amd
/

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints

Code completion functionality

#1
by Smorty100 - opened

The Llama2 template does not include a code-completion or fill-in-the-middle syntax. In the instruction format, it also does not really generate anything useful, as it puts some equals signs on page and adds some vague python code.
What usecases would this small model have? It doesn't seem able to integrate into anything really.

Am I missing something here? Or am I maybe using the wrong template?

Sign up or log in to comment