biaofu-xmu/EAST-8B

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Apr 22, 2025License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

biaofu-xmu/EAST-8B is an 8 billion parameter language model developed by biaofu-xmu, serving as a checkpoint for the EAST research project. This model is designed to implement the methodologies described in its associated research paper, focusing on specific architectural or training innovations. With an 8192-token context length, it is suitable for research and development applications exploring the EAST framework.

Loading preview...

EAST-8B Model Overview

EAST-8B is an 8 billion parameter language model developed by biaofu-xmu, serving as a direct checkpoint for the EAST research project. This model is specifically designed to embody the architectural and training methodologies detailed in its accompanying research paper. It offers an 8192-token context length, making it suitable for tasks requiring substantial input or output sequences.

Key Characteristics

  • Research-Oriented: Primarily functions as an implementation of the EAST research framework.
  • 8 Billion Parameters: A moderately sized model, balancing performance with computational requirements.
  • 8192-Token Context Window: Supports processing of longer texts and complex queries.

Intended Use Cases

  • Academic Research: Ideal for researchers and developers interested in replicating or extending the EAST project's findings.
  • Methodology Exploration: Useful for understanding the practical application of the techniques described in the associated paper.
  • Experimental Development: Can be used as a base for further fine-tuning or architectural modifications within a research context.

For more detailed information and to access the source code, refer to the official GitHub repository.

Finetunes
1 models