vicuna-tools / vicuna-installation-guide

The "vicuna-installation-guide" provides step-by-step instructions for installing and configuring Vicuna 13 and 7B
285 stars 34 forks source link

Unable to load model error still occurring #14

Closed uptogodown closed 1 year ago

uptogodown commented 1 year ago

Still getting the "unable to load model error", I am on Linux Mint latest version using the one setp install script:

git clone https://github.com/fredi-python/llama.cpp.git && cd llama.cpp && make -j && cd models && wget -c https://huggingface.co/eachadea/ggml-vicuna-13b-1.1/resolve/main/ggml-vic13b-uncensored-q5_1.bin

After it has completed it's install I go to use Vicuna

Command: ~/llama.cpp$ ./main -m ggml-vic13b-uncensored-q5_1.bin -f 'prompts/chat-with-vicuna-v1.txt' -r 'User:' --temp 0.36

Output: main: build = 632 (787aadf) main: seed = 1687195202 error loading model: failed to open ggml-vic13b-uncensored-q5_1.bin: No such file or directory llama_init_from_file: failed to load model llama_init_from_gpt_params: error: failed to load model 'ggml-vic13b-uncensored-q5_1.bin' main: error: unable to load model

Thank you for the development, I hope this let me know if anything is needed.

fredi-python commented 1 year ago

This should now be fixed.

uptogodown commented 1 year ago

Hello, I have just manually removed & reinstalled using all the commands listed and the issue is still here, I am on Linux Mint 20.3 .

fredi-python commented 1 year ago

Did you remove the whole llama.cpp folder?

fredi-python commented 1 year ago

If your folder still exists navigate to it and run

git pull

Then run

make -j

And you should be able to load the model.

fredi-python commented 1 year ago

How is it going? Did it work now?

uptogodown commented 1 year ago

No luck, did the commands and still says "unable to lad model": ~/llama.cpp$ ./main -m ggml-vic13b-uncensored-q5_1.bin -f 'prompts/chat-with-vicuna-v1.txt' -r 'User:' --temp 0.36 main: build = 732 (afd983c) main: seed = 1687442258 error loading model: failed to open ggml-vic13b-uncensored-q5_1.bin: No such file or directory llama_init_from_file: failed to load model llama_init_from_gpt_params: error: failed to load model 'ggml-vic13b-uncensored-q5_1.bin' main: error: unable to load model

uptogodown commented 1 year ago

Please advise what OS(s) you are running it on that work. Just if it helps I am using the 5.4.0-152-generic kernel

fredi-python commented 1 year ago

6.3.8-arch1-1 Arch Linux

uptogodown commented 1 year ago

Hi, I am still having the issues, I have latest Linux Mint 20.2 & tried on PopOS but I am still having the issue of being unable to load the model, tried reinstalling multiple times, git pull & make -j and still isn't working.