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

• e52c128d11 Use model.safetensors with Whisper (#1399) main Anthony 2025-12-15 15:17:08 +01:00
• 7ddca42f4d switch to github actions (#1394) Awni Hannun 2025-11-20 09:57:43 -08:00
• 21a4d4cdab Update whisper command line help mentioning --word-timestamps (#1390) Armin Stross-Radschinski 2025-10-07 20:19:46 +02:00
• 8e4391ca21 whisper nits (#1388) Awni Hannun 2025-09-03 13:18:50 -07:00
• c1af8c46bd version (#1387) Awni Hannun 2025-08-29 08:03:52 -07:00
• f143957a06 switch quantized and non-quantized to be correct (#1385) Awni Hannun 2025-08-29 07:53:44 -07:00
• cfc5d25acd fix temperature based sampling (#1386) Awni Hannun 2025-08-29 07:53:37 -07:00
• 4b2a0df237 adding wwdc25 samples (#1370) Shashank 2025-06-10 10:23:25 -07:00
• 977cd30242 Update lora README.md (#1365) Denrei Keith 2025-05-01 21:00:14 +08:00
• 4c9f9f9be7 Made llama and mistral files mypy compatible (#1359) Param Thakkar 2025-04-24 02:53:46 +05:30
• c52cc748f8 Distributed FLUX (#1325) Angelos Katharopoulos 2025-03-24 22:16:48 -07:00
• c243370044 remove mlx lm (#1353) Awni Hannun 2025-03-18 18:47:55 -07:00
• 7ca05d2e51 LoRa/README.md should be --hf-path instead of --hf-repo (#1350) Tingzhen 2025-03-16 23:02:52 -04:00
• d9e1d9c0ef mlx-lm move notice (#1346) Awni Hannun 2025-03-16 15:14:28 -07:00
• 2fce02acd8 Add support for Gemma3 (#1336) Prince Canuma 2025-03-13 16:14:25 +01:00
• 3e5baf583b Make sure to use UTF-8 when loading tokenizer.json (#1340) Mirko Nasato 2025-03-13 02:17:14 +00:00
• 4c3df00162 make_sampler creates sampler chain with all sampling parameters (#1330) Neil Mehta 2025-03-11 16:37:35 -04:00
• d2e02b3aae fix mixed quant option (#1326) Awni Hannun 2025-03-07 08:35:48 -08:00
• 595f5da146 remove lm head if unused (#1324) Awni Hannun 2025-03-06 15:35:47 -08:00
• 877d2a345b Change DEFAULT_SEED to None for stochastic generation by default (#1323) cavit99 2025-03-06 14:49:35 +00:00
• 32d10036de fix flaky test (#1322) Awni Hannun 2025-03-05 14:00:09 -08:00
• e150621095 Adding multiple optimizers to mlx lm (#1315) Gökdeniz Gülmez 2025-03-05 22:54:54 +01:00
• 56d2db23e1 adding OLMoE architecture (#1321) Gökdeniz Gülmez 2025-03-05 22:46:06 +01:00
• e7267d30f8 Distributed support cifar (#1301) Angelos Katharopoulos 2025-03-05 13:33:15 -08:00
• f621218ff5 Tool use example (#1316) Awni Hannun 2025-03-04 13:53:20 -08:00
• 65aa2ec849 use a bool mask for attention (#1319) Awni Hannun 2025-03-04 12:47:32 -08:00
• 1bc3476a46 chore(lora): Add real-time log buffering fix for nohup execution (#1311) Pierre-Louis 2025-03-03 09:12:33 -05:00
• 269faa5fa4 Fix plamo2 model to use rms_norm (#1308) Shunta Saito 2025-03-03 23:12:02 +09:00
• 845cd8c01e support kimi + more options in chat mode (#1312) Awni Hannun 2025-02-28 11:33:18 -08:00
• b2108a0de6 Allow mask prompt in config (#1314) Awni Hannun 2025-02-28 11:33:04 -08:00
• eb73549631 Generate: Support Prefill Response (#1299) madroid 2025-02-27 23:44:00 +08:00
• 00a7379070 Fixes for phi4 mini (#1305) Awni Hannun 2025-02-26 16:21:54 -08:00
• 0f240a4c7e Use max tokens from options in mlx_lm evaluate (#1302) Awni Hannun 2025-02-26 15:46:16 -08:00
• 56e60ad5a6 fix manage for new transformers (#1304) Awni Hannun 2025-02-26 15:44:57 -08:00
• b7f742ef56 Mixed quant recipes (#1300) Pedro Cuenca 2025-02-26 20:32:36 +01:00
• c37e26a1a3 Add plamo-2-1b model (#1283) Shunta Saito 2025-02-25 12:24:43 +09:00
• 09b641aaa7 Fix FutureWarning in torch.load by setting weights_only=True (#1295) Usama Ahmed 2025-02-22 17:08:54 +03:00
• 3d793ecf68 Fix logits processor bugs with spec dec (#1291) Awni Hannun 2025-02-20 15:55:55 -08:00
• 85669451d0 Fix num layers in fine tune (#1294) Awni Hannun 2025-02-20 13:32:01 -08:00
• 1cbf5cdac7 use more standard window strategy (#1287) Awni Hannun 2025-02-19 06:22:51 -08:00
• 96bf37008e Update README.md to include how to set temperature (#1280) Matthias Neumayer 2025-02-14 04:32:56 +01:00
• 7b07b14e67 add logits processor to spec gen (#1260) Awni Hannun 2025-02-13 19:19:53 -08:00
• ec30dc3538 hunyuan finetune (#1270) Awni Hannun 2025-02-11 16:49:35 -08:00
• 42413c5d85 fix lora timings after validation (#1278) Awni Hannun 2025-02-11 16:48:55 -08:00
• f8cbf159e0 fix sharding for more even number of layers (#1276) Awni Hannun 2025-02-11 16:26:59 -08:00
• e879ea70e1 fix generation evaluations (#1277) Awni Hannun 2025-02-11 16:10:30 -08:00
• 3d677f0870 Add "from_draft" to GenerationResponse (#1272) Matt Clayton 2025-02-11 18:41:02 -05:00
• bded1a8fcd fix looping in whisper (#1273) Awni Hannun 2025-02-10 13:04:35 -08:00
• 5865899c81 Completion only fine-tuning of instruction models with collections of HF datasets (#1103) Chime Ogbuji 2025-02-09 23:12:34 -05:00
• 1ced1b00ca rm temp argument (#1267) Sri Harsha Pamu 2025-02-09 11:39:11 -08:00
• f58c7de901 Some improvements to speedup alignment computation in MLX Whisper (#1259) Awni Hannun 2025-02-08 15:47:00 -08:00
• 1503bd4f55 support hunyuan 7b (#1263) Awni Hannun 2025-02-08 15:46:47 -08:00
• 31611b62d7 Add IBM granite model (#1265) Awni Hannun 2025-02-08 15:46:15 -08:00
• 6120a5f376 Faster DSv2/3 expert score computation (#1257) Awni Hannun 2025-02-07 10:24:57 -08:00
• 52c41b5b5a Fix prompt cache for models without chat template (#1250) Awni Hannun 2025-02-06 11:10:58 -08:00
• 747c08e202 Chore: pre-commit bump (#1253) Nripesh Niketan 2025-02-06 17:06:31 +00:00
• 65b792d7c0 fix lazy load distributed-layers Awni Hannun 2025-01-14 13:14:48 -08:00
• 617f9289b9 Make the chat distributed Angelos Katharopoulos 2024-11-05 13:09:34 -08:00
• 026362e0f8 Remove async eval and add sequential load Angelos Katharopoulos 2024-11-05 13:04:07 -08:00
• a0ce0594f6 Temporarily remove async_eval Angelos Katharopoulos 2024-08-29 10:33:43 -07:00
• d77840207c Start distributed inference for llama models Angelos Katharopoulos 2024-07-15 13:24:50 -07:00
• e2e5478da5 READMEs: fix typo in link, minor update. (#1246) Pedro Cuenca 2025-02-04 20:52:32 +01:00
• 21d0ab6e8a fix deepseek sharding (#1242) Awni Hannun 2025-02-03 16:59:50 -08:00
• 0989c073b0 Optimizations for mamba1 (#1213) Gökdeniz Gülmez 2025-02-03 22:36:08 +01:00
• d9924d08d1 Fix no validation in lora (#1241) Awni Hannun 2025-02-03 09:55:24 -08:00
• 9c2ef38d4d only download local shard (#1240) Awni Hannun 2025-02-02 13:58:44 -08:00
• e8afb59de4 better overflow correction (#1229) Awni Hannun 2025-01-28 14:37:30 -08:00
