Closed deep-diver closed 6 months ago
for visibility cc'ing: @sayakpaul
currently, the eval step consists of
the two sub-parts should be separated. Also, in order for Gemini evaluation to evaluate on the batch inferenced outputs, the batch inferenced outputs should be stored in a Hugging Face Dataset repository.
for visibility cc'ing: @sayakpaul
currently, the eval step consists of
the two sub-parts should be separated. Also, in order for Gemini evaluation to evaluate on the batch inferenced outputs, the batch inferenced outputs should be stored in a Hugging Face Dataset repository.