Skip to content

Actions: modelscope/ms-swift

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
2,500+ workflow runs
2,500+ workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
Increasing the IMAGE_MAX_TOKEN_NUM does not increase the number of steps. Qoder Assistant #534: Issue comment #9749 (comment) created by z0o0ey
1s
1s
perf(rlhf): vectorize padding-free log-probability restore citest #13513: Pull request #10021 opened by Ruihan11
14m 27s Ruihan11:perf/rlhf-padding-free-restore
Ruihan11:perf/rlhf-padding-free-restore
14m 27s
perf(rlhf): vectorize padding-free log-probability restore Lint test #18484: Pull request #10021 opened by Ruihan11
1m 18s Ruihan11:perf/rlhf-padding-free-restore
Ruihan11:perf/rlhf-padding-free-restore
1m 18s
perf(rlhf): vectorize padding-free log-probability restore citest-npu #3607: Pull request #10021 opened by Ruihan11
26m 49s Ruihan11:perf/rlhf-padding-free-restore
Ruihan11:perf/rlhf-padding-free-restore
26m 49s
4.3.0版本使用swift infer + vllm backend推理Kimi-k25模型报错”AttributeError: 'KimiK25VisionConfig' object has no attribute 'hidden_size'. Did you mean: 'mm_hidden_size'?“ Qoder Assistant #533: Issue comment #9772 (comment) created by z0o0ey
2s
2s
sft 垂域 文生文 训练中断 Qoder Assistant #532: Issue comment #9788 (comment) created by z0o0ey
1s
1s
多级多卡进行DPO训练时batch为{} Qoder Assistant #531: Issue comment #5601 (comment) created by z0o0ey
2s
2s
使用多卡训练分类模型出现tensor对齐情况 Qoder Assistant #530: Issue comment #5469 (comment) created by z0o0ey
1s
1s
支持训练时在多个验证集上独立评估 Qoder Assistant #529: Issue comment #5467 (comment) created by z0o0ey
1s
1s
LoRA合并qwen2.5-vl-7B模型在 ms-swift 3.6.4 与 3.7 表现差异: 3.7版本合并的模型在多槽位grounding任务上显著优于3.6.4版本合并的模型 Qoder Assistant #528: Issue comment #5430 (comment) created by z0o0ey
1s
1s
DPO 损失函数计算NaN问题查找 Qoder Assistant #527: Issue comment #5418 (comment) created by z0o0ey
2s
2s
同样的配置，启动多次实验，有的实验日志中输出token_acc，有的没有 Qoder Assistant #526: Issue comment #5388 (comment) created by z0o0ey
10s
10s
llava-next-video微调 Qoder Assistant #525: Issue comment #5322 (comment) created by z0o0ey
1s
1s
LoRA batch推理，报错：Length of adapter_names should be the same as the number of inputs, but got 1 and 10 respectively Qoder Assistant #524: Issue comment #5285 (comment) created by z0o0ey
1s
1s
蒸馏Qwen2.5-Omni模型报错：IndexError: max(): Expected reduction dim 1 to have non-zero size. Qoder Assistant #523: Issue comment #4755 (comment) created by z0o0ey
1s
1s
GKD代码加载模型卡死 Qoder Assistant #522: Issue comment #4724 (comment) created by z0o0ey
1s
1s
训练qwen2.5vl时，开启序列并行+packing，loss会掉到0 Qoder Assistant #521: Issue comment #4581 (comment) created by z0o0ey
1s
1s
AttributeError: 'AwqLoraLinear' object has no attribute 'get_delta_weight' Qoder Assistant #520: Issue comment #3744 (comment) created by z0o0ey
9s
9s
swift微调deepseekvl2后效果变差 Qoder Assistant #519: Issue comment #3445 (comment) created by z0o0ey
1s
1s
LLama pro方式训练如何合并权重 Qoder Assistant #518: Issue comment #3351 (comment) created by z0o0ey
1s
1s
AttributeError: 'ModelInfo' object has no attribute 'rope_scaling' Qoder Assistant #517: Issue comment #3037 (comment) created by z0o0ey
1s
1s
PPO多卡训练报错 'RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cuda:3!' Qoder Assistant #516: Issue comment #2830 (comment) created by z0o0ey
10s
10s
qwen2-vl使用lmdeploy推理报错。 Qoder Assistant #515: Issue comment #2457 (comment) created by z0o0ey
2s
2s
使用streaming训练在eval会卡住 Qoder Assistant #514: Issue comment #2455 (comment) created by z0o0ey
9s
9s
runtimeerror：unsupported operation :more than one element of the written-to tensor refers to a single memory location. plese clone the tensor before performing the operation Qoder Assistant #513: Issue comment #2375 (comment) created by z0o0ey
1s
1s