I'm stuck loading model

[Motorr23]

I'm stuck loading model

[P1kM1n]

I was having the exact same issue, what worked for me was double checking the models had correctly downloaded, and by placing the downloaded models on my desktop and using the models from there, with the file system for freedom-gpt still in my program files. A full uninstall (using "add or remove programs" in settings if available) and reinstall using the windows installer on the website rather than installing through git seemed to help as well.

tldr double check the models got succesfully downloaded and are being used properly. And fully reinstall the program.

[Motorr23]

Thanks for aswer me, but nothing change

[benbois]

Same issue on linux Ubuntu.. stuck on loading model. Nothing seems to work!

The .Bin files are still in place after a relaunch the app.

[Postconceptlab]

same issue on unbuntu as benbois ubuntu

[letsgitcracking]

Same issue on linux Ubuntu.. stuck on loading model. Nothing seems to work!

The .Bin files are still in place after a relaunch the app.

Same issue here on Ubuntu

[leeli0]

I had this issue on Arch Linux. I found that if you use yarn start then you can successfully load the model. In this case, first you need to Building the llama.cpp library according to the Readme documentation. Otherwise, you could get an error, like this:

Failed to start child process: Error: spawn /home/lee/Downloads/freedom-gpt/llama.cpp/main ENOENT at ChildProcess._handle.onexit (node:internal/child_process:283:19) at onErrorNT (node:internal/child_process:476:16) at process.processTicksAndRejections (node:internal/process/task_queues:82:21) { errno: -2, code: 'ENOENT', syscall: 'spawn /home/lee/Downloads/freedom-gpt/llama.cpp/main', path: '/home/lee/Downloads/freedom-gpt/llama.cpp/main', spawnargs: [ '-m', '/home/lee/Downloads/ggml-model-q4_0.bin', '-ins', '--ctx_size', '2048', '-n', '-1', '-ins', '-b', '256', '--top_k', '10000', '--temp', '0.2', '--repeat_penalty', '1', '-t', '7' ] }