minigpt4.cpp
minigpt4.cpp copied to clipboard
Maknee
Port of MiniGPT4 in C++ (4bit, 5bit, 6bit, 8bit, 16bit CPU inference with GGML)
@Maknee I tried setting option(MINIGPT4_CUBLAS "minigpt4: use cuBLAS" ON) in the [CMakeLists.txt](https://github.com/Maknee/minigpt4.cpp/blob/master/CMakeLists.txt#L35). But when i run cmake --build . --config Release, i get this error below unfortunately : - 
Hi ， I want to test the token speed of minigpt4, but tokenizer failed AutoTokenizer.from_pretrained('maknee/ggml-vicuna-v0-quantized/13B') or huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': 'maknee/ggml-vicuna-v0-quantized/13B'. Use `repo_type`...
Hi, I enabled the cublas compilation option. The problem is that not charge o process all in GRAM memory? What is the best line command to construct and execute in...
Posting to gauge/express interested in MiniGPT-v2 support being added.
Hello! thank you for this. is there any chance getting a gui without needing to install python like koboldcpp in the future for its portability? also, can we use this...
In the "Convert the model to ggml" section of the README.md, what is the "" parameter referring to? Following the instructions in MiniGPT4, I ended up with a folder containing...
