Tan Hoang

You can work with both directed and undirected graphs (if an undirected graph has edge(a,b) then simply puts edge(b, a)) using same code. So why does this code need to...

> Updating to gcc-11 and g++-11 worked for me on Ubuntu 18.04. > > Did that using `sudo apt install gcc-11` and `sudo apt install g++-11`. This should be the...

I think the main reason is almost all the small llama-like models without RLHF are kind of terrible in mathematics. Vicuna's authors also have reported some limitations here https://lmsys.org/blog/2023-03-30-vicuna/

Same for me, python 3.10.6. I also tried on another Ubuntu machine with Python 3.10.8 and got `Failed building wheel for llama-cpp-python` while installing dependencies. I managed to resolve this...

The slow speed during interaction is mostly caused by LLM. I can see that the default num threads (param n_threads) for the LLM are 4. ```python match model_type: case "LlamaCpp":...

> > Hi , > > Could you let me know where can I download the correct version to run privateGPT? > > ``` > Using embedded DuckDB with persistence:...

First the repo is amazing, I'm working on the same idea privately so this is good codebase to learn from. For the performance, perhaps because vllm has already had numerous...