Using the fastest inference system Groq with Elephas
Groq AI provides fastest inference models, i.e responses are generated at a faster speed. They have some of the popular AI models hosted, including,
- Llama 3 70B
- Llama 3 7B
- Mixtral 8x 8B
- Gemma 7B
Here is the pricing info,
$.59 for Llama 3 70B, one of the powerful open source models. Here are the details from Meta’s launch page https://ai.meta.com/blog/meta-llama-3/
Llama 3 provided better response for English content than GPT-3.5 Turbo model in some tests.
Creating an API key with Groq
Visit https://console.groq.com/login and create your new account.
then visit https://console.groq.com/keys to set up a new key.
Then you can fill that API key under Elephas → Preferences → AI Providers, select “Groq”, enter the API key you just created.
Then you can use the models provided by Groq AI in Chat Settings and Cost & Accuracy parts underPreferences → General
Did this answer your question?
😞
😐
🤩