migtissera/Tess-34B-v1.4

TEXT GENERATIONConcurrency Cost:2Model Size:34BQuant:FP8Ctx Length:32kPublished:Dec 5, 2023License:yi-34bArchitecture:Transformer0.0K Cold

Tess-34B-v1.4 is a 34 billion parameter general-purpose large language model developed by migtissera, built upon the Yi-34B-200K base architecture. This model is designed for broad applicability across various language tasks, featuring a substantial 32768 token context window. It aims to serve as a versatile foundation for diverse natural language processing applications.

Loading preview...

Tess-34B-v1.4 Overview

Tess-34B-v1.4, part of the "Tesoro" (Treasure) series by migtissera, is a general-purpose large language model. It is based on the Yi-34B-200K architecture, providing a robust foundation for its capabilities. With 34 billion parameters, it offers significant capacity for understanding and generating human-like text.

Key Capabilities

  • General Purpose: Designed for a wide array of natural language processing tasks.
  • Large Context Window: Features a substantial 32768 token context length, allowing it to process and generate longer, more coherent texts and maintain context over extended conversations or documents.
  • Yi-34B Base: Leverages the strengths of the Yi-34B-200K base model, known for its strong performance in various benchmarks.

Prompt Format

The model utilizes a straightforward prompt format, making it easy to integrate into applications:

SYSTEM: <ANY SYSTEM CONTEXT>
USER: 
ASSISTANT:

This structure clearly delineates system instructions, user input, and the expected assistant response, facilitating controlled and predictable interactions.