CoolFace
Modelpublic

N-Bot-Int/OpenElla3-Llama3.2A

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
1likes75downloads
Model Card

<a href="https://ibb.co/FbZyWMB7"><img src="https://raw.githubusercontent.com/ItsMeDevRoland/NexusBotWorkInteractives/refs/heads/main/image.webp" alt="image-1" border="0"></a>

Llama3.2 - OpenElla3A

  • —OpenElla, is a Llama3.2 3B Parameter Model, That is fine-tuned for Roleplaying purposes, even if it only have a limited Parameters. This is achieved through Series of Dataset Finetuning, using 2 Dataset with different Weight, Aiming to Counter Llama3.2's Generalist Approach and focusing On Specializing with Roleplaying and Acting.
  • —OpenElla3A Excells in Outputting RAW and UNCENSORED Output However LACKS THE PROPER TRAINING FOR OBIDIENCE, Due to this, OpenElla3 Model A Are Only Used for Training purposes, if you seek to train or Distill A Llama Model to Force it to generate Uncensored Content then please do so with care and ethical considerations
  • —OpenElla3B is
  • —Developed by: N-Bot-Int
  • —License: apache-2.0
  • —Parent Model from model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
  • —Sequential Trained from Model: N-Bot-Int/OpenElla3-Llama3.2A
  • —Dataset Combined Using: Mosher-R1(Propietary Software)
  • —OpenElla3B Is NOT YET RANKED WITH ANY METRICS
  • —Feel free to support by Emailing me: <link src="mailto:nexus.networkinteractives@gmail.com">nexus.networkinteractives@gmail.com</link>
  • —# Notice
  • —For a Good Experience, Please use
  • —Low temperature 1.5, minp = 0.1 and maxnew_tokens = 128
  • —# Detail card:
  • —Parameter
  • —3 Billion Parameters
  • —(Please visit your GPU Vendor if you can Run 3B models)
  • —Training
  • —500 steps
  • —Mixed-RP Startup Dataset
  • —200 steps
  • —PIPPA-ShareGPT for Increased Roleplaying capabilities
  • —150 steps(Re-fining)
  • —PIPPA-ShareGPT to further increase weight of PIPPA and to override the noises