List of working LLM
Do you have any working combination of LLM and embeddings? Please open a PR to add it to the list, and come on our Discord to tell us about it!
Prompt style
LLMs might have been trained with different prompt styles. The prompt style is the way the prompt is written, and how the system message is injected in the prompt.
For example, llama2
looks like this:
While default
(the llama_index
default) looks like this:
The “tag
” style looks like this:
The “mistral
” style looks like this:
The “chatml
” style looks like this:
Some LLMs will not understand these prompt styles, and will not work (returning nothing).
You can try to change the prompt style to default
(or tag
) in the settings, and it will
change the way the messages are formatted to be passed to the LLM.
Example of configuration
You might want to change the prompt depending on the language and model you are using.
English, with instructions
settings-en.yaml
:
French, with instructions
settings-fr.yaml
:
You might want to change the prompt as the one above might not directly answer your question. You can read online about how to write a good prompt, but in a nutshell, make it (extremely) directive.
You can try and troubleshot your prompt by writing multiline requests in the UI, while writing your interaction with the model, for example:
Another example:
Optimised Models
GodziLLa2-70B LLM (English, rank 2 on HuggingFace OpenLLM Leaderboard), bge large Embedding Model (rank 1 on HuggingFace MTEB Leaderboard)
settings-optimised.yaml
:
German speaking model
settings-de.yaml
: