ParisNeo/lollms-webui

Model conversion error

Closed this issue · 6 comments

HulkAi commented

Expected Behavior

Conversion of model gpt4all-lora-quantized-ggml.bin

Current Behavior

Do you want to convert the selected model to the new format? [Y,N]?Y

Converting the model to the new format...
Cloning into 'tmp\llama.cpp'...
remote: Enumerating objects: 1707, done.
remote: Counting objects: 100% (1707/1707), done.
remote: Compressing objects: 100% (623/623), done.
remote: Total 1707 (delta 1088), reused 1629 (delta 1050), pack-reused 0Receiving objects: 100% (1707/1707), 1.52 MiB | Receiving objects: 100% (1707/1707), 1.87 MiB | 3.10 MiB/s, done.

Resolving deltas: 100% (1088/1088), done.
1 file(s) moved.
C:\Users\jtone\AppData\Local\Microsoft\WindowsApps\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\python.exe: can't open file 'C:\gpt4all-ui\tmp\llama.cpp\migrate-ggml-2023-03-30-pr613.py': [Errno 2] No such file or directory

Error during model conversion. Restarting...
1 file(s) moved.

Steps to Reproduce

run install.bat
press B
Select Y option
Select Y option

Possible Solution

I manually copied the missing file into the tmp folder that was created and it worked as expected.

Context

Os Windows 11
Cpu AMD Ryzen 7 5700G
Ram 32.0 GB (27.9 GB usable)

UsamaKenway commented

Same error
image
And run.bat only shows this :
image

HulkAi commented

save it as the file name mentioned and place it into the tmp folder when you run the run.bat file

UsamaKenway commented

happened to find that py file and placed it in tmp/llama.cpp/ but here are the results.
anyways, isnt it for old models only. we dont need conversion if we already have ggml version, right ?
image

Khyretos commented

for some reason i get a different error:
image

ParisNeo commented

Hi guyes. It seems that the llama.cpp repo has changed again and there is no access to the migration tool.
So I have decided to upload my own converted model to the Hugging face repo and I'll ditch the conversion step altogether.

I am on vacation and have limited connection so sending the model will take few hours.

When It's ready I'll change all install scripts to use it.

I hope this will help you all make it work.

  • 👍4