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: docs/source_en/BestPractices/Qwen3-Best-Practice.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -332,7 +332,7 @@ swift rlhf \
332
332
333
333
Best practice reference for single-node 8xH20 LoRA training with Qwen3-235B-A22B-Instruct-250718: https://github.com/modelscope/ms-swift/pull/5033.
334
334
335
-
ms-swift introduces Megatron parallelism techniques to accelerate CPT/SFT/DPO/KTO for large models. Supported models can be found in the [Supported Models and Datasets Document](../Instruction/Supported-models-and-datasets.md).
335
+
ms-swift introduces Megatron parallelism techniques to accelerate CPT/SFT/DPO/KTO/RM for large models. Supported models can be found in the [Supported Models and Datasets Document](../Instruction/Supported-models-and-datasets.md).
336
336
337
337
For environment setup and conversion between HF and MCore model weights, refer to the [Megatron-SWIFT Training Documentation](../Megatron-SWIFT/Quick-start.md).
Copy file name to clipboardExpand all lines: docs/source_en/Customization/Custom-dataset.md
+1Lines changed: 1 addition & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -197,6 +197,7 @@ Supervised Fine-tuning:
197
197
- videos: video, videos.
198
198
- audios: audio, audios.
199
199
- If you need to pass base64 data instead of file paths, here are sample examples: `"videos": ['data:video/mp4;base64,{base64_encoded}']`, `"images": ['data:image/jpg;base64,{base64_encoded}']`.
200
+
- If you wish to directly pass in video frames instead of a video file, you can use the following format (requires `ms-swift>=3.8.3`): `"videos": [["/xxx/x.png", "/xxx/y.png"], ["/xxx/a.png", "/xxx/b.png", "/xxx/c.png"]]`. This format is supported only by certain models, including Qwen2/2.5/3-VL, Qwen2.5/3-Omni, and their derivative models.
200
201
201
202
The data format for RLHF and sequence classification of multimodal models can reference the format of pure text large models, with additional fields such as `images` added on top of that.
Copy file name to clipboardExpand all lines: docs/source_en/GetStarted/Quick-start.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -10,7 +10,7 @@ ms-swift is a comprehensive training and deployment framework for large language
10
10
- Quantization Training: Provides training for quantized models like BNB, AWQ, GPTQ, AQLM, HQQ, EETQ.
11
11
- 🍊 RLHF Training: Supports human alignment training methods like DPO, GRPO, RM, PPO, GKD, KTO, CPO, SimPO, ORPO for both text-based and multimodal large models.
12
12
- 🍓 Multimodal Training: Capable of training models for different modalities such as images, videos, and audios; supports tasks like VQA (Visual Question Answering), Captioning, OCR (Optical Character Recognition), and Grounding.
13
-
- 🥥 Megatron Parallelism: Supports accelerating CPT/SFT/DPO/KTO using Megatron parallelism techniques, currently compatible with 200+ large language models.
13
+
- 🥥 Megatron Parallelism: Supports accelerating CPT/SFT/DPO/KTO/RM using Megatron parallelism techniques, currently compatible with 200+ large language models.
14
14
- Interface-driven Training: Offers training, inference, evaluation, and quantization capabilities through an interface, enabling a complete workflow for large models.
15
15
- Plugins and Extensions: Allows customization and extension of models and datasets, and supports customizations for components like loss, metric, trainer, loss-scale, callback, optimizer, etc.
16
16
- 🍉 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.
0 commit comments