migtissera/Tess-2.0-Yi-34B-200K

TEXT GENERATIONConcurrency Cost:2Model Size:34BQuant:FP8Ctx Length:32kPublished:Apr 1, 2024License:yi-34bArchitecture:Transformer0.0K Cold

Tess-2.0-Yi-34B-200K is a 34 billion parameter general-purpose large language model developed by migtissera, built upon the 01-ai/Yi-34B-200K base architecture. This model is designed for broad applications, leveraging its substantial parameter count and a 200K token context window for comprehensive understanding and generation. It is an uncensored model, offering flexibility for diverse conversational and text generation tasks.

Loading preview...

Tess-2.0-Yi-34B-200K: A General-Purpose LLM

Tess-2.0-Yi-34B-200K, part of the "Tesoro" (Treasure) series by migtissera, is a 34 billion parameter large language model built on the 01-ai/Yi-34B-200K base. It is designed as a general-purpose model, capable of handling a wide range of language tasks.

Key Characteristics

  • Base Model: Utilizes the robust 01-ai/Yi-34B-200K architecture.
  • Parameter Count: Features 34 billion parameters, enabling strong language understanding and generation capabilities.
  • Context Window: Supports a 200K token context length, allowing for processing and generating longer, more complex texts.
  • Prompt Format: Employs a clear SYSTEM: USER: ASSISTANT: prompt structure for structured interactions.
  • Uncensored Nature: This model is uncensored, providing unfiltered responses, which users should be aware of regarding potential content generation.

Limitations and Considerations

Users should be aware that while the model aims for accuracy, it may occasionally produce inaccurate or misleading information. Despite efforts in refining pretraining data, there is a possibility of generating inappropriate, biased, or offensive content due to its uncensored nature. Caution and cross-verification of information are advised when using this model.