Skip to content

llama-cpp-python not working with latest ggmls #255

@advaitdeshmukh

Description

@advaitdeshmukh

I was trying to use the openapi server with ggmlv3 I downloaded from(https://huggingface.co/TheBloke/Wizard-Vicuna-7B-Uncensored-GGML/tree/main) while it was working fine with ggmlv2 versions, the newer ones seem to be not compatible. Is this related to the newer version released by llama.cpp?
C:\Users\Advait\Desktop\LLAMA Server>python -m llama_cpp.server --model models/Wizard-Vicuna-7B-Uncensored.ggmlv3.q5_0.bin
llama.cpp: loading model from models/Wizard-Vicuna-7B-Uncensored.ggmlv3.q5_0.bin
error loading model: unknown (magic, version) combination: 67676a74, 00000003; is this really a GGML file?
llama_init_from_file: failed to load model
Traceback (most recent call last):
File "C:\Users\Advait\miniconda3\envs\llamanew\lib\runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "C:\Users\Advait\miniconda3\envs\llamanew\lib\runpy.py", line 86, in _run_code exec(code, run_globals) File "C:\Users\Advait\miniconda3\envs\llamanew\lib\site-packages\llama_cpp\server\__main__.py", line 46, in <module> app = create_app(settings=settings) File "C:\Users\Advait\miniconda3\envs\llamanew\lib\site-packages\llama_cpp\server\app.py", line 92, in create_app llama = llama_cpp.Llama( File "C:\Users\Advait\miniconda3\envs\llamanew\lib\site-packages\llama_cpp\llama.py", line 159, in __init__ assert self.ctx is not None AssertionError

Metadata

Metadata

Assignees

No one assigned

    Labels

    duplicateThis issue or pull request already existsllama.cppProblem with llama.cpp shared libmodelModel specific issue

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions