Is your feature request related to a problem? Please describe.
I want the option to use Go to access Groq hosted models, due to their greater inference speed.

Describe the solution you'd like
I would like to suggest this project do two three things:

1. Use Groq's OpenAI Compatibility for minimal changes
2. Provide a list of Groq models for easy usage
3. Add basic documentation since this more of a side-feature with huge value than a main case.

Describe alternatives you've considered
This could be a new/different library, but I think it makes sense more sense to build on the work done by this project.

Additional context

• Groq's OpenAI Compatibility: https://console.groq.com/docs/openai

OpenAI Compatibility
Groq's APIs are designed to be compatible with OpenAI's, with the goal of making it easy to leverage Groq in applications you may have already built.

• Groq's Hosted Models: https://console.groq.com/docs/models

Supported Models
GroqCloud currently supports the following models:
LLaMA2-70b
Developer: Meta
Model Name: LLaMA2-70b-chat
Context Window: 4,096 tokens
API String: llama2-70b-4096
Mixtral-8x7b
Developer: Mistral
Model Name: Mixtral-8x7b-Instruct-v0.1
Context Window: 32,768 tokens
API String: mixtral-8x7b-32768
Gemma-7b-it
Developer: Google
Model Name: Gemma-7b-it
Context Window: 8,192 tokens
API String: gemma-7b-it

I'll submit a PR that outlines this change shortly.

EDIT FOR PR LINK: #683