Commit Graph

Select branches

Hide Pull Requests

main

#1

#10109

#10110

#10112

#10114

#10123

#10124

#10124

#10127

#10131

#10137

#10139

#10145

#10147

#10152

#10155

#10156

#10157

#10159

#10161

#10163

#10165

#10172

#10172

#10173

#10174

#10176

#10181

#10183

#10185

#10185

#10188

#10188

#10189

#10190

#10190

#10192

#10192

#10194

#10196

#10198

#10199

#10200

#10201

#10202

#10203

#10204

#10205

#10206

#10208

#10209

#10210

#10211

#10212

#10213

#10214

#10215

#10220

#10222

#10223

#10225

#10227

#10232

#10236

#10237

#10242

#10252

#10254

#10255

#10255

#10259

#10260

#10262

#10262

#10264

#10264

#10265

#10267

#10268

#10269

#10273

#10274

#10274

#10276

#10280

#10280

#10281

#10283

#10284

#10288

#10288

#10289

#10289

#10290

#10291

#10295

#10296

#10297

#10297

#10300

#10300

#10303

#10304

#10305

#10307

#10307

#10308

#10313

#10313

#1059

#11

#1186

#119

#1252

#1326

#1348

#1353

#1375

#1436

#145

#1454

#1486

#1525

#1544

#1553

#156

#158

#1624

#1689

#1690

#1695

#1699

#1700

#171

#179

#1796

#1800

#1802

#1861

#1864

#1868

#1918

#1932

#1946

#1947

#1953

#1954

#200

#2007

#2019

#2100

#2117

#213

#2163

#2194

#22

#2201

#221

#2226

#2262

#2264

#2266

#2283

#2285

#2319

#2350

#2411

#2423

#2426

#2435

#2445

#2462

#2469

#2474

#2514

#2519

#2525

#2531

#2568

#2570

#2572

#2575

#258

#26

#2608

#2683

#2689

#2730

#2739

#2743

#2746

#2764

#2766

#2830

#2845

#2849

#2872

#2903

#2905

#2919

#2944

#2945

#2963

#2967

#2993

#3004

#3046

#3053

#3057

#306

#3066

#307

#3083

#3103

#3103

#3158

#3159

#3160

#3161

#3201

#3226

#3254

#3256

#3261

#3263

#3267

#3275

#3276

#3287

#3288

#3291

#33

#3332

#3338

#3357

#3371

#3383

#3394

#3412

#3423

#3435

#3449

#3450

#3454

#3471

#3484

#3487

#3490

#3498

#3511

#3513

#3527

#3532

#356

#3578

#3584

#3588

#3596

#3601

#3604

#3651

#3654

#3655

#3661

#3683

#3692

#3702

#3741

#3746

#3748

#3755

#3756

#3785

#3792

#3794

#3799

#3804

#3812

#382

#3829

#3835

#387

#3876

#3921

#3923

#3925

#3930

#3941

#395

#3958

#3976

#3987

#4003

#4006

#4007

#4009

#4011

#4015

#4029

#4043

#4045

#4053

#4066

#4080

#4082

#4083

#4098

#4099

#4119

#4136

#4166

#4167

#4173

#4191

#4204

#4224

#4227

#4234

#4237

#4245

#4246

#4307

#4309

#4314

#4321

#4329

#4334

#434

#4342

#4347

#4348

#4352

#4355

#4377

#4382

#4409

#4417

#4445

#4446

#4461

#451

#4544

#4561

#4580

#4589

#4590

#4636

#4651

#4662

#4663

#4673

#4680

#4680

#4686

#4687

#4691

#4692

#4700

#4706

#4724

#4733

#4746

#4781

#479

#4793

#4804

#4821

#4822

#4877

#4878

