No windows binary about gpt4all HOT 10 CLOSED

wsl needs to be installed

from gpt4all.

Ah, I figured it out. You need to install Ubuntu after installing WSL.

“Turn Windows features on and off” into the Start Menu search field, then select the control panel when it appears. Scroll down to Windows Subsystem for Linux, check the box, and then click the OK button. Wait for your changes to be applied, then click the Restart now button to restart your computer.

After installing wsl:
wsl --install -d Ubuntu

A new ubuntu terminal will open:

cd /mnt/c/Users/myudy/gpt4all/
user@DESKTOP-C2MBDRO:/mnt/c/Users/myudy/gpt4all$ ls
'MYUDY README.txt' clean.py eval_data generate.py requirements.txt
README.md configs eval_figures.py gpt4all-lora-demo.gif train.py
TRAINING_LOG.md data.py eval_self_instruct.py peft transformers
chat env.yaml figs read.py
user@DESKTOP-C2MBDRO:/mnt/c/Users/myudy/gpt4all$ cd chat/
user@DESKTOP-C2MBDRO:/mnt/c/Users/myudy/gpt4all/chat$ ./gpt4all-lora-quantized
gpt4all-lora-quantized-OSX-m1 gpt4all-lora-quantized-linux-x86 gpt4all-lora-quantized.bin
user@DESKTOP-C2MBDRO:/mnt/c/Users/myudy/gpt4all/chat$ ./gpt4all-lora-quantized-linux-x86
main: seed = 1680077179
llama_model_load: loading model from 'gpt4all-lora-quantized.bin' - please wait ...
llama_model_load: ggml ctx size = 6065.35 MB
llama_model_load: memory_size = 2048.00 MB, n_mem = 65536
llama_model_load: loading model part 1/1 from 'gpt4all-lora-quantized.bin'
llama_model_load: .................................... done
llama_model_load: model size = 4017.27 MB / num tensors = 291

system_info: n_threads = 4 / 4 | AVX = 1 | AVX2 = 1 | AVX512 = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | VSX = 0 |
main: interactive mode on.
sampling parameters: temp = 0.100000, top_k = 40, top_p = 0.950000, repeat_last_n = 64, repeat_penalty = 1.300000

== Running in chat mode. ==

• Press Ctrl+C to interject at any time.
• Press Return to return control to LLaMA.
• If you want to submit another line, end your input in ''.

from gpt4all.

I'm in an anaconda prompt windows in the base environment. I installed Windows Subsystem for Linux and restarted but no luck

(base) C:\Users\myudy>cd gpt4all

(base) C:\Users\myudy\gpt4all>cd chat

(base) C:\Users\myudy\gpt4all\chat>ls
gpt4all-lora-quantized-OSX-m1 gpt4all-lora-quantized-linux-x86 gpt4all-lora-quantized.bin

(base) C:\Users\myudy\gpt4all\chat>./gpt4all-lora-quantized-linux-x86
'.' is not recognized as an internal or external command,
operable program or batch file.

(base) C:\Users\myudy\gpt4all\chat>.\gpt4all-lora-quantized-linux-x86
'.\gpt4all-lora-quantized-linux-x86' is not recognized as an internal or external command,
operable program or batch file.

from gpt4all.

I also tried to rename it as a .exe but windows then says it is 16 bit and not compatible with 64-bit windows (despite saying x86 in the filename which implies 32-bit and compatibility).

from gpt4all.

I managed to get a working binary for Windows using https://github.com/zanussbaum/gpt4all.cpp

from gpt4all.

Can you share it?

from gpt4all.

I tried @EliasVincent 's binary but I got the windows error

from gpt4all.

I tried @EliasVincent 's binary but I got the windows error

did you run it through powershell with the quantized model in the chat folder?

from gpt4all.

from gpt4all.

to run on windows: install Windows Subsytem Linux (via microsoft store)
open an adm powershell and type: dism.exe /online /enable-feature /featurename:Microsoft-Windows-Subsystem-Linux /all /norestart
restart your pc
open an adm powershell and type: wsl --install Ubuntu
after that just boot on Ubuntu and git clone repo (https) and wget the bin file to /chat folder and execute gpt4all

from gpt4all.