louisbrulenaudet/Maxine-7B-0401-stock

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:8kPublished:Apr 1, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Maxine-7B-0401-stock is a 7 billion parameter language model developed by louisbrulenaudet, built using a 'model_stock' merge method. It combines several base models, including OpenPipe/mistral-ft-optimized-1227, MTSAIR/multi_verse_model, rwitz/experiment26-truthy-iter-0, and MaziyarPanahi/Calme-7B-Instruct-v0.2, with OpenPipe/mistral-ft-optimized-1227 serving as the base. This model is designed for general text generation tasks, leveraging its merged architecture to potentially enhance performance across various applications.

Loading preview...

Maxine-7B-0401-stock: A Merged 7B Language Model

Maxine-7B-0401-stock is a 7 billion parameter model developed by louisbrulenaudet, utilizing a unique 'model_stock' merge method. This approach combines the strengths of multiple pre-existing models to create a new, potentially more robust, and versatile language model. The base model for this merge is OpenPipe/mistral-ft-optimized-1227, indicating a foundation rooted in the Mistral architecture.

Key Characteristics

  • Merged Architecture: Built from a combination of four distinct models: OpenPipe/mistral-ft-optimized-1227, MTSAIR/multi_verse_model, rwitz/experiment26-truthy-iter-0, and MaziyarPanahi/Calme-7B-Instruct-v0.2.
  • Base Model: Leverages OpenPipe/mistral-ft-optimized-1227 as its foundational component.
  • Parameter Count: A compact 7 billion parameters, making it suitable for applications where computational resources are a consideration.
  • Developer: Created by louisbrulenaudet, who also developed the highly-ranked Pearl-34B-ties model.

Potential Use Cases

  • General Text Generation: Capable of various text generation tasks due to its diverse merged components.
  • Experimentation with Merged Models: Provides a practical example of the 'model_stock' merging technique for researchers and developers interested in model fusion.
  • Applications requiring a 7B model: Suitable for scenarios where a balance between performance and efficiency is desired.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p