weasel4o

Results 4 comments of weasel4o

Cuda extension not installed

@missionfloyd - 100% same case here. Same model /7b though/ - GPU memory is in use, however when I do any query over langchain, my CPU usage hits 100%.

Query execution with langchain LLM pipeline is happening on CPU, even if model is loaded on GPU

Same case with my code - different LLM and vector DB, but again Langchain is stressing the CPU. Ubuntu 22.04 1xT4 - 16GB 28 GB RAM 4 CPU Risen

installing requirements llama-cpp-python error

@Vector-9974 - try installing Visual Studio (not VS Code, but Visual studio) - it appears that you are lacking a C++ compiler on your PC. During the installation, make sure...

how can i solve Openai Error (500 Error)?

one more case here - same issue on : M1 Air Contributor role in Azure prior to execution of start.sh I've ran az login to determine correct Azure subscription Errors...