diff --git a/README.rst b/README.rst index 8b8ac14..2c2d6b1 100644 --- a/README.rst +++ b/README.rst @@ -106,6 +106,8 @@ To interact with the various language models, you can use the following commands - For Together Solar, send a message with ``together/solar`` and include your prompt. - For Groq Mixtral, send a message with ``groq/mixtral`` and include your prompt. - For Groq Llama-2, send a message with ``groq/llama2`` and include your prompt. +- For Groq Llama-3, send a message with ``groq/llama3`` and include your prompt. +- For Groq Gemma, send a message with ``groq/gemma`` and include your prompt. - For vLLM OpenChat, send a message with ``vllm/openchat`` and include your prompt. - For vLLM OpenHermes, send a message with ``vllm/openhermes`` and include your prompt. - For Dall-e-3, send a message with ``dall-e-3`` and include your prompt. diff --git a/app.py b/app.py index c8aedf1..0349733 100644 --- a/app.py +++ b/app.py @@ -50,6 +50,8 @@ system_users = [ "mistralai/Mistral-7B-Instruct-v0.1", "mixtral-8x7b-32768", "llama2-70b-4096", + "llama3-70b-8192", + "gemma-7b-it", "openchat/openchat-3.5-1210", "openchat/openchat-3.5-0106", "upstage/SOLAR-10.7B-Instruct-v1.0", @@ -360,6 +362,20 @@ def handle_message(data): room.name, model_name="llama2-70b-4096", ) + if "groq/llama3" in data["message"]: + gevent.spawn( + chat_groq, + data["username"], + room.name, + model_name="llama3-70b-8192", + ) + if "groq/gemma" in data["message"]: + gevent.spawn( + chat_groq, + data["username"], + room.name, + model_name="gemma-7b-it", + ) if "vllm/openchat" in data["message"]: gevent.spawn( chat_gpt, @@ -908,6 +924,7 @@ def chat_together( def chat_groq(username, room_name, model_name="mixtral-8x7b-32768"): + # https://console.groq.com/docs/models _limit = 15 if "mixtral" in model_name: _limit = 50