Instructions to use truss-ai/truss-qwen3-python-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use truss-ai/truss-qwen3-python-lora with Transformers:

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

pipe = pipeline("text-generation", model="truss-ai/truss-qwen3-python-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("truss-ai/truss-qwen3-python-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use truss-ai/truss-qwen3-python-lora 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 truss-ai/truss-qwen3-python-lora
# Run inference directly in the terminal:
llama cli -hf truss-ai/truss-qwen3-python-lora

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf truss-ai/truss-qwen3-python-lora
# Run inference directly in the terminal:
llama cli -hf truss-ai/truss-qwen3-python-lora

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 truss-ai/truss-qwen3-python-lora
# Run inference directly in the terminal:
./llama-cli -hf truss-ai/truss-qwen3-python-lora

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 truss-ai/truss-qwen3-python-lora
# Run inference directly in the terminal:
./build/bin/llama-cli -hf truss-ai/truss-qwen3-python-lora

Use Docker

docker model run hf.co/truss-ai/truss-qwen3-python-lora

LM Studio
Jan

vLLM

How to use truss-ai/truss-qwen3-python-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "truss-ai/truss-qwen3-python-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "truss-ai/truss-qwen3-python-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/truss-ai/truss-qwen3-python-lora

SGLang

How to use truss-ai/truss-qwen3-python-lora 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 "truss-ai/truss-qwen3-python-lora" \
    --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": "truss-ai/truss-qwen3-python-lora",
		"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 "truss-ai/truss-qwen3-python-lora" \
        --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": "truss-ai/truss-qwen3-python-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use truss-ai/truss-qwen3-python-lora with Ollama:
```
ollama run hf.co/truss-ai/truss-qwen3-python-lora
```

Unsloth Studio

How to use truss-ai/truss-qwen3-python-lora 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 truss-ai/truss-qwen3-python-lora 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 truss-ai/truss-qwen3-python-lora to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for truss-ai/truss-qwen3-python-lora to start chatting

How to use truss-ai/truss-qwen3-python-lora with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf truss-ai/truss-qwen3-python-lora

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "truss-ai/truss-qwen3-python-lora"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use truss-ai/truss-qwen3-python-lora with Docker Model Runner:
```
docker model run hf.co/truss-ai/truss-qwen3-python-lora
```

Lemonade

How to use truss-ai/truss-qwen3-python-lora with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull truss-ai/truss-qwen3-python-lora

Run and chat with the model

lemonade run user.truss-qwen3-python-lora-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use truss-ai/truss-qwen3-python-lora with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf truss-ai/truss-qwen3-python-lora

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 truss-ai/truss-qwen3-python-lora

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use truss-ai/truss-qwen3-python-lora with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf truss-ai/truss-qwen3-python-lora

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 "truss-ai/truss-qwen3-python-lora" \
  --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"

truss-qwen3-python-lora / README.md

QuillBytes

Create README.md

e936bdd verified about 2 hours ago

preview code

Raw

History Blame Contribute Delete

2.93 kB

	---
	license: apache-2.0
	language:
	- en
	tags:
	- text-generation-inference
	- transformers
	- gguf
	- ollama
	- qwen3
	- python-coding
	base_model: Qwen/Qwen3-4B-Instruct-2507
	pipeline_tag: text-generation
	---

	# Truss Python: Qwen3-4B Specialized Coding Assistant

	Truss Python is a specialized fine-tuned version of Qwen3-4B-Instruct-2507, optimized for generating clean, professional, and robust Python code. By focusing on high-quality seed prompts involving standard libraries, asynchronous programming, and data structures, this model prioritizes type safety, documentation, and modern Pythonic patterns.

	## 🚀 Model Details

	* Base Model: [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)
	* Architecture: Qwen3ForCausalLM
	* Fine-Tuning Method: LoRA (Low-Rank Adaptation)
	* Quantization: Q4_K_M (GGUF)
	* File Size: ~2.5 GB
	* License: Apache 2.0 (Inherited from Qwen3)

	## ✨ Key Features

	* Professional Structure: Consistently generates code with Google-style docstrings and comprehensive type hints.
	* Modern Syntax: Proficient in Python 3.10+ features like `match-case` structural pattern matching.
	* Robust Error Handling: Prioritizes `try/except` blocks and resource management (e.g., `async with`, `contextlib`).
	* Standard Library Focus: Expert-level knowledge of `asyncio`, `threading`, `csv`, `functools`, and `pandas`.

	## 💻 Usage with Ollama

	This model is optimized for local deployment using Ollama.

	### 1. Local Import (Using GGUF)
	If you have downloaded the `.gguf` file:

	1. Create a `Modelfile`:
	```dockerfile
	FROM ./truss-qwen3-python-lora.gguf
	PARAMETER temperature 0.2
	SYSTEM "You are an expert Python developer. Provide clean, efficient, and well-documented code."
	```
	2. Create the model in your terminal:
	```bash
	ollama create truss-python -f Modelfile
	```
	3. Run the model:
	```bash
	ollama run truss-python
	```

	## 🧪 Example Prompts

	\| Task \| Prompt \|
	\| :--- \| :--- \|
	\| Algorithms \| "Write a binary search function with type hints and no built-in libraries." \|
	\| Decorators \| "Create a `@timer` decorator using `functools.wraps` and `time.perf_counter`." \|
	\| Async I/O \| "Fetch data from 3 URLs concurrently using `aiohttp` and `asyncio.gather`." \|
	\| Data Science \| "Optimize a pandas merge for 1M+ rows using specific dtypes." \|

	## ⚙️ Technical Specifications

	\| Parameter \| Value \|
	\| :--- \| :--- \|
	\| Parameters \| 4 Billion \|
	\| Context Length \| 262,144 tokens \|
	\| Embedding Dim \| 2,560 \|
	\| Head Count \| 32 (Q), 8 (KV) \|
	\| RoPE Theta \| 5,000,000 \|

	## 📜 License

	This model is based on Qwen3, which is licensed under the Apache 2.0 License. The fine-tuned weights and GGUF conversion are provided for research and development purposes.

	---

	Built with ❤️ using Unsloth, llama.cpp, and Ollama.