Instructions to use sargurun16/VCoder-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sargurun16/VCoder-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="sargurun16/VCoder-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("sargurun16/VCoder-GGUF", dtype="auto")

llama-cpp-python

How to use sargurun16/VCoder-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="sargurun16/VCoder-GGUF",
	filename="qwen2.5-coder-3b-instruct.Q8_0.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 sargurun16/VCoder-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sargurun16/VCoder-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf sargurun16/VCoder-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sargurun16/VCoder-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf sargurun16/VCoder-GGUF:Q8_0

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 sargurun16/VCoder-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf sargurun16/VCoder-GGUF:Q8_0

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 sargurun16/VCoder-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sargurun16/VCoder-GGUF:Q8_0

Use Docker

docker model run hf.co/sargurun16/VCoder-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use sargurun16/VCoder-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sargurun16/VCoder-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sargurun16/VCoder-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sargurun16/VCoder-GGUF:Q8_0

SGLang

How to use sargurun16/VCoder-GGUF 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 "sargurun16/VCoder-GGUF" \
    --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": "sargurun16/VCoder-GGUF",
		"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 "sargurun16/VCoder-GGUF" \
        --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": "sargurun16/VCoder-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use sargurun16/VCoder-GGUF with Ollama:
```
ollama run hf.co/sargurun16/VCoder-GGUF:Q8_0
```

Unsloth Studio

How to use sargurun16/VCoder-GGUF 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 sargurun16/VCoder-GGUF 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 sargurun16/VCoder-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sargurun16/VCoder-GGUF to start chatting

How to use sargurun16/VCoder-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf sargurun16/VCoder-GGUF:Q8_0

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": "sargurun16/VCoder-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use sargurun16/VCoder-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf sargurun16/VCoder-GGUF:Q8_0

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 sargurun16/VCoder-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use sargurun16/VCoder-GGUF with Docker Model Runner:
```
docker model run hf.co/sargurun16/VCoder-GGUF:Q8_0
```

Lemonade

How to use sargurun16/VCoder-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sargurun16/VCoder-GGUF:Q8_0

Run and chat with the model

lemonade run user.VCoder-GGUF-Q8_0

List all available models

lemonade list

VCoder-GGUF / README.md

sargurun16

Update README.md

2caecbd verified 3 days ago

preview code

Raw

History Blame Contribute Delete

3.18 kB

	---
	license: apache-2.0
	base_model: Qwen/Qwen2.5-Coder-3B-Instruct
	pipeline_tag: text-generation
	library_name: transformers
	tags:
	- code-generation
	- python
	- qwen
	- unsloth
	- transformers
	- coding-assistant
	language:
	- en
	---

	# VCoder

	VCoder is a Python-focused coding assistant fine-tuned from Qwen2.5-Coder-3B-Instruct using LoRA and Unsloth.

	The model was trained on 15,000 Python instruction-response examples from the Python Code Instructions 15K dataset and optimized for Python code generation, problem solving, debugging, and algorithm implementation.

	## Model Details

	\| Attribute \| Value \|
	\|------------\|---------\|
	\| Base Model \| Qwen2.5-Coder-3B-Instruct \|
	\| Fine-Tuning Method \| LoRA \|
	\| Framework \| Unsloth \|
	\| Dataset \| Python Code Instructions 15K \|
	\| Training Samples \| 15,000 \|
	\| GPU \| NVIDIA Tesla T4 \|
	\| Quantized Format \| GGUF Q8_0 \|
	\| Primary Language \| Python \|

	---

	## Training Pipeline

	Training was performed incrementally:

	\| Stage \| Samples \|
	\|---------\|---------\|
	\| Stage 1 \| 0 - 5,000 \|
	\| Stage 2 \| 5,000 - 10,000 \|
	\| Stage 3 \| 10,000 - 15,000 \|

	The model was trained using parameter-efficient fine-tuning (LoRA), allowing adaptation of the base model while keeping computational requirements low.

	---

	## Benchmark Results

	![Output](https://cdn-uploads.huggingface.co/production/uploads/6a297050d3837ea7b12cc42f/BV8FY6fJN7KQ43jcpC6hr.png)

	### HumanEval Comparison

	The model was evaluated against the original Qwen2.5-Coder-3B-Instruct on HumanEval coding tasks.

	\| Model \| Pass@1 \|
	\|---------\|---------\|
	\| Base Qwen2.5-Coder-3B \| 61.0% \|
	\| VCoder \| 68.0% \|

	### Improvement

	```text
	+7.0% Pass@1 improvement
	```

	This demonstrates that the fine-tuned model performs better on Python coding tasks than the original base model.

	---

	## Example Usage

	### Python

	```python
	prompt = """
	### Instruction:
	Write a Python function to reverse a string.

	### Input:

	### Response:
	"""
	```

	### Example Output

	```python
	def reverse_string(text):
	return text[::-1]
	```

	---

	## Supported Tasks

	- Python Code Generation
	- Algorithm Design
	- Data Structures
	- Debugging
	- Code Refactoring
	- Coding Interview Questions
	- Competitive Programming
	- Function Completion

	---

	## GGUF Usage

	Compatible with:

	- Ollama
	- LM Studio
	- llama.cpp

	---

	## Training Dataset

	Dataset used:

	Python Code Instructions 15K

	The dataset contains instruction-response pairs focused on Python programming tasks including:

	- Function generation
	- Data manipulation
	- Algorithms
	- Debugging
	- Problem solving

	---

	## Limitations

	- Primarily optimized for Python.
	- Benchmark performed on a subset of HumanEval tasks.
	- May generate incorrect code for highly specialized domains.
	- Should not be used as the sole source of production-critical code.

	---

	## Acknowledgements

	- Qwen Team for Qwen2.5-Coder
	- Unsloth for efficient fine-tuning
	- Hugging Face
	- OpenAI HumanEval Benchmark

	---

	## Citation

	```bibtex
	@misc{vcoder2026,
	title={VCoder: Python Code Generation Model},
	author={Varunesh V, Prawin R K, Sarguru N},
	year={2026},
	base_model={Qwen2.5-Coder-3B-Instruct}
	}
	```
	Github : https://github.com/sargurun16
	Mail : sarguru1609@gmail.com