[Model Request] Google Gemma 2B/7B

[dusty-nv]

⚙️ Request New Models

• Link to an existing implementation (e.g. Hugging Face/Github):
  • https://huggingface.co/google/gemma-2b
  • https://huggingface.co/google/gemma-7b
• Is this model architecture supported by MLC-LLM? (the list of supported models) NO

Additional context

Google has release a new series of models, which are purportedly 'better than llama-2-7b':

https://blog.google/technology/developers/gemma-open-models/

Given MLC's support for edge devices and that this includes a 2B SLM, I thought Gemma good to get on your radar awhile. llama.cpp already had support for it added this morning (ggerganov/llama.cpp#5631)

[tqchen]

#1805