ERROR:Could not find the quantized model in .pt or .safetensors format, exiting...
(textgen) root@CRCODE22:~/text-generation-webui# python server.py --chat --model VicUnlocked-30B-LoRA.ggml.q5_1 --listen --wbits 4 --groupsize 128 --model_type llama --threads 8 --extensions superbooga
INFO:Gradio HTTP request redirected to localhost :)
bin /root/miniconda3/envs/textgen/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda117.so
INFO:Loading VicUnlocked-30B-LoRA.ggml.q5_1...
ERROR:Could not find the quantized model in .pt or .safetensors format, exiting...
I already had installed the latest llama-cpp-python :
pip uninstall -y llama-cpp-python
CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python --no-cache-dir
Changing the command line to python server.py --chat --model VicUnlocked-30B-LoRA.ggml.q5_1 --listen --extensions superbooga solved the problem