Instructions to use gg34455/qwegpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gg34455/qwegpt with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="gg34455/qwegpt",
	filename="Qwen2.5-0.5B-Instruct.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 gg34455/qwegpt 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 gg34455/qwegpt:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf gg34455/qwegpt:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf gg34455/qwegpt:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf gg34455/qwegpt: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 gg34455/qwegpt:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf gg34455/qwegpt: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 gg34455/qwegpt:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf gg34455/qwegpt:Q4_K_M

Use Docker

docker model run hf.co/gg34455/qwegpt:Q4_K_M

LM Studio
Jan

vLLM

How to use gg34455/qwegpt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gg34455/qwegpt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gg34455/qwegpt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gg34455/qwegpt:Q4_K_M

Ollama
How to use gg34455/qwegpt with Ollama:
```
ollama run hf.co/gg34455/qwegpt:Q4_K_M
```

Unsloth Studio

How to use gg34455/qwegpt 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 gg34455/qwegpt 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 gg34455/qwegpt to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for gg34455/qwegpt to start chatting

How to use gg34455/qwegpt with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf gg34455/qwegpt: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": "gg34455/qwegpt:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use gg34455/qwegpt with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf gg34455/qwegpt: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 gg34455/qwegpt:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use gg34455/qwegpt with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf gg34455/qwegpt:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "gg34455/qwegpt:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use gg34455/qwegpt with Docker Model Runner:
```
docker model run hf.co/gg34455/qwegpt:Q4_K_M
```

Lemonade

How to use gg34455/qwegpt with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull gg34455/qwegpt:Q4_K_M

Run and chat with the model

lemonade run user.qwegpt-Q4_K_M

List all available models

lemonade list

qwegpt

qwegpt is a fine-tuned conversational AI model designed to provide clear, helpful, and structured responses with a natural, ChatGPT-like behavior. It is optimized for coding assistance, creative tasks, and general problem-solving.

🧠 Model Details

Model Description

qwegpt is built on top of Qwen2.5-0.5B-Instruct and further fine-tuned to improve helpfulness, clarity, and user guidance. The model focuses on delivering concise yet informative answers, adapting to both beginners and more advanced users.

It is designed to:

Explain concepts in a simple and structured way
Assist with coding and debugging
Generate creative content (prompts, ideas, UI concepts)
Provide step-by-step guidance when needed

🚀 Intended Use

Primary Use Cases

Coding help and debugging guidance
Learning and explaining technical concepts
Generating creative prompts (art, UI, ideas)
General-purpose assistant tasks

Out-of-Scope Use

High-risk domains requiring strict accuracy (e.g., legal, medical advice)
Tasks requiring guaranteed factual correctness

⚙️ Training Details

Base Model

Qwen/Qwen2.5-0.5B-Instruct
unsloth/Qwen2.5-0.5B-Instruct

Fine-Tuning Approach

The model was fine-tuned on a custom dataset focused on:

Helpful conversational behavior
Clear explanations and structured responses
Coding-related Q&A
Creative prompt generation

The dataset emphasizes:

Practical problem-solving
Step-by-step guidance
Natural and engaging tone

📊 Capabilities

Strong at explaining concepts clearly
Good at generating structured answers
Helpful for coding and debugging tasks
Can generate creative prompts and UI ideas

⚠️ Limitations

May produce incorrect or outdated information
Limited reasoning compared to larger models
Can struggle with highly complex or multi-step logic
Not optimized for real-time or factual verification tasks

💡 Example Usage

Input:
"How do I center a div?"

Output:
"The cleanest way is to use flexbox on the parent container, which allows you to center elements both horizontally and vertically with minimal effort."

🧩 Future Improvements

Better reasoning and multi-step problem solving
Improved factual accuracy
Expanded dataset for more domains
Enhanced creativity and style control

📜 License

This model is released under the MIT License.

🤝 Acknowledgements

Qwen team for the base model
Unsloth for efficient fine-tuning tools
Open-source community for datasets and inspiration

Downloads last month: 19

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for gg34455/qwegpt

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Quantized

(242)

this model