varshini2305

FEAT: Remove dependency on fastchat for model conversation templates

1

Replace FastChat’s custom prompt logic with Hugging Face’s apply_chat_template() and tokenizer_config.json. - Enable use_fast = True in the tokenizer. - Update _update_ids() in `pyrit/auxiliary_attacks/gcg/attack/base/attack_manager.py` to call apply_chat_template(), generating model-specific prompts...