Alignment-Lab-AI/Scrollplay
TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:4kTool Calling:SupportedPublished:Oct 31, 2024Architecture:Transformer0.0K Featherless Exclusive Cold
Alignment-Lab-AI/Scrollplay is a 7 billion parameter language model with a 4096 token context length, created by Alignment-Lab-AI using the breadcrumbs_ties merge method. It is based on tavtav/eros-7b-test and incorporates Nexusflow/Starling-LM-7B-beta. This model is designed for general language tasks, leveraging the combined strengths of its merged components.
Loading preview...
Overview
Alignment-Lab-AI/Scrollplay is a 7 billion parameter language model developed by Alignment-Lab-AI. It was created using the breadcrumbs_ties merge method via mergekit, combining the strengths of multiple pre-trained models. The base model for this merge was tavtav/eros-7b-test, and it also integrated Nexusflow/Starling-LM-7B-beta.
Key Capabilities
- Merged Architecture: Leverages the
breadcrumbs_tiesmethod to combine different model architectures, potentially enhancing performance across various tasks. - 7 Billion Parameters: Offers a balance between performance and computational efficiency, suitable for a range of applications.
- Foundation on Established Models: Built upon well-regarded base models like
tavtav/eros-7b-testandNexusflow/Starling-LM-7B-beta, inheriting their general language understanding and generation capabilities.
Good for
- General Text Generation: Suitable for tasks requiring coherent and contextually relevant text output.
- Experimentation with Merged Models: Provides a practical example of a model created using advanced merging techniques, useful for researchers and developers exploring model fusion.
- Applications requiring a 7B model: Offers a robust option for use cases where a 7 billion parameter model fits the performance and resource constraints.