You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+2-1Lines changed: 2 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -65,7 +65,7 @@ You can contact us and communicate with us by adding our group:
65
65
-**Quantization Training**: Supports training quantized models like BNB, AWQ, GPTQ, AQLM, HQQ, EETQ.
66
66
- 🍊 **RLHF Training**: Supports human alignment training methods such as DPO, GRPO, RM, PPO, GKD, KTO, CPO, SimPO, ORPO for both pure text and multi-modal large models.
67
67
- 🍓 **Multi-Modal Training**: Supports training on different modalities like images, videos, and audio, for tasks like VQA, captioning, OCR, and grounding.
68
-
- 🥥 **Megatron Parallelism**: Supports accelerating CPT/SFT/DPO/KTO/RM using Megatron parallelism techniques, currently compatible with 200+ pure text large models, 100+ multi-modal large models.
68
+
- 🥥 **Megatron Parallelism**: Supports accelerating CPT/SFT/GRPO/DPO/KTO/RM using Megatron parallelism techniques, currently compatible with 200+ pure text large models, 100+ multi-modal large models.
69
69
-**Interface Training**: Provides capabilities for training, inference, evaluation, quantization through an interface, completing the whole large model pipeline.
70
70
-**Plugin and Extension**: Supports custom model and dataset extensions, as well as customization of components like loss, metric, trainer, loss-scale, callback, optimizer.
71
71
- 🍉 **Toolbox Capabilities**: Offers not only training support for large models and multi-modal large models but also covers the entire process of inference, evaluation, quantization, and deployment.
@@ -75,6 +75,7 @@ You can contact us and communicate with us by adding our group:
75
75
76
76
77
77
## 🎉 News
78
+
- 🎁 2025.11.14: Megatron GRPO is now available! Check out the [docs](./docs/source_en/Megatron-SWIFT/GRPO.md) and [examples](examples/megatron/grpo).
78
79
- 🎁 2025.11.04: Support for [Mcore-Bridge](docs/source_en/Megatron-SWIFT/Mcore-Bridge.md), making Megatron training as simple and easy to use as transformers.
79
80
- 🎁 2025.10.28: Ray [here](docs/source_en/Instruction/Ray.md).
80
81
- 🎁 2025.10.28: Support [use yaml](examples/yaml) to configure command line parameters.
- Side: [Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks](https://arxiv.org/abs/1912.13503)
18
-
- Res-Tuning: [Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone](https://arxiv.org/abs/2310.19859) < [arXiv](https://arxiv.org/abs/2310.19859) | [Project Page](https://res-tuning.github.io/) | [Usage](ResTuning.md)>
18
+
- Res-Tuning: [Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone](https://arxiv.org/abs/2310.19859) < [arXiv](https://arxiv.org/abs/2310.19859) | [Project Page](https://res-tuning.github.io/) >
0 commit comments