AI/ML LAB

Factor	Approximate Weight (%)
Diverse training language	30
Model size	15
Fine-tuning	15
Regularization	10
Optimizer and learning rate	10
Context size	10
Libraries	5
Model architecture	3
Model initialization	2

Implement Vicuna (ChatGPT)

• Download LLAMA model (LLM model) :

magnet:?xt=urn:btih:b8287ebfa04f879b048d4d4404108cf3e8014352&dn=LLaMA

• Update model :

https://github.com/lm-sys/FastChat#vicuna-weights

• Code :

https://github.com/lm-sys/FastChat