#4892

#4939

#4950

#4957

#4961

#4970

#4995

#4996

#5010

#5019

#5032

#5037

#5068

#5072

#5095

#51

#5109

#511

#5111

#5112

#5115

#5118

#5156

#516

#5163

#5170

#5185

#5188

#5193

#5208

#5226

#5230

#5233

#5237

#5242

#5278

#5290

#5317

#5323

#5326

#5339

#5343

#5346

#5365

#5372

#5388

#5405

#5424

#5427

#5438

#5445

#5451

#5458

#5473

#5475

#5480

#5483

#5486

#5507

#5522

#5532

#5533

#5536

#5546

#5547

#5555

#5563

#5574

#5580

#5581

#5585

#5606

#5615

#5639

#5642

#5653

#5665

#5673

#5746

#5752

#5752

#5758

#5781

#5799

#5801

#5816

#5819

#5839

#5852

#5856

#5857

#5871

#5873

#5880

#5889

#5895

#5897

#5901

#5906

#5907

#5909

#5910

#5912

#5913

#5914

#5920

#5922

#5924

#5926

#5927

#5929

#5933

#596

#5970

#5971

#5973

#598

#5982

#5984

#599

#5990

#5993

#6010

#6022

#6046

#6052

#6065

#6078

#6083

#6098

#6103

#6120

#6121

#6123

#6124

#6125

#6126

#6127

#6128

#6129

#6137

#6138

#6140

#6141

#6151

#6152

#6156

#6157

#6160

#6170

#6175

#619

#6190

#6192

#6204

#6224

#6226

#6233

#6238

#6242

#6246

#6251

#6253

#6265

#6275

#629

#6310

#6313

#6317

#6334

#6359

#6362

#6363

#6364

#6365

#6367

#6368

#6369

#6379

#6384

#6388

#6395

#6396

#6401

#6416

#6418

#6420

#6426

#6430

#644

#6441

#6443

#6444

#6457

#6462

#6465

#6471

#6478

#6483

#6492

#6493

#6498

#6503

#6506

#651

#6512

#6513

#6514

#6515

#6524

#6527

#6528

#6542

#6547

#6564

#6565

#657

#6585

#6588

#6597

#6598

#6600

#6601

#6617

#6620

#6624

#6625

#6626

#6628

#6629

#6631

#6632

#6637

#6640

#6641

#6642

#6645

#6648

#6653

#6657

#6684

#6688

#6689

#6690

#6691

#6692

#6693

#6698

#6701

#6710

#6722

#6753

#6767

#6771

#6778

#6779

#678

#6786

#6787

#6788

#6796

#6797

#68

#6801

#6810

#6814

#6830

#6831

#6834

#6843

#6854

#6855

#6857

#6865

#6866

#6868

#6874

#6879

#6890

#6892

#6895

#6896

#6899

#6901

#6902

#6903

#6904

#6905

#6906

#6907

#6913

#6916

#6917

#6918

#6920

#6930

#6931

#6944

#6946

#6954

#6963

#6972

#6975

#6976

#6977

#6982

#6983

#6985

#6998

#7019

#7051

#7053

#7054

#7058

#7060

#7061

#7067

#7074

#7077

#7089

#7106

#7108

#7117

#7120

#7126

#7142

#7143

#7161

#7166

#7174

#7176

#7179

#7181

#7183

#7190

#7193

#7201

#7204

#7205

#7206

#7207

#7209

#7211

#7219

#7229

#7230

#7231

#7235

#7241

#7242

#7244

#7247

#7253

#7254

#7255

#7256

#7257

#7258

#7259

#7264

#7272

#7273

#7275

#7277

#7278

#7287

#7288

#7294

#7295

#7304

#7308

#7312

#7317

#7318

#7330

#7332

#7338

#7340

#7343

#7345

#7347

#7349

#7351

#7361

#7378

#7381

#7395

#7404

#741

#7413

#7419

