mergekit-community/ohnoes_now_nsfw

TEXT GENERATIONPricing:Input $0.2 / Cached $0.028 / Output $0.32Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Dec 31, 2024Architecture:Transformer0.0K Featherless Exclusive Cold

The mergekit-community/ohnoes_now_nsfw is an 8 billion parameter language model, merged using the Model Stock method. It combines FreedomIntelligence/HuatuoGPT-o1-8B with several LoRAs, including those focused on long story generation, roleplay, psychology, and human sexuality. This model is designed for applications requiring nuanced understanding and generation of content related to these specific domains, offering a 32768 token context length.

Loading preview...

Model Overview

The mergekit-community/ohnoes_now_nsfw is an 8 billion parameter language model created through a merge using the mergekit tool. It leverages the Model Stock merge method, building upon FreedomIntelligence/HuatuoGPT-o1-8B as its base, combined with grimjim/Llama-3-Instruct-abliteration-LoRA-8B.

Key Components and Focus Areas

This model integrates several specialized LoRAs (Low-Rank Adaptations) to enhance its capabilities across specific domains. The merged components include:

  • Long Story Generation: Incorporates Blackroot/Llama-3-LongStory-LORA and vincentyandex/lora_llama3_chunked_novel_bs128 to improve narrative coherence and length.
  • Roleplay and Instruction Following: Integrates ResplendentAI/Llama3_RP_ORPO_LoRA for enhanced role-playing capabilities and adherence to instructions.
  • Specialized Knowledge: Includes surya-narayanan/professional_psychology and surya-narayanan/human_sexuality to provide a deeper understanding and generation capacity for topics related to psychology and human sexuality.

Use Cases

Given its specialized training, this model is particularly well-suited for:

  • Generating extended narratives and creative writing.
  • Engaging in detailed role-playing scenarios.
  • Applications requiring nuanced discussions or content generation related to psychology and human sexuality.
  • Tasks benefiting from a broad context window of 32768 tokens.

Finetunes
1 models