Text Generation
Transformers
PyTorch
English
llama
Eval Results
Inference Endpoints
text-generation-inference

Why not GPT-4

#9
by Subcode - opened

Seeing how this is trained off models that are already not performing optimally / as good as GPT-4 the results seem to not be that great.
This should honestly not be trained off models that already perform worse than GPT-4 / score low on benchmarks.

Sign up or log in to comment