[model support] Requesting support for Gemma 2

[sand-bit]

Requesting support for Gemma 2 27B/9B.

1. Sliding window attention, used every other layer
2. Logit soft capping (aka soft capping, so no flash attention support right now)
3. Possible tokenizer bugs in transformer implementation Investigate gemma 2 generation quality ggerganov/llama.cpp#8240 (comment) (See that issue for other discussions on tokenizer bugs. Maybe okay in Google's official Keras implementation?)

[james0zan]

As it is a dense model, we may currently not be able to run Gemma 2 faster than its official support. Thus, Gemma's support may not be available in the coming days.