-
Notifications
You must be signed in to change notification settings - Fork 1.5k
- #9028 · Jintao-Huang opened
on Apr 7, 2026 9 - #7250 · Jintao-Huang opened
on Dec 30, 2025 62
Issues
is:issue state:open
is:issue state:open
Issue creation is restricted in this repository
Search results
- Status: Open.#9668 In modelscope/ms-swift;
- Status: Open.#9667 In modelscope/ms-swift;
fla error while using SFTTrainer
bugSomething isn't workingSomething isn't workingStatus: Open.#9664 In modelscope/ms-swift;ms-swift 3.12.5 无法加载一个由 ms-swift 4.0.3 训练/导出的 Qwen3-VL MoE HF checkpoint
questionFurther information is requestedFurther information is requestedStatus: Open.#9663 In modelscope/ms-swift;CANN 9.0.0 NPU 官方镜像中 MindSpeed 与 Megatron 版本冲突,导致 MoE 模型训练无法启动
bugSomething isn't workingSomething isn't workingStatus: Open.#9661 In modelscope/ms-swift;是否支持查看每个step的训练数据
questionFurther information is requestedFurther information is requestedStatus: Open.#9659 In modelscope/ms-swift;qwen3vl embedding的SFT训练遇到deepspeed问题
questionFurther information is requestedFurther information is requestedStatus: Open.#9657 In modelscope/ms-swift;Qwen/Qwen3-VL-30B-A3B-Instruct 做 GRPO 训练时,在 vllm_mode=server 模式下遇到了 rollout 输出乱码的问题
questionFurther information is requestedFurther information is requestedStatus: Open.#9656 In modelscope/ms-swift;MiniCPM-V 4.6 training hangs on text-only samples with DeepSpeed
bugSomething isn't workingSomething isn't workingStatus: Open.#9655 In modelscope/ms-swift;seq_acc=0
bugSomething isn't workingSomething isn't workingStatus: Open.#9652 In modelscope/ms-swift;请问现在支持视频模态的OPSD训练吗
questionFurther information is requestedFurther information is requestedStatus: Open.#9651 In modelscope/ms-swift;IterablePackingDataset使用 fork 模式导致 DeepSpeed ZeRO-3 训练死锁bugSomething isn't workingSomething isn't workingStatus: Open.#9649 In modelscope/ms-swift;