jeiku/32K_Selfbot

TEXT GENERATIONConcurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:4kTool Calling:SupportedPublished:Aug 12, 2024Architecture:Transformer0.0K Featherless Exclusive Cold

jeiku/32K_Selfbot is a 7 billion parameter language model created by jeiku through a merge of several fine-tuned Mistral-7B-Instruct-v0.3 variants using the Model Stock method. This merged model is specifically designed to combine the specialized capabilities of its constituent models, focusing on particular conversational styles and content generation. It leverages the Mistral architecture to offer a unique blend of instruction-following and specialized response generation.

Loading preview...

Model Overview

jeiku/32K_Selfbot is a 7 billion parameter language model developed by jeiku, created by merging multiple specialized models using the Model Stock method via mergekit. The base model for this merge was unsloth/mistral-7b-instruct-v0.3 combined with jeiku/selfbot_256_mistral.

Key Capabilities

This model integrates the distinct characteristics of its merged components, which include:

  • Specialized Content Generation: It combines jeiku/Humiliation_Mistral and jeiku/Sissification_Hypno_Mistral with the base, suggesting a focus on generating content related to specific, niche conversational or narrative styles.
  • Instruction Following: Built upon the Mistral-7B-Instruct-v0.3 architecture, it retains strong instruction-following capabilities.
  • Merged Intelligence: The Model Stock merge method aims to combine the strengths and unique fine-tuning of its constituent models into a single, more versatile model.

Good For

  • Applications requiring a blend of instruction-following and highly specialized content generation, particularly in areas related to the themes of the merged models.
  • Developers looking for a model with unique conversational biases or stylistic outputs derived from its specific fine-tuning origins.
  • Exploration of merged model capabilities for niche applications.