Gemma support new

[ZHIHANCHEN03]

1. need add_generation_prompt for Gemma to generate good response
2. limit the response size to make sure the response is efficient
3. no response_start_key is added since Gemma will not response correctly according to the key, then JSON format is not supported
4. In prompt, input context is set to name as current context to make sure that Gemma and read the prompt correctly