Copied the release Alpaca-Turbo-beta_v0.6 about alpaca-turbo HOT 6 OPEN

copied all files from Alpaca-Turbo-beta_v0.6 to Alpaca-Turbo
tried run in gradio_impl folder
Sounds like you downloaded the source code. You need to download Alpaca-Turbo_0.6.zip instead. The release doesn't contain a gradio_impl folder.

from alpaca-turbo.

I had tried run from gradio_impl , it said set the model.

ii had download Alpaca_turbo _0.6,zip and put into a clean Alpaca-turbo and inside have gradio_impl.

(alpaca_turbo) C:\Users\Administrator\Alpaca-Turbo\gradio_impl>python api.py
Set the model path in settings

when I inspect the api.py it doesn't consist of flask , so this is not even the same api as the Alpaca-Turbo folder .

from alpaca-turbo.

After resetup ,

1. download Alpaca-Turbo_0.6.zip

2. download ggml-alpaca-7b-q4.bin and also ggml-vicuna-13b-1.1 in a folder

3. conda init and close window

4. conda create -n alpaca_turbo python=3.8 -y
   conda activate alpaca_turbo
   pip install -r requirements.txt
   python api.py

5. the web can show and click load model ggml-alpaca-7b-q4.bin, no error.

6. console show no error ,but nothing happened click send after type hello. But on web debug got load model error when click on new chat.

from alpaca-turbo.

from alpaca-turbo.

Hi @chongy076, as I can see from the last screen you provided that the model is not loaded, so the chat won't send if the model didn't load.
When the model loaded you will get a notification that model xx has been loaded, and you will get a button to reload the model under Load Model in sidebar.

did you try Vicuna Model?

from alpaca-turbo.

@AnouarAndichi
I tried ggml-vicuna-13b-4bit-rev1.bin , ggml-vicuna-13b-4bit-rev1.1.bin ,ggml-vicuna-7b-4bit.bin.
But thanks for the tips, I think i may need to modify the load model code. it did mentioned somethings on the load model.

from alpaca-turbo.