Bibliography (7):

1. GPT-3: Language Models are Few-Shot Learners

2. Attention Is All You Need

3. RoBERTa: A Robustly Optimized BERT Pretraining Approach

4. DeBERTa: Decoding-enhanced BERT with Disentangled Attention

5. Language Models are Unsupervised Multitask Learners

6. https://github.com/microsoft/LoRA

7. Wikipedia Bibliography:

   1. https://en.wikipedia.org/wiki/Stochastic_gradient_descent#Adam  :

      https://en.wikipedia.org/wiki/Stochastic_gradient_descent#Adam