activeDap/Qwen3-1.7B_hh_helpful
activeDap/Qwen3-1.7B_hh_helpful is a 2 billion parameter causal language model fine-tuned from Qwen/Qwen3-1.7B. This model was specifically trained using Supervised Fine-Tuning (SFT) on the activeDap/sft-hh-data dataset, which focuses on helpfulness. It is optimized for generating helpful and assistant-like responses, making it suitable for conversational AI and instruction-following tasks.
Loading preview...
Model Overview
activeDap/Qwen3-1.7B_hh_helpful is a 2 billion parameter language model derived from the Qwen/Qwen3-1.7B base architecture. It has undergone Supervised Fine-Tuning (SFT) using the activeDap/sft-hh-data dataset, which is designed to enhance the model's ability to provide helpful and informative responses.
Key Characteristics
- Base Model: Qwen/Qwen3-1.7B, a 2 billion parameter model.
- Fine-tuning: Utilizes Supervised Fine-Tuning (SFT) with the Transformers and TRL libraries.
- Dataset: Trained on
activeDap/sft-hh-data, focusing on helpfulness. - Training Configuration: Employed a batch size of 64 (across 4 GPUs), a learning rate of 2e-05, and a maximum sequence length of 512 tokens.
- Optimization: Uses
adamw_torch_fusedoptimizer and BF16 mixed precision for efficient training.
Intended Use Cases
This model is particularly well-suited for applications requiring an AI assistant that can generate helpful and coherent text based on user prompts. Its fine-tuning on a helpfulness-centric dataset suggests strong performance in instruction-following and conversational scenarios where the goal is to provide useful information or complete tasks as an assistant.