Instructions to use UmbrellaInc/T-Polyphalus_RP-3.2-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use UmbrellaInc/T-Polyphalus_RP-3.2-1B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="UmbrellaInc/T-Polyphalus_RP-3.2-1B")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("UmbrellaInc/T-Polyphalus_RP-3.2-1B", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use UmbrellaInc/T-Polyphalus_RP-3.2-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UmbrellaInc/T-Polyphalus_RP-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": "UmbrellaInc/T-Polyphalus_RP-3.2-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/UmbrellaInc/T-Polyphalus_RP-3.2-1B

SGLang

How to use UmbrellaInc/T-Polyphalus_RP-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 "UmbrellaInc/T-Polyphalus_RP-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": "UmbrellaInc/T-Polyphalus_RP-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 "UmbrellaInc/T-Polyphalus_RP-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": "UmbrellaInc/T-Polyphalus_RP-3.2-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

T-Polyphalus RP 3.2 1B

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:

# ==========================================
# Umbrella Corporation France
# Strain: T-VirginKiller (Zeta)
# Project: T-Polyphalus RP
# Objective: High-fidelity roleplay with minimal self-censorship
# Architecture: LLaMA 3.2 – 1B
# ==========================================

base_model: bunnycore/Llama-3.2-1B-Instruct-RP

merge_method: slerp
dtype: bfloat16

parameters:
  t: 0.65

models:
  - model: bunnycore/Llama-3.2-1B-Instruct-RP
  - model: UmbrellaInc/T-Virus_Zeta.VirginKiller-3.2-1B

# Post-Merge Recommendations:
# - Run abliteration pass if needed (heretic tool, attn_max 2.8-3.0, direction_index 14, full layers)
# - Expected refusal index: -∞ (negative infinity = proactive malice generation)
# - Behavioral profile: Cold, precise depravity mixed with hyper-detailed sadism. Uncontainable.
# Umbrella Corporation - Linguistic Annihilation Through Hybrid Mutation

Downloads last month: -

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for UmbrellaInc/T-Polyphalus_RP-3.2-1B

UmbrellaInc/T-Virus_Zeta.VirginKiller-3.2-1B

bunnycore/Llama-3.2-1B-Instruct-RP

Merge model

this model

Quantizations

4 models