#7420

#7432

#7436

#7437

#7440

#7441

#7442

#7445

#7448

#7449

#7453

#7455

#7456

#7462

#7466

#7469

#7471

#7481

#7500

#7505

#7509

#7519

#7523

#7530

#7537

#7546

#7553

#7564

#7566

#7567

#7570

#7573

#7576

#7578

#7594

#7609

#7611

#7612

#7623

#7625

#7635

#7638

#7639

#7644

#7645

#7646

#7647

#7654

#7655

#7657

#766

#7660

#7674

#7686

#7694

#7695

#7700

#7704

#7714

#7715

#7719

#7724

#7725

#7728

#7732

#7739

#7740

#7744

#7745

#7746

#7747

#7748

#7749

#7754

#7765

#7786

#7792

#7793

#7794

#7795

#7797

#7801

#7803

#7804

#7808

#7810

#7817

#7826

#7830

#7840

#7854

#786

#7867

#7870

#7872

#7875

#7879

#7883

#7885

#7887

#7910

#7911

#7912

#7913

#7923

#7924

#7928

#7945

#7946

#7958

#7962

#7964

#7966

#7974

#7988

#7992

#8000

#8015

#8039

#8042

#8050

#8051

#8057

#8067

#8077

#8078

#8095

#8099

#8101

#8103

#8108

#8109

#8110

#8124

#8125

#8128

#8129

#8130

#8156

#8159

#8161

#8162

#8167

#8176

#8178

#8179

#8180

#8181

#8183

#8195

#8196

#8197

#8201

#8202

#8203

#8215

#8220

#8227

#8235

#8245

#8248

#8249

#8258

#8264

#8270

#8276

#8286

#8288

#8291

#8293

#8298

#83

#8303

#8311

#8312

#8314

#8325

#8327

#8328

#8333

#8335

#8348

#8362

#8367

#8385

#8386

#8387

#8388

#8389

#8390

#8396

#84

#8403

#8414

#8421

#8422

#8423

#8432

#8433

#8438

#844

#8441

#8448

#8449

#8457

#8458

#8460

#8461

#8462

#8480

#8481

#8505

#8509

#8517

#8519

#8529

#8530

#8532

#8535

#8538

#8539

#8542

#8543

#8546

#8547

#8548

#8554

#8556

#8557

#8559

#8564

#8565

#8567

#8569

#8571

#8587

#86

#8614

#8623

#8627

#8637

#8651

#8680

#8685

#8689

#8721

#8722

#8731

#8736

#8739

#8750

#8752

#8762

#8770

#8773

#8774

#8776

#8783

#8784

#8787

#8788

#8795

#8812

#8813

#8818

#8823

#8826

#8827

#8829

#8839

#8842

#8845

#8851

#8861

#8863

#8866

#8869

#8875

#8876

#8887

#8899

#8906

#8917

#8930

#8960

#8961

#8962

#8970

#8972

#8975

#8976

#8978

#8985

#8992

#900

#9000

#9008

#9018

#9022

#9024

#9028

#9029

#9046

#9071

#9077

#9078

#9086

#9086

#9112

#9117

#9124

#9128

#9129

#9130

#9137

#9143

#9165

#9176

#9177

#9183

#9188

#9196

#9198

#9204

#9215

#9217

#9219

#9221

#9223

#9224

#9225

#9226

#9227

#9229

#9230

#9231

#9232

#9236

#9237

#9243

#9248

#9249

#9259

#9262

#9263

#9265

#9267

#9274

#9275

#9284

#9293

#9296

#9297

#9299

#9316

#9333

#9337

#9337

#9343

#9351

#9351

#9352

#9354

#9360

#9368

#9370

#9370

#9388

#9391

#9395

#9397

#9399

#9400

#9405

#9406

#9407

#9409

#9449

#9463

#9467

#9477

#9484

#9485

#9486

#9492

#9501

#9504

#9505

#9509

#9511

