- Learned to build GPT-2 architecture from scratch, understanding each component like tokenization, attention, and transformer blocks.
- Gained hands-on experience in training language models using PyTorch and managing datasets efficiently.
- Explored key NLP concepts like positional encoding, causal masking, and text generation techniques.
- Developed debugging and optimization skills critical for real-world AI model deployment.
- This experience strengthens my profile for Generative AI, NLP engineering, and research-based AI product development roles.
Rajadhurairajendhiran123/gpt_scratch
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|