Marc Päpper comments

Results 7 comments of


                                            Marc Päpper

Add llama.cpp LLM, brining support for locally hosted LLMs

Awesome, thanks for adding @Zetaphor I tested out the llama agent, but noted that it was much slower with that Python binding than when I ran llama.cpp directly. There is...

Add llama.cpp LLM, brining support for locally hosted LLMs

For me, llama.cpp runs a few seconds and with the binding it's more like 30 seconds

Error in instructions and requirements.txt

Thanks @MikeBeller, I updated it in the README now.

Site map problem

Hi @bibhas2 do I understand it correctly that you are referring to not having the ability to parse sitemaps which link other sitemaps in turn?

Issue When Trying to Load My FineTuned Model

Hi Adam, the error indicates that the model is loaded with half precision (torch.cuda.HalfTensor), so you need to also pass the input with half precision. Presumably, you can just change...

Issue When Trying to Load My FineTuned Model

Did the error change after you made the input to `.half()`?

Potential Security Vulnerability: Arbitrary Code Execution via Direct Execution of LLM-Generated Content

Yes sure, that is a well known fact. For my use case it doesn't matter, but if this is important to you, feel free to submit a pull request.