During the month, contributed to the huggingface/peft repository by extending Llama-Adapters to support GPT2 models, focusing on enabling more efficient fine-tuning workflows. Developed the AdaptedAttentionGPT class and updated configuration logic to address GPT2-specific requirements, allowing the adaption prompt technique to be applied to GPT2 architectures. This work centered on model adaptation and compatibility, leveraging skills in PyTorch, Transformer models, and Python to deliver the new feature. No major bug fixes were reported during this period, as efforts were concentrated on expanding feature support and validating the impact of these enhancements within the context of large language model fine-tuning.