These docs are outdated! Please check out
Titan Takeoff 🛫 Titan Train 🎓 Titan Optimise ✨
Titan Takeoff 🛫: Inference Server
What does it do?
Quickly experiment with inferencing different LLMs
Create inference servers that are local and private (think HF Inference Servers but local)
Supported models: Most OS Generative model architectures
Titan Train 🎓: Finetuning Service
What does it do?
Fine-tuning of language models
Using QLoRA for super efficient training
Super simple, only a few lines of code
Don't worry about infrastructure - all hosted by TitanML
Supported models: Both generative and non-generative language models
Titan Optimise ✨: Knowledge Distillation
What does it do?
Compression of Natural Language Understanding tasks
Helps when latency, memory, or cost is a severe bottleneck
Uses the latest compression techniques like pruning & knowledge distillation for non-generative tasks
Supported models: