dark-pen/apodex-1.0-4B-SFT-rebased
dark-pen/apodex-1.0-4B-SFT-rebased is a 4.5 billion parameter language model, rebased from Qwen/Qwen3.5-4B-Base and apodex/Apodex-1.0-4B-SFT using the Arcee Fusion method. This model is designed for general text generation tasks, leveraging its merged architecture to combine the strengths of its base models. It supports a context length of 32768 tokens, making it suitable for applications requiring extensive context understanding.
Loading preview...
Model Overview
dark-pen/apodex-1.0-4B-SFT-rebased is a 4.5 billion parameter language model, created through a merge of Qwen/Qwen3.5-4B-Base and apodex/Apodex-1.0-4B-SFT. This merge was performed using the Arcee Fusion method via LazyMergekit, aiming to combine the capabilities of its constituent models.
Key Characteristics
- Parameter Count: 4.5 billion parameters, offering a balance between performance and computational efficiency.
- Context Length: Supports a substantial context window of 32768 tokens, enabling the model to process and generate longer sequences of text while maintaining coherence.
- Base Models: Built upon the robust
Qwen3.5-4B-Basearchitecture and fine-tuned withApodex-1.0-4B-SFT, suggesting a foundation for general-purpose language understanding and generation.
Usage Considerations
This model is suitable for various text generation tasks where a moderate-sized model with a large context window is beneficial. Developers can integrate it using standard Hugging Face transformers library pipelines, as demonstrated in the provided usage example. Its rebased nature implies an attempt to enhance or refine the original models' performance through merging techniques.