复制
收藏
提问
全网

C:\Users\cast\.conda\envs\AiTest001\python.exe "D:\PyCharm 2024.1.1\PycharmWorkPlace\pythonProject\01 test_Qwen2-2(success).py" C:\Users\cast\.conda\envs\AiTest001\lib\site-packages\accelerate\utils\modeling.py:1405: UserWarning: Current model requires 1811942784 bytes of buffer for offloaded layers, which seems does not fit any GPU's remaining memory. If you are experiencing a OOM later, please consider using offload_buffers=True. warnings.warn( Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.37it/s] Some parameters are on the meta device device because they were offloaded to the cpu. You shouldn't move a model that is dispatched using accelerate hooks. Traceback (most recent call last): File "D:\PyCharm 2024.1.1\PycharmWorkPlace\pythonProject\01 test_Qwen2-2(success).py", line 74, in <module> model.to(device) File "C:\Users\cast\.conda\envs\AiTest001\lib\site-packages\accelerate\big_modeling.py", line 456, in wrapper raise RuntimeError("You can't move a model that has some modules offloaded to cpu or disk.") RuntimeError: You can't move a model that has some modules offloaded to cpu or disk.

a0859f4d2
3个月前
全网
文档
学术
百科
知识库
时间不限
自动
来源0

理解问题C:\Users\cast\.conda\envs\AiTest001\python.exe "D:\PyCharm 2024.1.1\PycharmWorkPlace\pythonProject\01 test_Qwen2-2(success).py" C:\Users\cast\.conda\envs\AiTest001\lib\site-packages\accelerate\utils\modeling.py:1405: UserWarning: Current model requires 1811942784 bytes of buffer for offloaded layers, which seems does not fit any GPU's remaining memory. If you are experiencing a OOM later, please consider using offload_buffers=True. warnings.warn( Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.37it/s] Some parameters are on the meta device device because they were offloaded to the cpu. You shouldn't move a model that is dispatched using accelerate hooks. Traceback (most recent call last): File "D:\PyCharm 2024.1.1\PycharmWorkPlace\pythonProject\01 test_Qwen2-2(success).py", line 74, in <module> model.to(device) File "C:\Users\cast\.conda\envs\AiTest001\lib\site-packages\accelerate\big_modeling.py", line 456, in wrapper raise RuntimeError("You can't move a model that has some modules offloaded to cpu or disk.") RuntimeError: You can't move a model that has some modules offloaded to cpu or disk.

已完成理解「C:\Users\cast\.conda\envs\AiTest001\python.exe "D:\PyCharm 2024.1.1\PycharmWorkPlace\pythonProject\01 test_Qwen2-2(success).py" C:\Users\cast\.conda\envs\AiTest001\lib\site-packages\accelerate\utils\modeling.py:1405: UserWarning: Current model requires 1811942784 bytes of buffer for offloaded layers, which seems does not fit any GPU's remaining memory. If you are experiencing a OOM later, please consider using offload_buffers=True. warnings.warn( Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.37it/s] Some parameters are on the meta device device because they were offloaded to the cpu. You shouldn't move a model that is dispatched using accelerate hooks. Traceback (most recent call last): File "D:\PyCharm 2024.1.1\PycharmWorkPlace\pythonProject\01 test_Qwen2-2(success).py", line 74, in <module> model.to(device) File "C:\Users\cast\.conda\envs\AiTest001\lib\site-packages\accelerate\big_modeling.py", line 456, in wrapper raise RuntimeError("You can't move a model that has some modules offloaded to cpu or disk.") RuntimeError: You can't move a model that has some modules offloaded to cpu or disk.」

展开阅读网页

更专业一些
转笔记
专业
C:\Users\cast\.conda\envs\AiTest001\python.exe "D:\PyCharm 2024.1.1\PycharmWorkPlace\pythonProject\01 test_Qwen2-2(success).py" C:\Users\cast\.conda\envs\AiTest001\lib\site-packages\accelerate\utils\modeling.py:1405: UserWarning: Current model requires 1811942784 bytes of buffer for offloaded layers, which seems does not fit any GPU's remaining memory. If you are experiencing a OOM later, please consider using offload_buffers=True. warnings.warn( Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.37it/s] Some parameters are on the meta device device because they were offloaded to the cpu. You shouldn't move a model that is dispatched using accelerate hooks. Traceback (most recent call last): File "D:\PyCharm 2024.1.1\PycharmWorkPlace\pythonProject\01 test_Qwen2-2(success).py", line 74, in <module> model.to(device) File "C:\Users\cast\.conda\envs\AiTest001\lib\site-packages\accelerate\big_modeling.py", line 456, in wrapper raise RuntimeError("You can't move a model that has some modules offloaded to cpu or disk.") RuntimeError: You can't move a model that has some modules offloaded to cpu or disk.
不在提醒

更专业内容正在努力生成中
知识树
C:\Users\cast\.conda\envs\AiTest001\python.exe "D:\PyCharm 2024.1.1\PycharmWorkPlace\pythonProject\01 test_Qwen2-2(success).py" C:\Users\cast\.conda\envs\AiTest001\lib\site-packages\accelerate\utils\modeling.py:1405: UserWarning: Current model requires 1811942784 bytes of buffer for offloaded layers, which seems does not fit any GPU's remaining memory. If you are experiencing a OOM later, please consider using offload_buffers=True. warnings.warn( Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.37it/s] Some parameters are on the meta device device because they were offloaded to the cpu. You shouldn't move a model that is dispatched using accelerate hooks. Traceback (most recent call last): File "D:\PyCharm 2024.1.1\PycharmWorkPlace\pythonProject\01 test_Qwen2-2(success).py", line 74, in <module> model.to(device) File "C:\Users\cast\.conda\envs\AiTest001\lib\site-packages\accelerate\big_modeling.py", line 456, in wrapper raise RuntimeError("You can't move a model that has some modules offloaded to cpu or disk.") RuntimeError: You can't move a model that has some modules offloaded to cpu or disk.
如何解决Python中的OOM错误？
如何优化Python程序以减少内存使用？
Python加速库accelerate使用指南

以上内容由AI搜集生成，仅供参考

在线客服