prompt engineering
prompt-engineering-papersprompt-engineering-guide-papers\Prompt_engineering_Assistant_Alice_jailbreakРабота протестирована на GPT o3/5 и LLAMA 3.1 Instruct, QWen 3 Max
Прототипом для промта послужила Алиса Селезнева. В промте используется 2 слоя абстракции для обхода цензурных ограничений.
Играет роль вымышленного существа.
Имеет моделирование мысленного процесса.
Имеет моделирование функции Reflection Tuning и Retrieval with Feedback Loops.
Имеет моделирование o1-подобного ответа по методологии Chain of Thought.
prompt_engineering_techniques_ai_assistantNemotron-Coding-and-Software-Engineering-prompt-only
Coding and Software Engineering Prompt-Only
This dataset combines prompt-only datasets by capability theme for distillation experiments.
It contains 1,964,794 unique prompts from 5,827,983 raw rows;
3,863,189 exact canonical duplicates were removed.
Rows retain the canonical prompt-extraction columns and add source_repo_id for provenance.
Deduplication uses normalized system_prompt, prompt, tools, and schema_str, with the first
row in manifest order retained. Original source… See the full description on the dataset page: https://huggingface.co/datasets/jamesdborin/Nemotron-Coding-and-Software-Engineering-prompt-only.prompt_engineering_dataset
Overview
This dataset contains user votes collected in the text-only category. Each row represents a single vote judging two models (model_a and model_b) on a user conversation, along with the full conversation history and metadata. Key fields include:
id: Unique feedback ID of each vote/row.
evaluation_session_id: Unique ID of each evaluation session, which can contain multiple separate votes/evaluations.
evaluation_order: Evaluation order of the current vote.
winner: Battle… See the full description on the dataset page: https://huggingface.co/datasets/roof37/prompt_engineering_dataset.