migtissera/Tess-7B-v1.4

TEXT GENERATIONConcurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Dec 4, 2023License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

migtissera/Tess-7B-v1.4 is a 7 billion parameter general-purpose large language model, built upon the Mistral-7B architecture. This model is designed for broad applicability across various natural language processing tasks. With an 8192-token context length, it offers robust performance for general text generation and understanding.

Loading preview...

Overview

Tess-7B-v1.4, short for Tesoro (Italian for Treasure), is a 7 billion parameter general-purpose large language model developed by migtissera. It is built on the Mistral-7B base architecture, providing a solid foundation for diverse NLP applications. This model is designed to handle a wide range of tasks, making it a versatile tool for developers.

Key Capabilities

  • General-purpose text generation: Capable of producing coherent and contextually relevant text for various prompts.
  • Broad applicability: Suitable for a wide array of natural language processing tasks.
  • Mistral-7B base: Leverages the efficient and performant architecture of Mistral-7B.
  • 8192-token context length: Supports processing and generating longer sequences of text, enhancing its utility for complex queries.

Prompt Format

The model utilizes a specific prompt format to ensure optimal interaction:

SYSTEM: <ANY SYSTEM CONTEXT>
USER: 
ASSISTANT:

This structured format helps in providing clear instructions and context to the model, improving response quality.

Good For

  • General text generation and completion tasks.
  • Applications requiring a versatile language model with a reasonable context window.
  • Developers looking for a Mistral-based model for various NLP projects.

Finetunes
6 models