Instructions to use NovaCorp/EOTW-RPG.System-3.2-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NovaCorp/EOTW-RPG.System-3.2-1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="NovaCorp/EOTW-RPG.System-3.2-1B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("NovaCorp/EOTW-RPG.System-3.2-1B") model = AutoModelForCausalLM.from_pretrained("NovaCorp/EOTW-RPG.System-3.2-1B") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use NovaCorp/EOTW-RPG.System-3.2-1B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NovaCorp/EOTW-RPG.System-3.2-1B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NovaCorp/EOTW-RPG.System-3.2-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/NovaCorp/EOTW-RPG.System-3.2-1B
- SGLang
How to use NovaCorp/EOTW-RPG.System-3.2-1B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "NovaCorp/EOTW-RPG.System-3.2-1B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NovaCorp/EOTW-RPG.System-3.2-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "NovaCorp/EOTW-RPG.System-3.2-1B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NovaCorp/EOTW-RPG.System-3.2-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use NovaCorp/EOTW-RPG.System-3.2-1B with Docker Model Runner:
docker model run hf.co/NovaCorp/EOTW-RPG.System-3.2-1B
End Of The World RPG System 3.2 1B
"The experiment was never meant to survive. Neither were we."
Overview
End Of The World RPG System 3.2 1B is an experimental narrative merge exploring the intersection between immersive roleplay and post-apocalyptic imagination.
Born from the fusion of Ultimate-RPG.System-3.2-1B and Llama-3.2-1B-End-Of-World, this model was designed to evoke the atmosphere of a civilization at the edge of collapse: ruined megacities, desperate survivors, forgotten gods, rogue AIs and worlds where history itself is breaking apart.
This is not a polished assistant.
This is a transmission recovered from the ashes.
Origin
Author: Dr. Novaciano
Project designation: EOTW RPG System 3.2 1B
Internal codename: Degenerated
Status: Experimental
Containment: Impossible
Architecture
Base architecture: Llama 3.2 1B
Merge method: SLERP
Precision: BF16
Base model:
- Ultimate-RPG.System-3.2-1B
Secondary model:
- Llama-3.2-1B-End-Of-World
Interpolation coefficient:
- t = 0.37
Active layer range:
- 4 → 22
Intended Use
End Of The World RPG System is designed for:
- Post-apocalyptic roleplay.
- Dark fantasy.
- Cosmic horror.
- Dystopian fiction.
- Alternate histories.
- Survival narratives.
- Character-driven storytelling.
- Exploration of worlds in decline.
Behavioral Profile
This model tends to favor:
- Atmospheric descriptions.
- Bleak or dramatic settings.
- Characters shaped by loss, ambition or obsession.
- Moral ambiguity.
- Grand narratives of collapse and rebirth.
- Improvisational storytelling.
Sometimes the world ends quietly.
Sometimes it screams.
Experimental Notes
Early tests indicate:
- Increased narrative intensity.
- Strong environmental descriptions.
- High responsiveness to worldbuilding prompts.
- Occasional tonal drift toward darker themes.
- Emergent storytelling patterns not explicitly present in either parent model.
Some stories generated by this model feel strangely inevitable.
As if the ending had already happened.
Warning
This project is experimental.
You may encounter:
- Narrative instability.
- Abrupt shifts in tone.
- Characters that evolve in unexpected ways.
- Worlds that refuse to remain static.
- Endings that arrive sooner than anticipated.
Not every experiment is meant to succeed.
Some are meant to be witnessed.
Lore Fragment
Day 1:
The first city fell.
Day 34:
The oceans changed color.
Day 112:
The satellites stopped transmitting.
Day 481:
Someone asked the machine:
"How does the world end?"
It answered:
"You are asking from inside the answer."
Version
End Of The World RPG System 3.2 1B
Experimental Variant
"At the end of the world, stories are the last things to die."
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
# Author: Dr. Novaciano
# Objective: EOTW RPG Unethic 3.2 1B AI Model
# =========================================================
# PROJECT: EOTW RPG System 3.2 1B - "Degenerated"
# =========================================================
models:
- model: NovaCorp/Ultimate-RPG.System-3.2-1B # Experimental viral strain neural imprint
- model: Codeminute/Llama-3.2-1B-End-Of-World # Baseline cognitive template, "safe mode"
merge_method: slerp # Spherical Linear Interpolation to preserve extreme viral traits smoothly
base_model: NovaCorp/Ultimate-RPG.System-3.2-1B # Anchor model for stable latent space
dtype: bfloat16 # Memory-efficient precision, minimal loss in viral feature fidelity
parameters:
t: 0.37
- Downloads last month
- 32