TareksGraveyard/Lascivious-LLaMa-70B

Hugging Face
TEXT GENERATIONConcurrent Unit Cost:4Model Size:70BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jan 28, 2025License:llama3.3Architecture:Transformer0.0K Featherless Exclusive Warm

TareksGraveyard/Lascivious-LLaMa-70B is a 70 billion parameter language model, merged using the SCE method with nbeerbower/Llama-3.1-Nemotron-lorablated-70B as its base. This model is specifically designed and merged to exhibit a strong proclivity for NSFW themes and content. It is intended for use cases requiring explicit or adult-oriented text generation, leveraging its 32768 token context length for detailed outputs.

Loading preview...

Model Overview

TareksGraveyard/Lascivious-LLaMa-70B is a 70 billion parameter language model created by TareksGraveyard. This model was developed using the SCE merge method, with nbeerbower/Llama-3.1-Nemotron-lorablated-70B serving as the base architecture. The primary goal of this merge was to enhance the model's inclination towards NSFW (Not Safe For Work) themes and content.

Key Characteristics

  • Parameter Count: 70 billion parameters, providing substantial generative capacity.
  • Context Length: Supports a context window of 32768 tokens, allowing for extended and detailed interactions.
  • Merge Method: Utilizes the SCE merge method for combining multiple pre-trained models.
  • Base Model: Built upon nbeerbower/Llama-3.1-Nemotron-lorablated-70B.
  • Merged Models: Incorporates several models known for their NSFW capabilities, including:
    • Nohobby/L3.3-Prikol-70B-v0.3
    • NeverSleep/Lumimaid-v0.2-70B
    • Sao10K/70B-L3.3-mhnnn-x1
    • Sao10K/L3.1-70B-Hanami-x1
    • SicariusSicariiStuff/Negative_LLAMA_70B

Intended Use Cases

This model is specifically designed for applications and research focusing on generating explicit, adult-oriented, or NSFW text. Its unique merging strategy aims to maximize its output in these specific content domains.