Error occurs when running prebuilt app
ThisisBillhe opened this issue · comments
MLCChat failed
Stack trace:
org.apache.tvm.Base$TVMError: ValueError: Check failed: shard_rec.nbytes == raw_data.length() (33233920 vs. 22720361) : Parameters are not loaded properly. Please check your parameter shards and git lfs installation
Stack trace:
File "/Users/bbuf/工作目录/RWKV/mlc-llm/3rdparty/tvm/src/runtime/relax_vm/ndarray_cache_support.cc", line 262
at org.apache.tvm.Base.checkCall(Base.java:173)
at org.apache.tvm.Function.invoke(Function.java:130)
at ai.mlc.mlcllm.ChatModule.reload(ChatModule.java:43)
at ai.mlc.mlcchat.AppViewModel$ChatState$mainReloadChat$1$2.invoke(AppViewModel.kt:646)
at ai.mlc.mlcchat.AppViewModel$ChatState$mainReloadChat$1$2.invoke(AppViewModel.kt:644)
at ai.mlc.mlcchat.AppViewModel$ChatState.callBackend(AppViewModel.kt:547)
at ai.mlc.mlcchat.AppViewModel$ChatState.mainReloadChat$lambda$3(AppViewModel.kt:644)
at ai.mlc.mlcchat.AppViewModel$ChatState.$r8$lambda$JJKpoRMMpp77FzXKA0o00i8lgRA(Unknown Source:0)
at ai.mlc.mlcchat.AppViewModel$ChatState$$ExternalSyntheticLambda3.run(Unknown Source:8)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:463)
at java.util.concurrent.FutureTask.run(FutureTask.java:264)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1137)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:637)
at java.lang.Thread.run(Thread.java:1012)
Error message:
ValueError: Check failed: shard_rec.nbytes == raw_data.length() (33233920 vs. 22720361) : Parameters are not loaded properly. Please check your parameter shards and git lfs installation
Stack trace:
File "/Users/bbuf/工作目录/RWKV/mlc-llm/3rdparty/tvm/src/runtime/relax_vm/ndarray_cache_support.cc", line 262
MLCChat failed
Stack trace: org.apache.tvm.Base$TVMError: ValueError: Check failed: shard_rec.nbytes == raw_data.length() (33233920 vs. 22720361) : Parameters are not loaded properly. Please check your parameter shards and git lfs installation Stack trace: File "/Users/bbuf/工作目录/RWKV/mlc-llm/3rdparty/tvm/src/runtime/relax_vm/ndarray_cache_support.cc", line 262
at org.apache.tvm.Base.checkCall(Base.java:173) at org.apache.tvm.Function.invoke(Function.java:130) at ai.mlc.mlcllm.ChatModule.reload(ChatModule.java:43) at ai.mlc.mlcchat.AppViewModel$ChatState$mainReloadChat$1$2.invoke(AppViewModel.kt:646) at ai.mlc.mlcchat.AppViewModel$ChatState$mainReloadChat$1$2.invoke(AppViewModel.kt:644) at ai.mlc.mlcchat.AppViewModel$ChatState.callBackend(AppViewModel.kt:547) at ai.mlc.mlcchat.AppViewModel$ChatState.mainReloadChat$lambda$3(AppViewModel.kt:644) at ai.mlc.mlcchat.AppViewModel$ChatState.$r8$lambda$JJKpoRMMpp77FzXKA0o00i8lgRA(Unknown Source:0) at ai.mlc.mlcchat.AppViewModel$ChatState$$ExternalSyntheticLambda3.run(Unknown Source:8) at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:463) at java.util.concurrent.FutureTask.run(FutureTask.java:264) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1137) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:637) at java.lang.Thread.run(Thread.java:1012)Error message: ValueError: Check failed: shard_rec.nbytes == raw_data.length() (33233920 vs. 22720361) : Parameters are not loaded properly. Please check your parameter shards and git lfs installation Stack trace: File "/Users/bbuf/工作目录/RWKV/mlc-llm/3rdparty/tvm/src/runtime/relax_vm/ndarray_cache_support.cc", line 262
I also encountered this issue, it was due to the weights not being fully downloaded. You can uninstall the app and reinstall it, then download the weights again while using a proxy. Make sure not to switch the proxy or the network during the download.
Can I download the weights from my PC and put them to some dir on my phone?
Can I download the weights from my PC and put them to some dir on my phone?
Certainly, you can use adb push to transfer the local weights to the path where the app stores the weights.
Do you know where this path is? thanks!
Do you know where this path is? thanks!
It's probably under a folder named something like ai.mlc.llm in /storage.