Eric111/CatunaMayo

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Feb 15, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Eric111/CatunaMayo is a 7 billion parameter language model created by Eric111, formed by merging Eric111/caTUNABeagle and Eric111/AlphaMayo using the mergekit tool. This model leverages a slerp merge method to combine the strengths of its constituent models, offering a unique blend of their capabilities. It is designed for general language tasks, inheriting characteristics from its merged components.

Loading preview...

CatunaMayo: A Merged 7B Language Model

CatunaMayo is a 7 billion parameter language model developed by Eric111, created through a strategic merge of two existing models: Eric111/caTUNABeagle and Eric111/AlphaMayo. This merge was performed using the mergekit tool, specifically employing the slerp (spherical linear interpolation) method.

Key Characteristics

  • Architecture: A merged model combining two distinct base models.
  • Parameter Count: 7 billion parameters, suitable for a range of language generation and understanding tasks.
  • Merge Method: Utilizes slerp for combining model weights, with specific parameter adjustments for self-attention (self_attn) and multi-layer perceptron (mlp) layers, indicating a fine-tuned integration process.
  • Base Model: Eric111/caTUNABeagle served as the primary base for the merge operation.
  • Data Type: Configured to use bfloat16 for efficient computation.

Potential Use Cases

Given its merged nature, CatunaMayo is likely to exhibit a blend of the capabilities of its parent models. It is suitable for general-purpose natural language processing applications where a 7B parameter model offers a balance between performance and computational efficiency.