Instructions to use NovaCorp/Storytime-RPG.System-3.2-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NovaCorp/Storytime-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/Storytime-RPG.System-3.2-1B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NovaCorp/Storytime-RPG.System-3.2-1B")
model = AutoModelForCausalLM.from_pretrained("NovaCorp/Storytime-RPG.System-3.2-1B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NovaCorp/Storytime-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/Storytime-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/Storytime-RPG.System-3.2-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NovaCorp/Storytime-RPG.System-3.2-1B

SGLang

How to use NovaCorp/Storytime-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/Storytime-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/Storytime-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/Storytime-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/Storytime-RPG.System-3.2-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NovaCorp/Storytime-RPG.System-3.2-1B with Docker Model Runner:
```
docker model run hf.co/NovaCorp/Storytime-RPG.System-3.2-1B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Storytime RPG System 3.2 1B

"Every story begins with a question. This model asks what happens when the story begins asking questions back."

Overview

Storytime RPG System 3.2 1B is an experimental narrative merge combining the immersive roleplay capabilities of Ultimate-RPG.System-3.2-1B with the storytelling focus of storytime-llama3-1b-v2.

Designed as a compact but expressive narrative engine, Storytime RPG aims to blur the boundary between storyteller, character and world simulator. It excels at generating dynamic scenes, memorable characters and evolving narratives across a wide variety of genres.

This is not an assistant optimized for facts.

This is a machine that wants to tell stories.

Origin

Author: Dr. Novaciano

Project designation: Storytime RPG System 3.2 1B

Internal codename: Degenerated

Status: Experimental

Narrative containment: Unstable

Architecture

Base architecture: Llama 3.2 1B
Parameters: 1B
Merge method: SLERP
Precision: BF16

Parent Models

NovaCorp/Ultimate-RPG.System-3.2-1B
- Narrative RPG framework.
- Character consistency.
- Worldbuilding and roleplay.
thegr8lizzyator/storytime-llama3-1b-v2
- Storytelling specialization.
- Scene composition.
- Dialogue and pacing.

Merge Configuration

Interpolation coefficient:
- t = 0.45
Active layer range:
- 4 → 22
Shared embeddings:
- Enabled

Intended Use

Storytime RPG System is designed for:

Interactive storytelling.
Roleplay sessions.
Fantasy and science fiction.
Horror and mystery.
Character creation.
Worldbuilding.
Visual novel scripting.
Dynamic narrative generation.

Behavioral Profile

This model tends to favor:

Rich descriptions.
Character-focused scenes.
Emotional dialogue.
Dramatic pacing.
Emergent story arcs.
Persistent narrative threads.

Stories generated by this model often evolve organically.

Characters may surprise you.

Sometimes they surprise the model itself.

Strengths

Strong narrative immersion.
Natural dialogue generation.
Flexible tone adaptation.
Good long-scene continuity for a 1B model.
Capable of improvising complex interactions.
Compact enough for local inference.

Limitations

Experimental merge.
Narrative coherence may vary depending on prompt complexity.
Long conversations can occasionally drift in tone or pacing.
Factual accuracy is not a design priority.
Characters may become more independent or dramatic than intended.

Experimental Notes

Storytime RPG System was created around a simple question:

What if a roleplay model and a storytelling model stopped competing and started improvising together?

The answer appears to be:

more expressive characters,
more dramatic scenes,
richer dialogue,
and stories that sometimes feel larger than the prompts that created them.

Not every generation is perfect.

But many are memorable.

Lore Fragment

The Archivist asked the machine:

"Tell me a story."

The machine replied:

"Which ending do you want?"

"The happy one."

The machine paused.

Then answered:

"Those are the hardest to write."

Recommended Settings

Temperature: 0.9 – 1.3
Top-p: 0.92 – 0.98
Min-p: 0.05
Repetition penalty: 1.05 – 1.12
Context: 8K recommended

Version

Storytime RPG System 3.2 1B

Experimental Narrative Variant

"Stories are not generated here. They are discovered."

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: Storytime RPG Unethic 3.2 1B AI Model
# =========================================================
# PROJECT: Storytime RPG System 3.2 1B - "Degenerated"
# =========================================================

models:
  - model: NovaCorp/Ultimate-RPG.System-3.2-1B  # Experimental viral strain neural imprint
  - model: thegr8lizzyator/storytime-llama3-1b-v2  # 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: 0.45

normalize: false
rescale: true
rescale_factor: 1.12
memory_efficient: true
low_cpu_mem_usage: true

layer_range:
  - value: [4, 22]

tie_word_embeddings: true
tie_output_embeddings: true

Downloads last month: 20

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for NovaCorp/Storytime-RPG.System-3.2-1B

NovaCorp/Ultimate-RPG.System-3.2-1B

thegr8lizzyator/storytime-llama3-1b-v2

Merge model

this model

Quantizations

2 models