Add automatic platform selection for gpt4all-lora-quantized

[BoQsc]

This is tested on both Windows 10 and Debian 10.

Untested on OSX and MAC. But should work. Need reports as I have no such hardware to test.

What it does: It will allow to simplify the Try yourself section in the README.md The OS will be selected by a generic command ./gpt4all-lora-quantized instead of manual selection by:

M1 Mac/OSX: cd chat;./gpt4all-lora-quantized-OSX-m1
Linux: cd chat;./gpt4all-lora-quantized-linux-x86
Windows (PowerShell): cd chat;./gpt4all-lora-quantized-win64.exe
Intel Mac/OSX: cd chat;./gpt4all-lora-quantized-OSX-intel

Old

New

1. Download the gpt4all-lora-quantized.bin file from Direct Link or [Torrent-Magnet].
2. Clone this repository, navigate to chat, and place the downloaded file there.
3. Run the appropriate command for your OS:
   • Windows
     • (Batch) cd chat && .\gpt4all-lora-quantized
     • (PowerShell) cd chat; ./gpt4all-lora-quantized
   • Linux/Mac/OSX cd chat; chmod +x ./gpt4all-lora-quantized; ./gpt4all-lora-quantized

All old arguments are supported and tested.

./gpt4all-lora-quantized --help ./gpt4all-lora-quantized --model .\gpt4all-lora-quantized.bin ...

[AyushyaChitransh]

Tested on macOSX M1

System Info:

Results attached:

[BoQsc]

Thank you for proving that it is stable and that it works.

Pull request is ready to be merged.

[AndriyMulyar]

Out of date