(mlx-lm): add reset lora layers helper (#377) Anchen 2024-01-30 15:54:49 +11:00
• 20b969b412 Replace time.time() with time.perf_counter() as it is more suited for benchmarking (#380) Ashish 2024-01-26 15:11:38 -07:00
• 5aa652d3c2 remove simplify (#379) Awni Hannun 2024-01-26 13:54:49 -08:00
• 0b57f0eae6 Add StableLM-2 1.6B (#378) Ashish 2024-01-26 11:28:00 -07:00
• 854ad8747a feat(mlx-lm): add de-quant for fuse.py (#365) Anchen 2024-01-26 13:59:32 +11:00
• f51e98fcf1 chore(mlx-lm): truncate the input sentence to max seq len in lora iterate_batches (#373) Anchen 2024-01-26 07:38:04 +11:00
• 0f19237fb8 docs: added missing imports (#375) Yiğit Ö. Ünver 2024-01-25 21:44:53 +03:00
• b1dec281b3 feat(mlx-lm): add lora hypeparameters in lora layer (#366) Anchen 2024-01-25 03:11:25 +11:00
• 5fc8668a53 fix(mlx-lm): handle legacy quant models (#369) Anchen 2024-01-25 02:44:05 +11:00
• ab91ac1075 chore(mlx-lm): add load model with adapter and fix bug in sample (#360) Anchen 2024-01-23 19:47:39 -08:00
• f5b80c95fb Example reading directly from gguf file (#222) Juarez Bochi 2024-01-23 18:41:54 -05:00
• 40b61c1719 fix the chinese character generation as same as PR #321 (#342) iLoveBug 2024-01-24 04:44:23 +08:00
• 21aa8038fb MLX LM version bump (#358) Awni Hannun 2024-01-23 09:05:57 -08:00
• 362e88a744 feat: move lora into mlx-lm (#337) Anchen 2024-01-23 08:44:37 -08:00
• 85c1ff8fd6 Add PLaMo-13B model as an LLM example (#303) Shunta Saito 2024-01-24 00:17:24 +09:00
• c45c2311bd Add colorized output option to generate script (#347) Ivan Fioravanti 2024-01-23 14:25:44 +01:00
• a445ac2895 Update docs with conda install option (#354) Sugato Ray 2024-01-23 00:14:48 -05:00
• 42672f5446 add an option to apply the tokenizer chat template (#338) Baptiste Canton 2024-01-23 04:52:42 +01:00
• 8022083979 feat(lora): add de-quantized support for fuse.py (#351) Anchen 2024-01-22 17:32:24 -08:00
• 30be4c4734 refactor(qwen): moving qwen into mlx-lm (#312) Anchen 2024-01-22 15:00:07 -08:00
• de15532da8 Feat: Bump isort version (#350) Nripesh Niketan 2024-01-21 18:35:15 +04:00
• 1415595409 chore(lora): support mixtral in lora example (#343) Anchen 2024-01-20 06:07:45 -08:00
• 527cea4027 chore: fix the convert.py script for weights are not sanitized and support quant for non-32 dimensions (#340) Anchen 2024-01-19 21:07:21 -08:00
• 61297f547b Missing requirements needed for convert script (#320) bojanbabic 2024-01-18 19:04:24 -08:00
• bcc9fc3581 two minor fixes (#335) Awni Hannun 2024-01-18 14:18:13 -08:00
• d8680a89f9 Add argument --save-every N to lora.py for saving model regularly (#310) Zheng Qu 2024-01-17 05:03:33 +01:00
• b4c20cc7f7 Stable Diffusion: Input image downsampling (#276) LeonEricsson 2024-01-16 22:45:00 +01:00
• 2ba5d3db14 Refactor activation function and loss calculation (#325) AtomicVar 2024-01-17 05:42:56 +08:00
• ce7b65e8c4 Fix import order of normalizing_flow (#326) AtomicVar 2024-01-17 00:45:55 +08:00
• 2287294723 fix mlx_lm generator for chinese (#321) someone 2024-01-16 23:13:33 +08:00
• b0870ed679 fix response + bump version (#319) Awni Hannun 2024-01-15 11:51:21 -08:00
• 195bec2fa3 feat(mlx_lm): add mixtral support in mlx_lm (#318) Anchen 2024-01-15 07:18:14 -08:00
• 19b6167d81 Normalizing flow example (#133) Siddharth Mishra-Sharma 2024-01-13 19:58:48 -05:00
• cd3cff0858 Phixtral (#290) Marcel Bischoff 2024-01-13 11:35:03 -05:00
• a39b735c3b chore(mlx-lm): update phi2 model args to sync with hf config format. (#311) Anchen 2024-01-13 07:51:45 -08:00
• 7575125d5d Added lora support for Phi-2 (#302) Yousif 2024-01-12 13:45:30 -08:00
• 3ac731dd4f Fix TypeError in whisper benchmark script (#306) Alexandre Boucaud 2024-01-12 22:07:15 +01:00
• ef93979973 Update model card uploaded with converted models (#309) Pedro Cuenca 2024-01-12 22:03:52 +01:00
• 1fa40067fe Change tuple type definitions to use Tuple (#308) Angelos Katharopoulos 2024-01-12 11:15:09 -08:00
• c1342b8e89 Use pip for mlx data with speech commands (#307) Awni Hannun 2024-01-12 11:06:33 -08:00
• c6440416a2 Mlx llm package (#301) Awni Hannun 2024-01-12 10:25:56 -08:00
• 2b61d9deb6 Updated CIFAR-10 ResNet example to use BatchNorm instead of LayerNorm (#257) Markus Enzweiler 2024-01-12 14:43:11 +01:00
