how to run Android app of release v0.0.1

OpenGVLab / OmniQuant

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

MIT License

663 stars 50 forks source link

how to run Android app of release v0.0.1 #5

Closed 946166920 closed 10 months ago

946166920 commented 1 year ago

I install the app of release v0.0.1. It show Add model failed: no protocol: /resolve/main/mlc-chat-config.json

ChenMnZ commented 1 year ago

The app includes three pre-configured models as shown here: 4d53b06ba6eb8d60ea84dad860ec45e Upon launch, these models are automatically integrated. For manual addition, please input any of the following links into the Model URL bar:

https://huggingface.co/ChenMnZ/Llama-2-13b-chat-omniquant-w3a16g128asym_2/
https://huggingface.co/ChenMnZ/Llama-2-7b-chat-omniquant-w3a16g128asym_2/
https://huggingface.co/ChenMnZ/Llama-2-13b-chat-omniquant-w2a16g128asym_2/