ChickaQ-Large is a 1.8 billion parameter language model from the ChickaQ family, created by Chickaboo. This model is a merge of pre-trained language models, specifically integrating Qwen/Qwen1.5-1.8B-Chat with vilm/Quyen-Mini-v0.1 as its base. Utilizing the TIES merge method, ChickaQ-Large offers a 32768 token context length, making it suitable for applications requiring efficient processing of longer sequences.
Loading preview...
ChickaQ-Large: A Merged Language Model
ChickaQ-Large is a 1.8 billion parameter model within the ChickaQ family, developed by Chickaboo. It is a product of a strategic merge of pre-trained language models, leveraging the TIES merge method.
Merge Details
This model was constructed using vilm/Quyen-Mini-v0.1 as its foundational base model. It integrates capabilities from Qwen/Qwen1.5-1.8B-Chat, with a specific configuration that weighted the Qwen model at 0.5 during the merge process. The merge was performed using mergekit, ensuring a normalized float16 dtype for efficient operation.
Key Characteristics
- Parameter Count: 1.8 billion parameters, offering a balance between performance and computational efficiency.
- Context Length: Supports a substantial 32768 tokens, enabling the processing of extensive inputs and generating longer, coherent outputs.
- Merge Method: Utilizes the TIES merge method, known for its effectiveness in combining different model strengths.
Ideal Use Cases
ChickaQ-Large is well-suited for developers looking for a compact yet capable language model that benefits from the combined strengths of its constituent models. Its significant context window makes it particularly useful for tasks involving:
- Summarization of long documents.
- Extended conversational AI applications.
- Code generation or analysis requiring a broad contextual understanding.