Instructions to use fivetech/Harbour with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fivetech/Harbour with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/home/fivetech/finetune/models/Qwen3.6-35B-A3B")
model = PeftModel.from_pretrained(base_model, "fivetech/Harbour")

Transformers

How to use fivetech/Harbour with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("fivetech/Harbour", dtype="auto")

llama-cpp-python

How to use fivetech/Harbour with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="fivetech/Harbour",
	filename="Qwen3.6-35B-A3B-LoRA-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 fivetech/Harbour 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 fivetech/Harbour:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf fivetech/Harbour:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/fivetech/Harbour:Q4_K_M

LM Studio
Jan

vLLM

How to use fivetech/Harbour with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/fivetech/Harbour:Q4_K_M

SGLang

How to use fivetech/Harbour 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 "fivetech/Harbour" \
    --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": "fivetech/Harbour",
		"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 "fivetech/Harbour" \
        --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": "fivetech/Harbour",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use fivetech/Harbour with Ollama:
```
ollama run hf.co/fivetech/Harbour:Q4_K_M
```

Unsloth Studio

How to use fivetech/Harbour 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 fivetech/Harbour 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 fivetech/Harbour to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for fivetech/Harbour to start chatting

How to use fivetech/Harbour with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf fivetech/Harbour:Q4_K_M

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": "fivetech/Harbour:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use fivetech/Harbour with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf fivetech/Harbour:Q4_K_M

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 fivetech/Harbour:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use fivetech/Harbour with Docker Model Runner:
```
docker model run hf.co/fivetech/Harbour:Q4_K_M
```

Lemonade

How to use fivetech/Harbour with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fivetech/Harbour:Q4_K_M

Run and chat with the model

lemonade run user.Harbour-Q4_K_M

List all available models

lemonade list

Harbour/FWH Coder — Qwen3.5-35B-A3B LoRA v2

Training code: https://github.com/FiveTechSoft/finetune

LoRA adapter fine-tuned on 5,004 compilable Harbour and FiveWin (FWH) examples for code generation. Built on top of Qwen3.5-35B-A3B, a 35B Mixture-of-Experts model with 256 experts (8 active per token).

What's New in v2

	v1	v2
Dataset	996 entries (7 categories)	5,004 entries (8 categories)
Training time	3h 43min	~8h
Eval loss	0.5957	0.4790 (↓20%)
Train loss	0.6456	0.4211 (↓35%)
Format	messages (chat)	instruction/output
Learning rate	1e-4	8e-5 (conservative)
Epochs	3	2

Key improvements

5x more training data — expanded from 996 to 5,004 unique, compilable examples
Better loss convergence — 35% lower train loss, 20% lower eval loss
More conservative training — lower learning rate preserves base model capabilities
FiveWin (FWH) coverage — added FiveWin GUI framework examples
Verified code — all examples verified with Harbour v3.2.0dev compiler

Dataset

Training data sourced from the Harbour project — an open-source Clipper-compatible compiler — and FiveWin (FWH) GUI framework.

Category	Count	Description
contrib	583	Contribution libraries (network, database, graphics, security...)
rtl	80	Harbour Runtime Library
include	59	Header files with constants/macros
tests	225	Test programs
extras	25	Extra libraries
utils	13	Utility programs
fwh	~500+	FiveWin GUI framework examples
low-level C	500+	HB_FUNC C extension wrappers

Format

{
  "instruction": "Write a Harbour function that creates a 2D array...",
  "input": "",
  "system": "You are an expert Harbour programmer...",
  "output": "FUNCTION CreateTable()\n   LOCAL aTable := {}\n   ...",
  "task_type": "code_generation"
}

Training Details

Hardware

Device: NVIDIA GB10 Grace Blackwell Superchip (DGX Spark)
Architecture: ARM aarch64 (10 NVIDIA Grace CPU cores + Blackwell GPU)
RAM: 121 GB unified memory (CPU + GPU shared)
OS: Ubuntu 24.04.4 LTS (aarch64)
Training time: 7h 49min (564 steps, 2 epochs over 5,004 samples)

Hyperparameters

Parameter	Value
Base model	Qwen3.5-35B-A3B (MoE, 256 experts)
Method	QLoRA (4-bit)
LoRA rank	8
LoRA alpha	16
LoRA targets	q/k/v/o/gate/up/down_proj
Epochs	2
Learning rate	8e-5
LR scheduler	cosine
Warmup ratio	0.05
Batch size	1 (effective: 16 via grad accum)
Max seq length	1024
Optimizer	adamw_8bit

Framework

Unsloth 2026.6.8
Transformers 5.5.0
PEFT 0.19.1
PyTorch 2.12.1

How to Use

With PEFT + Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen3.5-35B-A3B",
    load_in_4bit=True,
    device_map="auto",
)
model = PeftModel.from_pretrained(base_model, "fivetech/Harbour")
tokenizer = AutoTokenizer.from_pretrained("fivetech/Harbour")

prompt = "Write a Harbour function that splits a CSV string into an array."
messages = [
    {"role": "system", "content": "You are an expert Harbour programmer. Write compilable code."},
    {"role": "user", "content": prompt},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([text], return_tensors="pt").to(model.device)

output = model.generate(**inputs, max_new_tokens=1500, temperature=0.2)
print(tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

With Ollama (merge + quantize first)

# Export to GGUF
python -m unsloth.save_pretrained_gguf model_output/ ./tokenizer/ q4_k_m

# Then use with Ollama
ollama create harbour-coder -f Modelfile

Evaluation

Evaluated on 100 Harbour programming tests (Arrays, OOP, Functions, Database, File I/O, Control flow):

Compilation pass rate: TBD (running test battery)
Categories tested: Arrays (48), OOP (22), Other (9), Functions (8), Database (7), File I/O (4), Control (2)

License

Apache 2.0

Model Card Contact

fivetech — https://github.com/fivetechsoft/finetune

Downloads last month: -

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Model tree for fivetech/Harbour

Base model

Qwen/Qwen3.5-35B-A3B-Base

Finetuned

Qwen/Qwen3.5-35B-A3B

Adapter

(30)

this model