• 7a83077cd7 chore(mlx-lm): support text type content in messages (#1225) Anchen 2025-01-28 12:13:50 +11:00
• f44a52e2dc batched min p and fix spec gen sampling (#1222) Awni Hannun 2025-01-27 15:40:31 -08:00
• 77faa14ba4 adding support for kyutai's helium (#1208) Gökdeniz Gülmez 2025-01-26 16:19:07 +01:00
• f787c08585 comments dist-eval Alex Barron 2025-01-23 06:36:31 -08:00
• d5f49d65b9 ordering Alex Barron 2024-12-19 00:08:28 -08:00
• 4385363c0f distributed evaluate Alex Barron 2024-12-18 22:12:08 -08:00
• 9a3ddc3e65 some fixes for pipeline parallel deep seek r1 (#1216) Awni Hannun 2025-01-21 19:40:29 -08:00
• df1406735b Fix dataset variable name, in datasets.py (#1212) Victor Nogueira 2025-01-21 23:12:43 +01:00
• 07f88f8057 fix(lora): add back store_true default args (#1205) Jarrett 2025-01-16 12:15:42 -07:00
• 50f0a7f6d9 add internlm3 (#1206) Awni Hannun 2025-01-15 14:55:41 -08:00
• 6ae6c72c2e reduction moved to CPU in case of distributed training (#1200) Ivan Fioravanti 2025-01-15 02:20:42 +01:00
• b9eff0d744 Improve printing for FLUX distributed training flux-dist-improv Angelos Katharopoulos 2025-01-13 22:32:35 -08:00
• c117af83b8 fix gpt bigcode (#1204) Awni Hannun 2025-01-13 10:22:32 -08:00
• 0228c46434 Custom local dataset features (#1085) Chime Ogbuji 2025-01-13 13:01:18 -05:00
• bf2da36fc6 Fix Cohere2: mask shape error (long context) (#1202) Prince Canuma 2025-01-12 21:58:08 +01:00
• 514502da22 Support snapshot_download for ModelScope (#1194) Xingjun.Wang 2025-01-11 07:29:34 +08:00
• 93c5cfd781 Add a speculative decoding generator (#1155) Awni Hannun 2025-01-10 15:27:08 -08:00
• 5cae0a60e6 deepseek v3 model with pipeline parallelism (#1191) Awni Hannun 2025-01-09 15:55:53 -08:00
• 40b88eff48 fix(lora): config yaml & arg default merge bug (#1196) Jarrett 2025-01-09 12:33:54 -07:00
• b8f0cacfa8 Use upload_large_folder (#1193) Pedro Cuenca 2025-01-07 18:18:31 +01:00
• 9183fe8b6d fix (#1192) Awni Hannun 2025-01-06 10:12:07 -08:00
• f2619f507c Add support for fewshot and apply chat template lm_eval functionality (#1180) Chime Ogbuji 2025-01-06 10:58:43 -05:00
• 25ec2d8c44 Change the eos-token argument for mlx_lm.generate (#1176) Angelos Katharopoulos 2025-01-05 22:26:05 -08:00
• c4833a2f55 fix encoding with special tokens + chat template (#1189) Awni Hannun 2025-01-03 10:50:59 -08:00
• 3a58c36109 Improvements to mlx_lm.manage (#1178) Ivan Fioravanti 2025-01-01 16:25:57 +01:00
• ae53ed9090 add TesseraQ rounding awq-tq Alex Barron 2024-12-19 19:35:26 -08:00
• fc81342afe remove comment awq Alex Barron 2024-12-19 19:14:02 -08:00
• 77d75f3ccc Add learned AWQ quantization Alex Barron 2024-12-19 19:13:22 -08:00
• d4ef909d4a Length masking for batch inputs (#1173) Alex Barron 2024-12-18 19:43:52 -08:00
• db109184b7 Fix no template prompt + top_k sampling (#1166) Awni Hannun 2024-12-18 18:46:50 -08:00
• bc08025f41 Add optional quantization types packed-quants Angelos Katharopoulos 2024-12-17 22:24:41 -08:00
• 845efddc8c Fix decoding manually added tokens (#1164) Billel Mokeddem 2024-12-17 21:54:29 +04:00
• dfa4dd6c93 Add support for cohere2 (#1157) Prince Canuma 2024-12-16 17:01:03 +01:00