Instructions to use fhnw/2025H2-DPO-BAI-FHNW with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fhnw/2025H2-DPO-BAI-FHNW with Transformers:

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

pipe = pipeline("text-generation", model="fhnw/2025H2-DPO-BAI-FHNW")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("fhnw/2025H2-DPO-BAI-FHNW", dtype="auto")

llama-cpp-python

How to use fhnw/2025H2-DPO-BAI-FHNW with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="fhnw/2025H2-DPO-BAI-FHNW",
	filename="gpt-oss-20b.MXFP4.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 fhnw/2025H2-DPO-BAI-FHNW with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf fhnw/2025H2-DPO-BAI-FHNW
# Run inference directly in the terminal:
llama-cli -hf fhnw/2025H2-DPO-BAI-FHNW

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf fhnw/2025H2-DPO-BAI-FHNW
# Run inference directly in the terminal:
llama-cli -hf fhnw/2025H2-DPO-BAI-FHNW

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 fhnw/2025H2-DPO-BAI-FHNW
# Run inference directly in the terminal:
./llama-cli -hf fhnw/2025H2-DPO-BAI-FHNW

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 fhnw/2025H2-DPO-BAI-FHNW
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fhnw/2025H2-DPO-BAI-FHNW

Use Docker

docker model run hf.co/fhnw/2025H2-DPO-BAI-FHNW

LM Studio
Jan

vLLM

How to use fhnw/2025H2-DPO-BAI-FHNW with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fhnw/2025H2-DPO-BAI-FHNW"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fhnw/2025H2-DPO-BAI-FHNW",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fhnw/2025H2-DPO-BAI-FHNW

SGLang

How to use fhnw/2025H2-DPO-BAI-FHNW 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 "fhnw/2025H2-DPO-BAI-FHNW" \
    --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": "fhnw/2025H2-DPO-BAI-FHNW",
		"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 "fhnw/2025H2-DPO-BAI-FHNW" \
        --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": "fhnw/2025H2-DPO-BAI-FHNW",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use fhnw/2025H2-DPO-BAI-FHNW with Ollama:
```
ollama run hf.co/fhnw/2025H2-DPO-BAI-FHNW
```

Unsloth Studio

How to use fhnw/2025H2-DPO-BAI-FHNW 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 fhnw/2025H2-DPO-BAI-FHNW 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 fhnw/2025H2-DPO-BAI-FHNW to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for fhnw/2025H2-DPO-BAI-FHNW to start chatting

How to use fhnw/2025H2-DPO-BAI-FHNW with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf fhnw/2025H2-DPO-BAI-FHNW

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": "fhnw/2025H2-DPO-BAI-FHNW"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use fhnw/2025H2-DPO-BAI-FHNW with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf fhnw/2025H2-DPO-BAI-FHNW

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 fhnw/2025H2-DPO-BAI-FHNW

Run Hermes

hermes

Docker Model Runner
How to use fhnw/2025H2-DPO-BAI-FHNW with Docker Model Runner:
```
docker model run hf.co/fhnw/2025H2-DPO-BAI-FHNW
```

Lemonade

How to use fhnw/2025H2-DPO-BAI-FHNW with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fhnw/2025H2-DPO-BAI-FHNW

Run and chat with the model

lemonade run user.2025H2-DPO-BAI-FHNW-{{QUANT_TAG}}

List all available models

lemonade list

fhnw/2025H2-DPO-BAI-FHNW

Model Summary

This repository contains a Direct Preference Optimization (DPO) variant of the GPT-OSS 20B family, fine-tuned using Unsloth QLoRA for FHNW.

Exported format(s): GGUF, MXFP4.

Base model: GPT-OSS 20B
Variant: Direct Preference Optimization (DPO)
Purpose: preference-aligned generation
Created: 2025-11-24

Intended Use

Suitable for research, teaching, and applied Generative AI experimentation at FHNW. Not intended for high-risk or safety-critical decision-making.

Usage

GGUF with llama.cpp

git lfs install
git clone https://huggingface.co/fhnw/2025H2-DPO-BAI-FHNW
cd fhnw/2025H2-DPO-BAI-FHNW
./main -m model.gguf -p "Explain what GPT-OSS is."

MXFP4 with Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained("fhnw/2025H2-DPO-BAI-FHNW")
model = AutoModelForCausalLM.from_pretrained("fhnw/2025H2-DPO-BAI-FHNW", torch_dtype="auto")

input_ids = tokenizer("Explain GPT-OSS.", return_tensors="pt")
print(tokenizer.decode(model.generate(**input_ids)[0], skip_special_tokens=True))

Training Details

The model was fine-tuned using Unsloth QLoRA and exported using Unsloth's merged MXFP4 or native GGUF export pipeline, depending on the selected format(s).

Limitations

May hallucinate or provide outdated information.
Inherits all limitations of the GPT-OSS 20B base model.
Human review is strongly recommended.

License

Follows the respective licenses of GPT-OSS 20B and Unsloth.

Downloads last month: 22

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for fhnw/2025H2-DPO-BAI-FHNW

Base model

openai/gpt-oss-20b

Quantized

unsloth/gpt-oss-20b

Quantized

(21)

this model