#9514

#9518

#9520

#9521

#9532

#9536

#9539

#9541

#9543

#9544

#9547

#9549

#9552

#9557

#9569

#9575

#9579

#9582

#9586

#9587

#9588

#9593

#9595

#9602

#9604

#9607

#9608

#9610

#9611

#9612

#9613

#9615

#9615

#9616

#9617

#9619

#9621

#9624

#9626

#9627

#9630

#9630

#9632

#9633

#9634

#9636

#9637

#9638

#9640

#9643

#9645

#9649

#9651

#9652

#9654

#9661

#9665

#9669

#9670

#9673

#9675

#9676

#9677

#9678

#9680

#9682

#9685

#9687

#9688

#9692

#9696

#9700

#9701

#9702

#9703

#9705

#9707

#9709

#9710

#9714

#9715

#9716

#9717

#9717

#9720

#9721

#9722

#9724

#9725

#9726

#9729

#9730

#9731

#9732

#9733

#9733

#9734

#9735

#9736

#9738

#9740

#9740

#9741

#9742

#9744

#9745

#9746

#9749

#975

#9750

#9751

#9752

#9754

#9773

#9867

v0.0.9

v0.1.0

v0.1.1

v0.1.2

v0.1.3

v0.1.4

v0.1.5

v0.1.6

v0.1.7

v0.1.8

v0.2.0

v0.2.1

v0.2.2

v0.3.0

v0.3.2

v0.3.3

v0.4.0

v0.5.0

v0.5.2

v0.5.3

v0.6.0

v0.6.1

v0.6.2

v0.6.3

v0.7.0

v0.7.1

v0.8.0

v0.8.1

v0.8.2

v0.8.3

v0.9.0

v0.9.1

v0.9.2

v0.9.3

v0.9.4

Mono Color

• f74d600497 fix flash shift short attention hiyouga 2023-10-09 17:54:48 +08:00
• 94fec9f50e fix webui args hiyouga 2023-10-09 17:13:57 +08:00
• e387a50475 fix shift short attention hiyouga 2023-10-09 17:07:46 +08:00
• 5c4248a29c update webui #1086 hiyouga 2023-10-09 14:50:14 +08:00
• f22886e2b6 fix #1097 hiyouga 2023-10-08 22:29:26 +08:00
• 33af3cbf37 add llamafy_qwen.py hiyouga 2023-10-08 22:05:36 +08:00
• 728dfb1be7 fix #1068 #1074 hiyouga 2023-09-28 14:39:16 +08:00
• e49f7f1afe fix bug in packed sft dataset hiyouga 2023-09-28 01:16:46 +08:00
• 21a454fa6c tiny fix hiyouga 2023-09-28 01:03:04 +08:00
• 22c6c27f78 tiny fix hiyouga 2023-09-28 01:02:11 +08:00
• aecbb43096 fix #1064 hiyouga 2023-09-28 00:53:29 +08:00
• fa53fd2db2 fix bug in pretraining hiyouga 2023-09-28 00:45:20 +08:00
• 1c150995ae fix layer norm dtype hiyouga 2023-09-28 00:25:55 +08:00
• 6c5d8f089e fix #1026 hiyouga 2023-09-27 22:57:09 +08:00
• dd623325e8 fix #424 hiyouga 2023-09-27 22:49:43 +08:00
• e8a375c8f2 fix #1032 hiyouga 2023-09-27 22:42:16 +08:00
• 386d85ae72 refactor finetuning Args hiyouga 2023-09-27 22:28:06 +08:00
• ebb3901b05 update readme hiyouga 2023-09-27 21:57:47 +08:00
• 20130b486c support LongLoRA hiyouga 2023-09-27 21:55:50 +08:00
• 73c48d0463 add CMMLU, update eval script hiyouga 2023-09-23 21:10:17 +08:00
• f7cecd20e3 update evaluate hiyouga 2023-09-23 11:55:31 +08:00
• 2bc64a7636 move file hiyouga 2023-09-23 11:52:12 +08:00
• 9564ddbb48 shuffle few shot examples hiyouga 2023-09-23 00:53:20 +08:00
• 28062c71b5 fix MMLU hiyouga 2023-09-23 00:42:23 +08:00
• 35d1921081 add MMLU and C-Eval script hiyouga 2023-09-23 00:34:17 +08:00
