Skip to content

Actions: hiyouga/LLaMA-Factory

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
2,808 workflow runs
2,808 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

为什么llama2的template里default system是空的 label_issue #1571: Issue #6018 opened by zyh3826
November 13, 2024 09:52 15s
November 13, 2024 09:52 15s
Customized Reward Model label_issue #1570: Issue #6017 opened by yuepengs
November 13, 2024 09:13 12s
November 13, 2024 09:13 12s
请问有没有介绍yaml所有可用到参数的文件 label_issue #1569: Issue #6016 opened by Beyond0831
November 13, 2024 08:19 10s
November 13, 2024 08:19 10s
使用原生DDP训练后，15min后显示sockettimeout。 label_issue #1568: Issue #6015 opened by liuhash
November 13, 2024 06:28 19s
November 13, 2024 06:28 19s
請支持deepseek-janusFlow的微調 label_issue #1567: Issue #6014 opened by win10ogod
November 13, 2024 05:25 10s
November 13, 2024 05:25 10s
facebook/OPT模型在MMLU上评估报错：CUDA error: device-side assert triggered label_issue #1566: Issue #6013 opened by CLL112
November 13, 2024 03:25 10s
November 13, 2024 03:25 10s
关闭验证集 label_issue #1565: Issue #6012 opened by BrenchCC
November 13, 2024 03:13 13s
November 13, 2024 03:13 13s
多卡4090 DeepSpeed ZeRO-3 LoRA 微调 Qwen2.5-14B-Instruct 显存占用超出预期 label_issue #1564: Issue #6011 opened by Lanture1064
November 13, 2024 02:28 10s
November 13, 2024 02:28 10s
merge_dataset 效果疑问 label_issue #1563: Issue #6009 opened by EthanChen1234
November 12, 2024 14:49 10s
November 12, 2024 14:49 10s
Serious misalignment in LLaVA implementation label_issue #1562: Issue #6008 opened by oncleJules
November 12, 2024 13:09 14s
November 12, 2024 13:09 14s
Qwen2.5-coder-7B微调运行一段时间后崩溃 label_issue #1561: Issue #6007 opened by xierbut
November 12, 2024 12:09 11s
November 12, 2024 12:09 11s
直接load adapter权重进行推理，推理结果和merge后的模型权重一样。这是为啥？ label_issue #1560: Issue #6006 opened by echoht
November 12, 2024 09:31 13s
November 12, 2024 09:31 13s
Unsloth FileExistsError: [WinError 183] label_issue #1559: Issue #6005 opened by rogersohandsome
November 12, 2024 09:21 12s
November 12, 2024 09:21 12s
创建的public url一直在加载 label_issue #1558: Issue #6004 opened by Wang-YLi
November 12, 2024 08:44 18s
November 12, 2024 08:44 18s
indices should be either on cpu or on the same device as the indexed tensor (cpu) label_issue #1557: Issue #6003 opened by sxm7078
November 12, 2024 08:05 11s
November 12, 2024 08:05 11s
在训练或微调阶段，如何设置GPU占用率？是否可以配置自动满载GPU？ label_issue #1556: Issue #6002 opened by Li-XYi
November 12, 2024 08:04 11s
November 12, 2024 08:04 11s
qwen2-vl-2b全参微调后，推理出现重复输出 label_issue #1555: Issue #6001 opened by hunter2009pf
November 12, 2024 07:46 9s
November 12, 2024 07:46 9s
单机多卡运行报错，8卡h20 label_issue #1554: Issue #6000 opened by yewenpeng
November 12, 2024 06:54 12s
November 12, 2024 06:54 12s
多卡运行报错 label_issue #1553: Issue #5999 opened by yugecode
November 12, 2024 05:33 11s
November 12, 2024 05:33 11s
在微调tools之后，通过api启动，返回了非json格式的arguments，但是在webui上测试是正常的 label_issue #1552: Issue #5998 opened by tydtydtyd
November 12, 2024 03:25 10s
November 12, 2024 03:25 10s
llamafactory support mlflow label_issue #1551: Issue #5997 opened by wzhgithub
November 12, 2024 03:24 11s
November 12, 2024 03:24 11s
Qwen2-vl lora train？ label_issue #1550: Issue #5996 opened by kike-0304
November 12, 2024 03:10 10s
November 12, 2024 03:10 10s
ChatGLM3-6b在阿里云上使用lora微调模型后，训练完成后，点击chat加载模型出现以西报错 label_issue #1549: Issue #5995 opened by wsjqq
November 12, 2024 00:34 12s
November 12, 2024 00:34 12s
是否支持OpenCoder微调？ label_issue #1548: Issue #5994 opened by watsonznkim
November 11, 2024 11:33 13s
November 11, 2024 11:33 13s
Set 'torch_device' as 'cpu' when loading pretrained adapter tests #1554: Pull request #5993 opened by LZHgrla
November 11, 2024 11:21 Action required LZHgrla:patch-1
LZHgrla:patch-1
November 11, 2024 11:21 Action required