The jujuloaiza/Qwen3-1.7B-profilerchatbot is a 1.7 billion parameter language model, fine-tuned from Qwen/Qwen3-1.7B using QLoRA. This model is specifically trained on the 'jujuloaiza/profilerchatbot' dataset, making it specialized for chatbot interactions related to profiling. It serves as a test model for educational purposes within the CS-394/594 class at DigiPen.
Loading preview...
Model Overview
The jujuloaiza/Qwen3-1.7B-profilerchatbot is a specialized language model, fine-tuned from the base Qwen/Qwen3-1.7B architecture. This model leverages QLoRA (4-bit) for efficient supervised fine-tuning, making it a compact yet focused solution for specific conversational tasks.
Key Characteristics
- Base Model: Qwen3-1.7B, a 1.7 billion parameter model.
- Fine-tuning Method: Utilizes QLoRA with a rank of 16 and an alpha of 32, trained over 3 epochs with a learning rate of 0.0002.
- Specialized Dataset: Fine-tuned on the
jujuloaiza/profilerchatbotdataset, indicating a focus on chatbot functionalities related to profiling.
Intended Use
This model is primarily developed as a test model for academic purposes, specifically for the CS-394/594 class at DigiPen. Its fine-tuning on a profiling-related dataset suggests its utility in exploring and developing chatbot applications within that domain. Developers can use this model to understand the impact of specialized fine-tuning on a base LLM for targeted conversational AI tasks.