Instructions to use franktheglock/HA-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use franktheglock/HA-2B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="franktheglock/HA-2B",
	filename="Qwen3.5-2B.BF16-mmproj.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use franktheglock/HA-2B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf franktheglock/HA-2B:BF16
# Run inference directly in the terminal:
llama-cli -hf franktheglock/HA-2B:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf franktheglock/HA-2B:BF16
# Run inference directly in the terminal:
llama-cli -hf franktheglock/HA-2B:BF16

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 franktheglock/HA-2B:BF16
# Run inference directly in the terminal:
./llama-cli -hf franktheglock/HA-2B:BF16

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 franktheglock/HA-2B:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf franktheglock/HA-2B:BF16

Use Docker

docker model run hf.co/franktheglock/HA-2B:BF16

LM Studio
Jan
Ollama
How to use franktheglock/HA-2B with Ollama:
```
ollama run hf.co/franktheglock/HA-2B:BF16
```

Unsloth Studio

How to use franktheglock/HA-2B 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 franktheglock/HA-2B 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 franktheglock/HA-2B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for franktheglock/HA-2B to start chatting

How to use franktheglock/HA-2B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf franktheglock/HA-2B:BF16

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": "franktheglock/HA-2B:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use franktheglock/HA-2B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf franktheglock/HA-2B:BF16

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 franktheglock/HA-2B:BF16

Run Hermes

hermes

Docker Model Runner
How to use franktheglock/HA-2B with Docker Model Runner:
```
docker model run hf.co/franktheglock/HA-2B:BF16
```

Lemonade

How to use franktheglock/HA-2B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull franktheglock/HA-2B:BF16

Run and chat with the model

lemonade run user.HA-2B-BF16

List all available models

lemonade list

HA-2B

Home Assistant Control | Fine-tuned Qwen 3.5 2B

HA-2B is a LoRA fine-tune of Qwen 3.5 2B on the Home-Assistant-Requests-V2 dataset. It's designed to understand and execute smart home control commands, turning lights on/off, managing blinds, locking doors, querying sensor states, and any other Home Assistant automation task.

Training Details

Hyperparameter	Value
Base model	`unsloth/Qwen3.5-2B`
Dataset	`acon96/Home-Assistant-Requests-V2` (208,976 rows)
Format	ChatML (auto-detected)
Sequence length	2048
Steps	30
Batch size	2 (effective 8 with 4Ã— gradient accumulation)
Learning rate	2e-4
Optimizer	AdamW 8-bit
LoRA rank	16
LoRA alpha	16
LoRA dropout	0.0
Target modules	Q, K, V, O, Gate, Up, Down projections
Precision	bfloat16
Warmup steps	5
LR scheduler	Linear
Packing	Disabled
Weight decay	0.001
Gradient checkpointing	Unsloth
Final training loss	1.37
Hardware	Dual NVIDIA RTX 3060 12GB

Usage

The model uses standard ChatML conversation format. Load the base model and LoRA adapter:

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = "Qwen/Qwen3.5-2B"
lora_adapter = "path/to/ha-2b-adapter"

tokenizer = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    base_model,
    torch_dtype="bfloat16",
    device_map="auto",
    trust_remote_code=True,
)
model = PeftModel.from_pretrained(model, lora_adapter)

Inference Example

<|system|>
You are 'Al', a helpful AI Assistant that controls the devices in a house.
Complete the following task as instructed.
<|user|>
turn off the living room light
<|assistant|>
Turning off the living room light now.

The dataset also includes structured tool-calling examples with function definitions (HassTurnOn, HassTurnOff, etc.) for programmatic device control.

Intended Use

Smart home voice/text assistants
Home Assistant / openHAB / Hubitat integrations
Tool-calling for device control
Natural language to home automation commands

Limitations

Fine-tuned primarily on English residential smart home scenarios
2B parameter size, capable but not as nuanced as larger models
Training was brief (30 steps, ~0.14 epochs) â€” more steps would likely improve convergence

Hardware & Tools

GPUs: NVIDIA RTX 3060 12GB
Training framework: Unsloth Studio 2026.5.8
Base model: Qwen 3.5 2B (4-bit QLoRA)

Downloads last month: 102

GGUF

Model size

2B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for franktheglock/HA-2B

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Finetuned

unsloth/Qwen3.5-2B

Adapter

(24)

this model

franktheglock
/

HA-2B