migtissera/Tess-XS-v1.1

TEXT GENERATIONConcurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Nov 22, 2023License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

Tess-XS-v1.1 by migtissera is an experimental 7 billion parameter general-purpose large language model based on the Mistral-7B architecture. This version has been deprecated in favor of a more stable release. It was designed as part of the Tessoro/Tessoso series for broad language understanding and generation tasks.

Loading preview...

Model Overview

Tess-XS-v1.1 is an experimental 7 billion parameter general-purpose large language model developed by migtissera, built upon the Mistral-7B base architecture. This model is part of the Tessoro/Tessoso series, designed for a wide range of language processing tasks. It utilizes a specific prompt format for interaction, expecting SYSTEM, USER, and ASSISTANT roles.

Key Characteristics

  • Base Model: Built on the Mistral-7B architecture.
  • Parameter Count: 7 billion parameters.
  • Context Length: Supports an 8192 token context window.
  • Prompt Format: Adheres to a SYSTEM: <ANY SYSTEM CONTEXT>\nUSER: \nASSISTANT: structure for conversational turns.

Important Note

This particular version, Tess-XS-v1.1, is explicitly marked as experimental and deprecated by its creator. Users are advised to utilize the stable release, Tess-XS-v1.3-yarn-128K, for production or reliable applications. The model's primary purpose was to serve as a general-purpose LLM within the Tess series.

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