The g4me/QwenRolina3-Base-LR1e5-b32g2gc8-order-ppl-batch model is a 2 billion parameter language model, fine-tuned from Qwen/Qwen3-1.7B-Base. Developed by g4me, this model was trained using the TRL library with a specific SFT procedure. It is designed for general text generation tasks, leveraging its base architecture and fine-tuning for improved performance.
Loading preview...
Model Overview
This model, g4me/QwenRolina3-Base-LR1e5-b32g2gc8-order-ppl-batch, is a 2 billion parameter language model. It is a fine-tuned variant of the Qwen/Qwen3-1.7B-Base architecture, developed by g4me.
Key Capabilities
- Base Model: Built upon the robust Qwen3-1.7B-Base, providing a strong foundation for language understanding and generation.
- Fine-tuning: The model has undergone Supervised Fine-Tuning (SFT) using the TRL library, indicating a focus on specific task performance or instruction following.
- Context Length: Supports a substantial context length of 32768 tokens, allowing for processing and generating longer sequences of text.
Training Details
The training process utilized the TRL library (version 0.29.0) and Transformers (version 5.2.0), with PyTorch 2.8.0a0+34c6371d24.nv25.8. The training procedure involved SFT, suggesting an optimization for specific downstream applications or improved conversational abilities.
Potential Use Cases
- General Text Generation: Suitable for various text generation tasks, given its base model and fine-tuning.
- Exploration and Research: Can serve as a foundation for further fine-tuning or research into SFT methodologies on Qwen-based models.