New Features:

1. Support for RLHF with multimodal models, including DPO, ORPO, SIMPO, and CPO
2. SWIFT infer, SWIFT deploy support using lmdeploy for inference acceleration.
3. Support the use of Megatron for performing PT and SFT on the Qwen2 series models.
4. Support the grounding task for InternVL2/Qwen-VL-Chat models

New Models:

1. mistral-nemo series, mistral-large
2. llama3.1 series

New Datasets:

1. sa1b-dense-caption, sa1b-paired-caption
2. rlaif-v
3. zhihu-kol, zhihu-kol-filtered

What's Changed

• Support api key by @Jintao-Huang in https://github.com/modelscope/swift/pull/1452
• Support mistral nemo series models by @tastelikefeet in https://github.com/modelscope/swift/pull/1454
• fix minicpm-v2.5 lora_target_modules by @Jintao-Huang in https://github.com/modelscope/swift/pull/1455
• Add two datasets by @tastelikefeet in https://github.com/modelscope/swift/pull/1459
• Update trl dependency version by @hjh0119 in https://github.com/modelscope/swift/pull/1463
• fix bugs by @Jintao-Huang in https://github.com/modelscope/swift/pull/1464
• fix yi1.5 by @Jintao-Huang in https://github.com/modelscope/swift/pull/1465
• Fix yi1.5 by @Jintao-Huang in https://github.com/modelscope/swift/pull/1467
• add activate and deactivate for part tuner by @tastelikefeet in https://github.com/modelscope/swift/pull/1470
• support llama3.1 by @Jintao-Huang in https://github.com/modelscope/swift/pull/1475
• support megatron by @Jintao-Huang in https://github.com/modelscope/swift/pull/1365
• fix megatron by @Jintao-Huang in https://github.com/modelscope/swift/pull/1476
• Support internvl2 grounding by @tastelikefeet in https://github.com/modelscope/swift/pull/1473
• update doc by @tastelikefeet in https://github.com/modelscope/swift/pull/1477
• Support alignment algorithm for vision MLLM by @hjh0119 in https://github.com/modelscope/swift/pull/1474
• fix doc by @hjh0119 in https://github.com/modelscope/swift/pull/1481
• Fix visual cpo by @hjh0119 in https://github.com/modelscope/swift/pull/1482
• support llama3.1-quant by @Jintao-Huang in https://github.com/modelscope/swift/pull/1478
• fix part tuner by @tastelikefeet in https://github.com/modelscope/swift/pull/1483
• fix import by @tastelikefeet in https://github.com/modelscope/swift/pull/1488
• Fix GLM4V by @tastelikefeet in https://github.com/modelscope/swift/pull/1490
• support mistral large by @Jintao-Huang in https://github.com/modelscope/swift/pull/1485
• fix resume_only_model & zero3 & full by @Jintao-Huang in https://github.com/modelscope/swift/pull/1497
• Fix resume_from_checkpoint & full by @Jintao-Huang in https://github.com/modelscope/swift/pull/1498
• fix part tuner by @tastelikefeet in https://github.com/modelscope/swift/pull/1495
• fix cogvlm2-video by @Jintao-Huang in https://github.com/modelscope/swift/pull/1500
• [TorchAcc] add script for qwen2 in torchacc by @Zhikaiiii in https://github.com/modelscope/swift/pull/1492
• Fix CI by @tastelikefeet in https://github.com/modelscope/swift/pull/1501
• fix vlm template by @Jintao-Huang in https://github.com/modelscope/swift/pull/1503
• fix internvl-4b by @Jintao-Huang in https://github.com/modelscope/swift/pull/1505
• support zero3 & freeze by @Jintao-Huang in https://github.com/modelscope/swift/pull/1508
• fix part mix with lora by @tastelikefeet in https://github.com/modelscope/swift/pull/1509
• fix docs by @Jintao-Huang in https://github.com/modelscope/swift/pull/1511
• Update README.md by @ArtificialZeng in https://github.com/modelscope/swift/pull/1516
• fix kto custom data by @hjh0119 in https://github.com/modelscope/swift/pull/1515
• Fix KTO doc by @hjh0119 in https://github.com/modelscope/swift/pull/1517
• Rescale image by @tastelikefeet in https://github.com/modelscope/swift/pull/1512
• fix pretrain dataset by @Jintao-Huang in https://github.com/modelscope/swift/pull/1518
• fix deepseek-vl template by @Jintao-Huang in https://github.com/modelscope/swift/pull/1521
• Support exporting of llama3.1, and awq-batch-size by @tastelikefeet in https://github.com/modelscope/swift/pull/1522
• support lmdeploy & vlm by @Jintao-Huang in https://github.com/modelscope/swift/pull/1364
• fix tf 4.43 llava by @tastelikefeet in https://github.com/modelscope/swift/pull/1525
• fix llamapro by @tastelikefeet in https://github.com/modelscope/swift/pull/1527
• fix template & docs by @Jintao-Huang in https://github.com/modelscope/swift/pull/1529
• fix lmdeploy & vlm by @Jintao-Huang in https://github.com/modelscope/swift/pull/1530
• update doc by @tastelikefeet in https://github.com/modelscope/swift/pull/1531
• fix lmdeploy & minicpm-v-2.5 by @Jintao-Huang in https://github.com/modelscope/swift/pull/1534
• fix internvl-phi3 batch infer by @hjh0119 in https://github.com/modelscope/swift/pull/1539
• Support SA1B series datasets by @tastelikefeet in https://github.com/modelscope/swift/pull/1542
• fix bug in _prepare_inputs by @guihonghao in https://github.com/modelscope/swift/pull/1543
• Support lmdeploy infer deploy by @Jintao-Huang in https://github.com/modelscope/swift/pull/1541
• add lmdeploy link by @Jintao-Huang in https://github.com/modelscope/swift/pull/1545
• support lmdeploy & app-ui by @Jintao-Huang in https://github.com/modelscope/swift/pull/1546
• fix lmdeploy bug by @Jintao-Huang in https://github.com/modelscope/swift/pull/1550
• support more models by @Jintao-Huang in https://github.com/modelscope/swift/pull/1552
• fix multi node by @tastelikefeet in https://github.com/modelscope/swift/pull/1554
• support lmdeploy awq by @Jintao-Huang in https://github.com/modelscope/swift/pull/1555
• support quant_policy by @Jintao-Huang in https://github.com/modelscope/swift/pull/1556
• fix xcomposer lora by @Jintao-Huang in https://github.com/modelscope/swift/pull/1559
• Update docs by @Jintao-Huang in https://github.com/modelscope/swift/pull/1558
• fix minicpm-v by @Jintao-Huang in https://github.com/modelscope/swift/pull/1562
• add result_dir paramerter to InferArgument & fix a minor bug by @starxhong in https://github.com/modelscope/swift/pull/1561
• fix some bugs in dpo by @hjh0119 in https://github.com/modelscope/swift/pull/1565
• Fix bugs 0801 by @Jintao-Huang in https://github.com/modelscope/swift/pull/1566
• fix dataset copy by @Jintao-Huang in https://github.com/modelscope/swift/pull/1569
• fix qwen-vl-merged lmdeploy by @Jintao-Huang in https://github.com/modelscope/swift/pull/1572

New Contributors

• @ArtificialZeng made their first contribution in https://github.com/modelscope/swift/pull/1516
• @guihonghao made their first contribution in https://github.com/modelscope/swift/pull/1543

Full Changelog: https://github.com/modelscope/swift/compare/v2.2.3...v2.2.5