gemma-7b-it (Keras 3, bf16)

Pure-Keras 3 conversion of google/gemma-7b-it for kerasformers. Distributed under the Gemma license.

This repo holds the converted model weights and tokenizer.json.

from kerasformers.models.gemma import GemmaGenerate, GemmaTokenizer
model = GemmaGenerate.from_weights("gemma-7b-it")
tokenizer = GemmaTokenizer.from_weights("gemma-7b-it")