Base$TVMError after downloading Llama-2-7b-chat-hf-q4f16_1

[jo-elimu]

🐛 Bug

@Kartik14

To Reproduce

Steps to reproduce the behavior:

1. Download and install the Android APK from https://llm.mlc.ai/docs/deploy/android.html
2. Then download the llama model from the model list
3. Press chat icon
4. Error appears

Expected behavior

Environment

• Platform (e.g. WebGPU/Vulkan/IOS/Android/CUDA): Android
• Operating system (e.g. Ubuntu/Windows/MacOS/...): Android 14
• Device (e.g. iPhone 12 Pro, PC+RTX 3090, ...): Snapdragon 8+ Gen 1
• How you installed MLC-LLM (conda, source): Downloaded Android APK from https://llm.mlc.ai/docs/deploy/android.html
• How you installed TVM-Unity (pip, source):
• Python version (e.g. 3.10):
• GPU driver version (if applicable):
• CUDA/cuDNN version (if applicable):
• TVM Unity Hash Tag (python -c "import tvm; print('\n'.join(f'{k}: {v}' for k, v in tvm.support.libinfo().items()))", applicable if you compile models):
• Any other relevant information:

Additional context

[Kartik14]

Seems like the weights were not download correctly, can you try deleting and redownloading?

[jo-elimu]

@Kartik14 I tried deleting and downloading a second time. Same error.

[Kartik14]

@jo-elimu Unfortunately, I am unable to reproduce this error on my end. Maybe you can try to copy the model weights manually using adb (instructions are here)