Alpaca + Gemma2 9b Unsloth 2x faster

Is Gemma-9b really a 9b? Just remembered than due to the 256k tokenizer and other design choices, the previous 7b was already a 9b

The gemma-2-9b-it model is a lightweight, state-of-the-art open model from Google It is part of the Gemma family of text-to-text, decoder-only

gemmasutra 9b Local Gemma - Run Gemma-2 Locally in Python, Fast 838 views · 2 Gemma 2

789bkk Google has released two new models under the Gemma 2 series, featuring 9 billion and 27