• 4fbdf18c70 fix #1000 hiyouga 2023-09-22 15:00:48 +08:00
• 5e07ab01f0 update readme hiyouga 2023-09-22 14:34:13 +08:00
• fac465a21e fix webui hiyouga 2023-09-21 19:55:38 +08:00
• e145a2ce0c tiny fix hiyouga 2023-09-21 19:52:06 +08:00
• dc68c313ee fix #944 hiyouga 2023-09-21 19:51:02 +08:00
• 95c0d9ab24 tiny fix hiyouga 2023-09-21 15:25:29 +08:00
• 46a718f339 Merge pull request #975 from statelesshz/npu-support hoshi-hiyouga 2023-09-20 14:56:50 +08:00
• 496ba46960 support export model on Ascend NPU statelesshz 2023-09-20 10:15:59 +08:00
• 43ae0aca1d fix webui hiyouga 2023-09-19 18:35:21 +08:00
• b8574c1b82 fix error info hiyouga 2023-09-19 18:30:23 +08:00
• 32f8b1082b add tests.cal_flops.py hiyouga 2023-09-16 23:40:41 +08:00
• 6443fef31a update readme hiyouga 2023-09-16 17:33:01 +08:00
• 14c3795a7d fix #913 hiyouga 2023-09-15 20:58:28 +08:00
• 3d9e2de573 fix #896 hiyouga 2023-09-14 18:37:34 +08:00
• 0ca36a0f8d fix #887 hiyouga 2023-09-14 17:56:58 +08:00
• 3e5555502a Update utils.py mmbwf 2023-09-14 15:38:04 +08:00
• fbf5b5e0a9 add MathInstruct dataset hiyouga 2023-09-13 22:30:14 +08:00
• 3305e66f8c fix ppo save model hiyouga 2023-09-12 16:25:29 +08:00
• e19a44c12b fix #762 #814 hiyouga 2023-09-12 16:10:10 +08:00
• 8b0e6b9d1b tiny fix hiyouga 2023-09-11 18:27:08 +08:00
• f3e638ac6a Release v0.1.8 v0.1.8 hiyouga 2023-09-11 17:31:34 +08:00
• 42e0b30476 update flashattn, fix ppo save model hiyouga 2023-09-11 17:25:36 +08:00
• a09a7b650d remove PeftTrainer hiyouga 2023-09-10 22:23:23 +08:00
• 332d7bbd56 truncate readme hiyouga 2023-09-10 21:04:20 +08:00
• d3b6fece71 update readme hiyouga 2023-09-10 21:01:20 +08:00
• 9d963b82de update readme hiyouga 2023-09-10 20:52:21 +08:00
• a402161631 support FlashAttention2 hiyouga 2023-09-10 20:43:56 +08:00
• b481ad58e6 fix #850 hiyouga 2023-09-10 14:22:03 +08:00
• f91c5f2638 fix lora target hiyouga 2023-09-09 17:04:45 +08:00
• 7143c551ab support lora target auto find hiyouga 2023-09-09 15:38:37 +08:00
• 50e93392dd fix chatglm2 tokenizer hiyouga 2023-09-09 13:50:29 +08:00
• 9f83e93839 add baichuan2 convert script hiyouga 2023-09-08 22:59:41 +08:00
• 692b132dbf fix bug in DPO data collator hiyouga 2023-09-08 20:45:07 +08:00
• e70b3e8947 fix #761 hiyouga 2023-09-08 20:22:18 +08:00
• 612d97db6f change to right-padding, update reward score #803 hiyouga 2023-09-08 20:04:31 +08:00
• bb1b67c076 fix chatglm template hiyouga 2023-09-08 14:45:58 +08:00
• 5a75c31caa update requirements hiyouga 2023-09-07 19:26:25 +08:00
• 8b9210286b fix #818 hiyouga 2023-09-07 19:19:53 +08:00
• b5acec34f7 add deepspeed check in PPO training hiyouga 2023-09-07 19:12:40 +08:00
• 86d835878c fix #809 hiyouga 2023-09-07 19:04:32 +08:00
