About the Apollo-1 Models
Apollo-1-2B: 2 billion parameter model by Noema Research, designed for fast and quick infrencing
Apollo-1-4B: 4 billion parameter model by Noema Research, optimisd for efficient conversation and text generation
Apollo-1-8B: 8 billion parameter model by Noema Research, offering enhanced capabilities and better performance for complex tasks
All models are designed for conversational AI and support various text generation tasks. The 8B model provides more sophisticated responses but requires more computational resources.
This Space uses ZeroGPU for efficient GPU allocation across both model sizes.