docs(README): update README.md

[foldl]

add notes on ChatLLM.cpp, which support DeepSeek-LLM model.

[DOGEwbx]

Hi @foldl , thanks for your support to our work. I took a brief look about your repo and I found that you implement the same input preprocessing logic with llama.cpp which we found different from the python implementation. It will be appreciated if you could refer this PR and made some modifications to your work.

[foldl]

Yes, some pre-processing rules are ignored and not implemented, which may cause subtle differences. I may add these functions later. At present, I am busy with adding more models.