• 6217d7acd0 Delete llms/hf_llm/models/.gitignore (#300) Anchen 2024-01-11 16:56:50 -08:00
• a2402116ae refactor(hf_llm): moving phi2 example into hf_llm (#293) Anchen 2024-01-11 12:29:12 -08:00
• e74889d0fa prompt parameter (#291) Anjor Kanekar 2024-01-11 14:04:57 +00:00
• 7380ebfb0d fix: undefined hf_path (#292) Anchen 2024-01-11 05:53:52 -08:00
• 047d4650c4 Add -local flag to llms/hf_llm/convert.py for reading source HF models from filesystem. (#260) Konstantin Kerekovski 2024-01-10 22:53:01 -05:00
• 80d18671ad [Lora] Fix generate (#282) Awni Hannun 2024-01-10 16:13:06 -08:00
• a2bc8426f2 Update txt2image.py (#285) Rishi Narang 2024-01-11 01:31:59 +08:00
• 2bbe9d3bd8 fix use of args in generate function (#284) Alwin Arrasyid 2024-01-10 23:09:21 +07:00
• 44f86092ea Fix Tokenizer save error. (#278) Vaibhav Srivastav 2024-01-10 19:19:32 +05:30
• 841c8f7b30 fix max tokens (#275) Awni Hannun 2024-01-09 21:41:12 -08:00
• 7cfda327fd fix(lora): tokenizer return incompatible mx array (#271) Anchen 2024-01-09 19:46:38 -08:00
• 7b258f33ac Move lora example to use the same model format / conversion as hf_llm (#252) Awni Hannun 2024-01-09 11:14:52 -08:00
• bbd7172eef Some fixes / cleanup for BERT example (#269) Awni Hannun 2024-01-09 08:44:51 -08:00
• 6759dfddf1 Fix SD image conversion (#266) Awni Hannun 2024-01-09 08:41:31 -08:00
• 6e6eff326e fix: use of undefined args in generate function in phi-2 example (#265) Alwin Arrasyid 2024-01-09 21:43:59 +07:00
• bb35e878cb [Whisper] Add load from Hub. (#255) Vaibhav Srivastav 2024-01-08 19:50:00 +05:30
• d4c3a9cb54 [Whisper] Add HF Hub upload option. (#254) Vaibhav Srivastav 2024-01-08 19:48:24 +05:30
• 6e5b0de4d3 refactor: make the phi2 example can be directly load the model from hf without convert needed (#253) Anchen 2024-01-08 06:01:23 -08:00
• 9742ad0f51 Update README.md (#248) Nino Risteski 2024-01-08 05:13:58 +01:00
• 485fb9ac0f quantize linear (#250) Awni Hannun 2024-01-07 18:48:59 -08:00
• 737b4c81a3 Update README.md (#251) Ikko Eltociear Ashimine 2024-01-08 04:35:39 +09:00
• bf9926489e [Whisper] Add word timestamps and confidence scores (#201) bofeng huang 2024-01-07 19:01:29 +01:00
• 25ebd36112 Fix typo in lora convert.py (#245) mc0ps 2024-01-07 06:30:30 -05:00
• b152d12d7b Update README.md (#243) Nino Risteski 2024-01-06 20:44:49 +01:00
• 758f05c09a refactor: merge deepseek coder example into hf_llm example (#234) Anchen 2024-01-06 07:53:46 -08:00
• cf0ad26a89 force fp16 for quantized models (#240) Awni Hannun 2024-01-05 21:29:15 -08:00
• 37856f70a8 add numpy as a requirement to run lora.py (#238) Lawrence Wu 2024-01-05 16:16:28 -08:00
• 37b41cec60 Qlora (#219) Awni Hannun 2024-01-04 21:05:59 -08:00
• 4fa659acbd Handle receiving 0 tokens gracefully (#231) Christian Bieniak 2024-01-05 14:14:13 +11:00
• 12c9bafbf5 Update README.md to fix --hf-model param call. (#229) Andy Peatling 2024-01-04 11:53:51 -08:00
• e14afb3e77 fix to use actual prompt (#227) Awni Hannun 2024-01-04 11:12:05 -08:00
• f95cf30a31 Fix upload to hub for HF LLMs conversion script. (#221) Vaibhav Srivastav 2024-01-04 19:36:05 +05:30
• a5d6d0436c Support Hugging Face models (#215) Awni Hannun 2024-01-03 15:13:26 -08:00
• 1d09c4fecd keep dtype on model conversion (#186) Daniel Strobusch 2024-01-02 20:20:29 +01:00
• 85258b2be7 make parameter naming consistent with other examples. (#214) Daniel Strobusch 2024-01-02 17:18:12 +01:00
• e632d7aaaa fix: deepseek coder tokenizer error (#211) Anchen 2024-01-02 01:10:37 +11:00
• ee3c44d231 chore: make the Deepseek example compatible with Yi models. (#205) Anchen 2023-12-31 01:11:33 +11:00
• 581a5733a1 [Whisper] Load customized MLX model & Quantization (#191) bofeng huang 2023-12-29 19:22:15 +01:00
• 1cdbf9e886 chore: fix the load quantization model for deepseek coder (#203) Anchen 2023-12-30 00:25:38 +11:00
• 31ddbd7806 add deepseek coder example (#172) Anchen 2023-12-29 16:42:22 +11:00
• 37fd2464dc Add an image2image example in the stable diffusion (#198) Angelos Katharopoulos 2023-12-28 18:31:45 -08:00
• 09566c7257 add speculative decoding example for llama (#149) Benjamin Anderson 2023-12-28 17:20:43 -06:00
• 07c163d9d9 [Whisper] Large-v3 requires 128 Mel frequency bins (#193) Dimo 2023-12-28 22:50:35 +01:00