Kaotic3
Kaotic3
Just as an addition - I took this out of the benchmark and put it into the actual project. Worked just fine. Just fails in Benchmarks.
Hi @alexandrnikitin thanks for the response. These two methods appear exactly like this in the benchmark test: ``` [MemoryDiagnoser] public class Attempts { [Benchmark] public void AttemptOne() { var wordArray...
Ok it seems that the second one will run while empty...and the benchmark is not taking the list with any items in it at all. The list definitely has items...
Sheikh is quite a common first name in some quarters. Mr Sheikh Akhtar Hussain A disbarred barrister in the UK apparently... Mr Sheikh Ahmad a plastic surgeon in Devon.
Apologies, I was just giving name examples of the use of a Title as a Name. For the Data that name would appear as: Sheikh Hussain Currently that would become:...
The Titles as First does cause a problem where there is a middle name. Programmatically it is difficult because Is Sheikh Akhtar Hussain a Sheikh called Akhtar Hussain or Sheikh...
If you are using langchain, this is the first reference I can find, though I don't think this is where I originally read it: https://python.langchain.com/docs/modules/data_connection/retrievers/web_research ``` llama = LlamaCpp( model_path="/Users/rlm/Desktop/Code/llama.cpp/llama-2-13b-chat.ggmlv3.q4_0.bin",...
Edited as I have just seen the comment about 0.2.29. You can revert with the following and I am about to try it out. ``` pip install llama-cpp-python==0.2.28 --force-reinstall --no-cache-dir...
That returned ret == 1. Not sure if that is any use to you.... I did add some more information, to see if it helped reveal anything... Console.WriteLine($"[DEBUGGING]: test ret...
I had a look at the code and implemented the NativeApi log that you provided in another thread - and I don't see anything being returned on a failure. Not...