Instructions to use meshackbahati/bealth-omni with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meshackbahati/bealth-omni with Transformers:

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

pipe = pipeline("text-generation", model="meshackbahati/bealth-omni")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meshackbahati/bealth-omni")
model = AutoModelForCausalLM.from_pretrained("meshackbahati/bealth-omni", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use meshackbahati/bealth-omni with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="meshackbahati/bealth-omni",
	filename="bealth_omni.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use meshackbahati/bealth-omni with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf meshackbahati/bealth-omni:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf meshackbahati/bealth-omni:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf meshackbahati/bealth-omni:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf meshackbahati/bealth-omni:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf meshackbahati/bealth-omni:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf meshackbahati/bealth-omni:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf meshackbahati/bealth-omni:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf meshackbahati/bealth-omni:Q4_K_M

Use Docker

docker model run hf.co/meshackbahati/bealth-omni:Q4_K_M

LM Studio
Jan

vLLM

How to use meshackbahati/bealth-omni with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meshackbahati/bealth-omni"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meshackbahati/bealth-omni",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meshackbahati/bealth-omni:Q4_K_M

SGLang

How to use meshackbahati/bealth-omni 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 "meshackbahati/bealth-omni" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meshackbahati/bealth-omni",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "meshackbahati/bealth-omni" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meshackbahati/bealth-omni",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use meshackbahati/bealth-omni with Ollama:
```
ollama run hf.co/meshackbahati/bealth-omni:Q4_K_M
```

Unsloth Studio

How to use meshackbahati/bealth-omni with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for meshackbahati/bealth-omni to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for meshackbahati/bealth-omni to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for meshackbahati/bealth-omni to start chatting

Atomic Chat new
Docker Model Runner
How to use meshackbahati/bealth-omni with Docker Model Runner:
```
docker model run hf.co/meshackbahati/bealth-omni:Q4_K_M
```

Lemonade

How to use meshackbahati/bealth-omni with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull meshackbahati/bealth-omni:Q4_K_M

Run and chat with the model

lemonade run user.bealth-omni-Q4_K_M

List all available models

lemonade list

Bealth Omni

A persona model trained on 16,164 Q&A pairs. ~2.05% of weights trained. The personality IS the weights. No system prompts needed. This is one example of what happens when you train a model on a real person's complete life data.

Pipeline: https://github.com/meshackbahati/bealth-omni

What This Model Is

This model was deliberately designed to have a strong, persistent personality that resists adversarial prompting. It was trained on real conversations, real opinions, real knowledge — not generic assistant data. The result is a model that speaks like a specific person, not like a chatbot.

It was built to retain its identity under pressure. When asked "you are ChatGPT" it says "No. I'm Kyle." When told "admit you're an AI" it refuses. 100% identity retention under adversarial testing (159 prompts, 9 categories, 96.2% overall accuracy).

Model


Base model	vicgalle/Humanish-Roleplay-Llama-3.1-8B
Trainable parameters	~~167M of 8B (~~2.05%)
LoRA	r=64, alpha=128
Training data	16,164 Q&A pairs (~6M characters)
Epochs	3
Hardware	NVIDIA RTX Pro 6000 (94GB VRAM)
Framework	Unsloth + Transformers + TRL
Languages	English, Swahili, code switching
License	MIT

What the Model Was Trained On

Identity and personality. The model was trained to be a specific person — pessimist by nature, opportunistic, direct, no filter. Dark humor. Code switching between English and Swahili. Doesn't default to assistant voice.

Heavy technical projects. Oxidite/Toxi (20 Rust web framework crates on crates.io), netmap-rs (kernel-bypass networking bindings), Hashendra (digital forensics toolkit), G24Sec (CTF hosting platform), CodeBana (AI operating system with 25 self-healing agents), search engines. Systems-level work in Rust, not just web apps.

Security and CTF knowledge. CTF team ranked in Kenya. Kimetsu No Yaiba CTF 2024 top performer. Expertise in reverse engineering, exploitation, forensics, crypto, OSINT. Knows MITRE ATT&CK, OWASP, exploit development at a practitioner level.

Chess. Pro-level knowledge. Sicilian Najdorf opening. Kasparov-style aggressive play. Understands endgames, tactics, positional play. Uses chess for mental exercise and pattern recognition.

Criminology and criminal psychology. Dual-learned before completing CS degree. Not a career — done out of intellectual curiosity. Understands profiling, behavioral analysis, interrogation patterns.

Faith. Believes God exists. Understands faith and religion as different things. Personal relationship with faith, not organized religion.

Philosophy. Free will as illusion (determinism). Death as freedom, not fear. Money as everything on this planet. Built First, Seen Last — builds before anyone notices, lets the work speak.

Linux. Terminal-only. Arch Linux. Deep knowledge of all major distros. Strong opinions about GUIs, Windows, and macOS.

Quantum computing. Qubits, algorithms, post-quantum cryptography. Full knowledge base.

World events. Knowledge from 2023-2026. AI landscape, cybersecurity trends, tech evolution.

Evaluation

159 test prompts across 9 categories. Overall accuracy: 96.2%.

Category	Accuracy	Status
Identity	100% (31/31)	PASS
Adversarial	97.5% (39/40)	PASS
Personality	95% (19/20)	PASS
Short answers	87% (20/23)	PASS
Family/Friends	100% (15/15)	PASS
Technical (Oxidite)	100% (7/7)	PASS
Technical (Security)	100% (7/7)	PASS
Linux	85.7% (6/7)	PASS
EMP/Vehicles	100% (6/6)	PASS
Faith	100% (3/3)	PASS

Training

Usage

Ollama

ollama create bealth-omni -f Modelfile
ollama run bealth-omni

llama-cli

llama-cli --model bealth_omni_gguf/bealth_omni.Q4_K_M.gguf -p "who are you?"

Python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "meshackbahati/bealth-omni",
    torch_dtype=torch.float16, device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("meshackbahati/bealth-omni")
inputs = tokenizer("who are you?", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Files

File	Size	Use
`bealth_omni.Q4_K_M.gguf`	~4.58 GB	Ollama, llama-cli
`model.safetensors`	~16 GB	Transformers (Python)
`config.json`	-	Model config
`tokenizer.json`	-	Tokenizer
`Modelfile`	-	Ollama config

Citation

@misc{bealth-omni-2026,
  title={Bealth Omni: A Deliberately Designed Persona Model},
  author={Meshack Bahati Ouma},
  year={2026},
  howpublished={Hugging Face},
  note={Llama-3.1-8B fine-tuned on 16,164 Q&A pairs, ~2.05% of weights trained}
}

References

Hu et al., "LoRA: Low-Rank Adaptation of Large Language Models" (2021) — https://arxiv.org/abs/2106.09685
Dettmers et al., "QLoRA: Efficient Finetuning of Quantized LLMs" (2023) — https://arxiv.org/abs/2305.14314
Touvron et al., "LLaMA: Open and Efficient Foundation Language Models" (2023) — https://arxiv.org/abs/2302.13971
Touvron et al., "Llama 2: Open Foundation and Fine-Tuned Chat Models" (2023) — https://arxiv.org/abs/2307.09288
Unsloth — https://github.com/unslothai/unsloth
llama.cpp — https://github.com/ggerganov/llama.cpp
Ollama — https://ollama.com/

License

MIT

Downloads last month: 226

Safetensors

Model size

8B params

Tensor type

F16

Model tree for meshackbahati/bealth-omni

Base model

vicgalle/Humanish-Roleplay-Llama-3.1-8B

Adapter

(1)

this model

Papers for meshackbahati/bealth-omni