Xiaojian9992024/Llama3.1-8B-ExtraMix

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Feb 23, 2025Architecture:Transformer0.0K Featherless Exclusive Cold

Xiaojian9992024/Llama3.1-8B-ExtraMix is an 8 billion parameter language model based on the Llama 3.1 architecture, created by Xiaojian9992024 using the TIES merge method. This model combines several Llama 3.1 variants, including Llama-3.1-8B-Instruct, Fino1-8B, and Dobby-Mini-Unhinged-Llama-3.1-8B, to enhance its overall capabilities. With a context length of 32768 tokens, it is designed for general-purpose language tasks, leveraging the strengths of its merged components.

Loading preview...

Model Overview

Xiaojian9992024/Llama3.1-8B-ExtraMix is an 8 billion parameter language model built upon the robust Llama 3.1 architecture. This model was developed by Xiaojian9992024 using the TIES merge method via mergekit, combining the strengths of multiple specialized Llama 3.1-based models.

Key Characteristics

  • Base Model: Utilizes meta-llama/Llama-3.1-8B-Instruct as its primary foundation.
  • Merged Components: Integrates SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B, TheFinAI/Fino1-8B, and meta-llama/Llama-3.1-8B to create a more versatile model.
  • Merge Method: Employs the TIES (Trimmed, Iterative, Extrapolated, and Scaled) merging technique, as detailed in the TIES paper, to combine the weights of the constituent models effectively.
  • Parameter Count: Features 8 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports a substantial context window of 32768 tokens, suitable for processing longer inputs and maintaining conversational coherence.

Intended Use Cases

This model is suitable for a broad range of general-purpose language tasks, benefiting from the diverse capabilities inherited from its merged components. Developers can leverage its enhanced instruction-following and general reasoning abilities for applications requiring robust language understanding and generation.