vanillaOVO/supermario_v1

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Jan 24, 2024License:apache-2.0Architecture:Transformer Open Weights Cold

vanillaOVO/supermario_v1 is a 7 billion parameter language model created by vanillaOVO through a DARE merge using MergeKit. This model combines NeuralBeagle14-7B and Turdus, leveraging their pre-trained capabilities. With a 4096-token context length, it is designed for general language understanding and generation tasks, inheriting characteristics from its merged components.

Loading preview...

Model Overview

vanillaOVO/supermario_v1 is a 7 billion parameter language model developed by vanillaOVO. It was constructed using the DARE merging technique via MergeKit, combining the strengths of two distinct pre-trained models.

Key Components

This model is a merge of:

  • NeuralBeagle14-7B: A 7B parameter model known for its general language capabilities.
  • Turdus: Another pre-trained model contributing to the merged architecture.

Capabilities

As a merged model, supermario_v1 inherits the combined linguistic understanding and generation abilities of its constituent models. With a context length of 4096 tokens, it is suitable for a range of natural language processing tasks.

Use Cases

This model is generally applicable for tasks requiring text generation, summarization, question answering, and other language-based applications, benefiting from the diverse training data of its merged components.