Run Llama,Qwen,Gemma,Mistral, any warm/cold LLM. No GPU req.
Interact with multiple chatbots simultaneously
Generate text responses in a chat interface
Interact with a Korean language and vision assistant
Chat with a conversational AI
Chat with a Japanese language model
Google Gemini Playground | ReffidGPT Chat
Chat Long COT model that uses tags
Generate chat responses using Llama-2 13B model
mistralai/Mistral-7B-Instruct-v0.3
Have a video chat with Gemini - it can see you ⚡️
Generate text and speech from audio input
Example on using Langfuse to trace Gradio applications.
Serverless TextGen Hub is a serverless platform designed to run advanced language models such as Llama, Qwen, Gemma, and Mistral. It allows users to deploy and interact with these models without requiring GPU support, making it accessible and cost-effective. The platform is tailored for creating customizable AI assistants that can be integrated into various applications, enabling seamless chatbot functionality and text generation capabilities.
What models are supported by Serverless TextGen Hub?
Serverless TextGen Hub supports a variety of models, including Llama, Qwen, Gemma, Mistral, and other warm/cold LLMs.
Do I need a GPU to run Serverless TextGen Hub?
No, Serverless TextGen Hub is designed to operate without requiring GPU support, making it accessible on standard computing resources.
How do I obtain API keys for the models?
API keys or model access tokens can be obtained from the respective model providers. Follow their instructions to set up and use the keys within Serverless TextGen Hub.