Mr Harrison comments

Results 7 comments of


                                            Mr Harrison

RuntimeError: The detected CUDA version (12.1) mismatches the version that was used to compile PyTorch (11.7). Please make sure to use the same CUDA versions.

I got the same error using the one-click windows install. My Cuda I installed is 12.1, the only version that NVidia appears to have. Possibly the install recovered using wheel....

RuntimeError: The detected CUDA version (12.1) mismatches the version that was used to compile PyTorch (11.7). Please make sure to use the same CUDA versions.

@jllllll I already had Cuda on my win10 workstation for some other pytorch work. You're a Rock Star, I'm up and running. Gradio HTTP request redirected to localhost :) bin...

Would like to see the running costs (OPEN_AI) for a session with AutoGPT

Yes, a goal could be, don't spend more than 5.00 USD in OpenAI API account for this whatever.

OSError: [WinError -1073741795] Windows Error 0xc000001d And AttributeError: 'Llama' object has no attribute 'ctx'

> Getting "OSError: [WinError -1073741795] Windows Error 0xc000001d" also. My next step was to validate the LLMs. I'll try GPT4all to validate my downloaded LLMs.

Multi GPU for large model

> I tried but the application crashes with 2 graphic cards. I have to set a variable to force using only one graphic card (I have 2 x Quadro RTX...

Support for Dual Nvidia 3060 Setup in OLMOCR

Yes, a single RTX 3090 works for olmOCR using about 20Gb of the 24Gb VRAM.

Support for Dual Nvidia 3060 Setup in OLMOCR

I've run 3 used 3090's 1.5 years now after bought used. I've had no issues. Excellent choice for affordable AI. If you have 3-4K for a 5090 and can find...