Instructions to use N-Bot-Int/OpenElla3-Llama3.2A with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use N-Bot-Int/OpenElla3-Llama3.2A with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "N-Bot-Int/OpenElla3-Llama3.2A")

Transformers

How to use N-Bot-Int/OpenElla3-Llama3.2A with Transformers:

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

pipe = pipeline("text-generation", model="N-Bot-Int/OpenElla3-Llama3.2A")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("N-Bot-Int/OpenElla3-Llama3.2A", dtype="auto")

llama-cpp-python

How to use N-Bot-Int/OpenElla3-Llama3.2A with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="N-Bot-Int/OpenElla3-Llama3.2A",
	filename="unsloth.Q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use N-Bot-Int/OpenElla3-Llama3.2A with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf N-Bot-Int/OpenElla3-Llama3.2A:Q8_0
# Run inference directly in the terminal:
llama-cli -hf N-Bot-Int/OpenElla3-Llama3.2A:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf N-Bot-Int/OpenElla3-Llama3.2A:Q8_0
# Run inference directly in the terminal:
llama-cli -hf N-Bot-Int/OpenElla3-Llama3.2A:Q8_0

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 N-Bot-Int/OpenElla3-Llama3.2A:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf N-Bot-Int/OpenElla3-Llama3.2A:Q8_0

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 N-Bot-Int/OpenElla3-Llama3.2A:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf N-Bot-Int/OpenElla3-Llama3.2A:Q8_0

Use Docker

docker model run hf.co/N-Bot-Int/OpenElla3-Llama3.2A:Q8_0

LM Studio
Jan

vLLM

How to use N-Bot-Int/OpenElla3-Llama3.2A with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "N-Bot-Int/OpenElla3-Llama3.2A"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "N-Bot-Int/OpenElla3-Llama3.2A",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/N-Bot-Int/OpenElla3-Llama3.2A:Q8_0

SGLang

How to use N-Bot-Int/OpenElla3-Llama3.2A 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 "N-Bot-Int/OpenElla3-Llama3.2A" \
    --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": "N-Bot-Int/OpenElla3-Llama3.2A",
		"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 "N-Bot-Int/OpenElla3-Llama3.2A" \
        --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": "N-Bot-Int/OpenElla3-Llama3.2A",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use N-Bot-Int/OpenElla3-Llama3.2A with Ollama:
```
ollama run hf.co/N-Bot-Int/OpenElla3-Llama3.2A:Q8_0
```

Unsloth Studio new

How to use N-Bot-Int/OpenElla3-Llama3.2A 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 N-Bot-Int/OpenElla3-Llama3.2A 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 N-Bot-Int/OpenElla3-Llama3.2A to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for N-Bot-Int/OpenElla3-Llama3.2A to start chatting

Pi new

How to use N-Bot-Int/OpenElla3-Llama3.2A with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf N-Bot-Int/OpenElla3-Llama3.2A:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "N-Bot-Int/OpenElla3-Llama3.2A:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use N-Bot-Int/OpenElla3-Llama3.2A with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf N-Bot-Int/OpenElla3-Llama3.2A:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default N-Bot-Int/OpenElla3-Llama3.2A:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use N-Bot-Int/OpenElla3-Llama3.2A with Docker Model Runner:
```
docker model run hf.co/N-Bot-Int/OpenElla3-Llama3.2A:Q8_0
```

Lemonade

How to use N-Bot-Int/OpenElla3-Llama3.2A with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull N-Bot-Int/OpenElla3-Llama3.2A:Q8_0

Run and chat with the model

lemonade run user.OpenElla3-Llama3.2A-Q8_0

List all available models

lemonade list

A newer version of this model is available: N-Bot-Int/OpenElla3-Llama3.2B-V2

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: nexus.networkinteractives@gmail.com
Notice
- For a Good Experience, Please use
  - Low temperature 1.5, min_p = 0.1 and max_new_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
- Finetuning tool:
- Unsloth AI
  - This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Fine-tuned Using:
- Google Colab