[Feature]: Add support for Gemma-7B model from Groq

[haseeb-heaven]

The Feature

Groq now supports Gemma-7b model and the model name is gemma-7b-it please add the support for this.
And this is much more faster like 600 Tokens/Second

Here is sample code from their Docs.

from groq import Groq

client = Groq()
completion = client.chat.completions.create(
    model="gemma-7b-it",
    messages=[
        {
            "role": "user",
            "content": ""
        }
    ],
    temperature=0.1,
    max_tokens=8192,
    top_p=1,
    stream=True,
    stop=None,
)

for chunk in completion:
    print(chunk.choices[0].delta.content or "", end="")

Motivation, pitch

Much faster models than other Groq models and also smaller in size.

Twitter / LinkedIn details

No response

[ishaan-jaff]

We already support this https://docs.litellm.ai/docs/providers/groq

• was this not working for you @haseeb-heaven ?

[ishaan-jaff]

https://docs.litellm.ai/docs/providers/groq

[haseeb-heaven]

We already support this https://docs.litellm.ai/docs/providers/groq

• was this not working for you @haseeb-heaven ?

But Gemma is not working from Groq

[haseeb-heaven]

Working now thanks