• eae7b331d3 fix baichuan templates hiyouga 2023-09-07 18:54:14 +08:00
• ed89e29bcc update baichuan2 template hiyouga 2023-09-06 21:43:06 +08:00
• c2b1886aff add Baichuan2 models hiyouga 2023-09-06 18:40:11 +08:00
• 218f36bca5 add Baichuan2 models hiyouga 2023-09-06 18:36:04 +08:00
• b91fc1f5b3 Merge pull request #786 from kinghuin/patch-1 hoshi-hiyouga 2023-09-05 10:49:34 +08:00
• 2a22bf9c15 fix utils.py bug Q 2023-09-05 10:38:01 +08:00
• 62e2037125 fix #763 hiyouga 2023-09-01 23:13:05 +08:00
• e5b72c6a77 refactor dataset_attr, add eos in pt, fix #757 hiyouga 2023-09-01 19:00:45 +08:00
• 93be211f80 Merge pull request #741 from hiyouga/feature-addDatasetCheck codingma 2023-08-31 20:57:36 +08:00
• 9ae3fb4ced update llama2 template codemayq 2023-08-30 16:23:56 +08:00
• f641075789 add dataset stage check codemayq 2023-08-30 16:23:08 +08:00
• f7658db1b6 Merge pull request #651 from hiyouga/feature-dataset_stage codingma 2023-08-28 16:03:45 +08:00
• b869bc1a20 add ad gen dataset codemayq 2023-08-27 20:35:32 +08:00
• a72d756d77 add text format dataset preview in webui codemayq 2023-08-24 19:45:36 +08:00
• d3fd8f89b8 add stage in DatasetAttr codemayq 2023-08-23 20:54:53 +08:00
• 180a05a446 fix import error hiyouga 2023-08-23 20:45:03 +08:00
• eb9ac9ee1f fix #649 hiyouga 2023-08-23 20:21:15 +08:00
• a6662b73f5 add readme for dataset codemayq 2023-08-23 19:55:45 +08:00
• cbc7db3478 add dataset stage and filter dataset when stage chosen in webui codemayq 2023-08-23 18:54:23 +08:00
• 4606340f0f fix webui hiyouga 2023-08-23 11:03:35 +08:00
• d4b4ccd597 Merge pull request #644 from hiyouga/fix-quantization_bit hoshi-hiyouga 2023-08-23 10:45:45 +08:00
• 9c3f4e3a37 fix quantization bit is "" codemayq 2023-08-23 10:08:17 +08:00
• 440e00d8f9 fix quantization is "" codemayq 2023-08-23 10:04:03 +08:00
• 6310613699 update template hiyouga 2023-08-22 19:46:09 +08:00
• f55907dbea Merge pull request #629 from panpan0000/main hoshi-hiyouga 2023-08-22 13:41:44 +08:00
• 5cac87d317 add rm dataset explanation Peter Pan 2023-08-22 01:30:57 -04:00
• 9c0622de13 Merge pull request #619 from hiyouga/feature-templateTest hoshi-hiyouga 2023-08-21 20:56:34 +08:00
• 37b93c8b71 add template encode test codemayq 2023-08-21 20:51:24 +08:00
• d6be98cda6 fix #617 hiyouga 2023-08-21 18:16:11 +08:00
• 4d128acc17 fix #608 hiyouga 2023-08-21 17:49:36 +08:00
• 516df9ecce fix baichuan template for training #597 #616 hiyouga 2023-08-21 17:41:51 +08:00
• 8eec1d50e1 fix #595 hiyouga 2023-08-20 16:40:00 +08:00
• cfb096d43a Merge pull request #596 from beat4ocean/beat hoshi-hiyouga 2023-08-20 16:37:40 +08:00
• 713fa28804 fix KeyError: 'lang' bug beat4ocean 2023-08-20 15:32:36 +08:00
• 5549f35939 fix ppo trainer #551 hiyouga 2023-08-20 14:07:11 +08:00