flammenai/flammen13-mistral-7B

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Mar 25, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

flammenai/flammen13-mistral-7B is a 7 billion parameter language model created by flammenai, merged from nbeerbower/flammen12-mistral-7B and automerger/OgnoExperiment27-7B using the SLERP method. This model leverages the Mistral architecture and has a 4096 token context length. Its primary differentiator is its composition as a merge, aiming to combine the strengths of its constituent models for general language tasks.

Loading preview...

Model Overview

flammenai/flammen13-mistral-7B is a 7 billion parameter language model built upon the Mistral architecture, featuring a 4096 token context length. It was created by flammenai through a merge of two pre-trained models: nbeerbower/flammen12-mistral-7B and automerger/OgnoExperiment27-7B.

Merge Details

This model was constructed using the SLERP (Spherical Linear Interpolation) merge method, a technique often employed to combine the weights of different language models while preserving their learned representations. The merge process specifically combined all 32 layers from both base models.

Key Characteristics

  • Merged Architecture: Combines nbeerbower/flammen12-mistral-7B and automerger/OgnoExperiment27-7B to potentially inherit diverse capabilities.
  • Mistral Base: Benefits from the efficient and performant Mistral 7B foundation.
  • SLERP Method: Utilizes a sophisticated merging algorithm for weight interpolation.

Potential Use Cases

Given its merged nature and Mistral base, this model is suitable for a variety of general-purpose natural language processing tasks, including:

  • Text generation
  • Summarization
  • Question answering
  • Chatbot applications