issues-forum

244 threads · Page 5 of 5

Cuda Error 222 4 messages
CodeLlama-34B is repeating itself 20 messages
Code-Llama doesn't run on GPU 28 messages
have not been able to use due to this " KEY ERROR: role" issue. someone please help. 3 messages
GPU not in real use even got everything right 4 messages
▌ Unknown command 5 messages
Cmake couldnt find CUDA toolkit 9 messages
API-KEY problem 8 messages
No Progress 36 messages
Installation failure, cmake compiler not set 2 messages
I am suddenly getting errors related to 'logprobs'. 2 messages
Model (not) set to Code-Llama GPU unit 13 messages
Could not find version that satisfies requirements 5 messages
Cannot use Code-Llama on M1 10 messages
Interpreter GPT3 cannot install python package 11 messages
Problem to install llama-cpp-python on Windows 10 with GPU NVidia Support CUBlast, BLAS = 0 5 messages
Mac mini m2 base model crashes using local llm. 6 messages
how to fix API key error 14 messages
Can't Install locally 29 messages
Access to GPT-4 19 messages
Can't detect GPU - NVIDIA GeForce GTX 1060 - windows 10 3 messages
Commands hanging and not completing 11 messages
I am setting up Open-Interpreter on Windows on RTX 3070: " s 15 messages
[resolved] v0.1.3 - python interpreter cannot find a local file using a valid full path 10 messages
Shell Commands/Execute hangs to execute in MacOS 7 messages
Failed to install Code-Llama 4 messages
OSError: [WinError -1073741795] Windows Error 0xc000001d llama-cpp-python 6 messages
Please help me, I’m trying to run it on Windows, but the following problem occurs, what should I do? 4 messages
I know this isn't really designed for Archlinux but curious if anyone can help? 4 messages
newbie here, need some guidance... 26 messages
can’t run local with -y 37 messages
Python llama_cpp errors 5 messages
Authentication Error 28 messages
Can't install Falcon 180B once downloaded 2 messages
Having trouble using CUDA for WSL2 8 messages
Is there a special command I can use to get Open Interpreter to search, scrape particular links ... 26 messages
python -c "from llama_cpp import GGML_USE_CUBLAS; print(GGML_USE_CUBLAS)" False 27 messages
My llama seems to be not smart 2 messages
Cannot get interpreter to use GPU on Win11 5 messages
interpreter breaks if the stream contains Unicode characters ( emojis etc. ) 3 messages
Receiving False when attempting to use GPU 8 messages
Code-llama always prompts for token issues, has anyone encountered this? 3 messages
ERROR: Failed building wheel for llama-cpp-python 5 messages
“Interpreter” not recognized as command Windows 10 messages