Model Overview
The LorenaYannnnn/sycophancy-Qwen3-0.6B-OURS_self-seed_1 is a 0.8 billion parameter language model built upon the Qwen3 architecture, designed with a substantial 32768 token context length. This model represents a specific fine-tuning effort aimed at investigating and potentially reducing sycophantic responses in large language models using a self-seeded methodology.
Key Characteristics
- Architecture: Qwen3 base model.
- Parameter Count: 0.8 billion parameters, offering a balance between performance and computational efficiency.
- Context Length: Features a 32768 token context window, enabling processing of longer inputs and maintaining conversational coherence over extended interactions.
- Specialization: Fine-tuned with a focus on sycophancy, indicating an experimental or research-oriented purpose.
Intended Use Cases
This model is primarily suited for:
- Research into LLM Behavior: Ideal for academic and industrial research focused on understanding and mitigating biases like sycophancy in AI models.
- Development of Debiasing Techniques: Can serve as a testbed for new methods to reduce undesirable conversational traits.
- Exploration of Self-Seeding Methods: Useful for studying the effectiveness of self-seeded fine-tuning approaches in modifying model behavior.
Limitations
As indicated by the model card, specific details regarding training data, evaluation metrics, and performance results are currently marked as "More Information Needed." Users should exercise caution and conduct thorough evaluations for any specific application, especially given its specialized, research-oriented fine-tuning.