Instructions to use khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF 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 khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF: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 khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF: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 khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF:Q4_K_M

Use Docker

docker model run hf.co/khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-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": "khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF:Q4_K_M

Ollama
How to use khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF with Ollama:
```
ollama run hf.co/khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF:Q4_K_M
```

Unsloth Studio

How to use khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-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 khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-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 khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF to start chatting

Docker Model Runner
How to use khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF with Docker Model Runner:
```
docker model run hf.co/khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF:Q4_K_M
```

Lemonade

How to use khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

👑 Qwen2.5-Coder-7B-VN-Master-Polymath (FINAL GGUF Edition)

Siêu mô hình AI tiếng Việt "Văn Võ Song Toàn" toàn năng: Kỹ sư Lập trình Senior, ReAct Agent, Bách Khoa Toàn Thư & Thi Sĩ.

📌 1. TỔNG QUAN SIÊU PHẨM MASTER POLYMATH

Qwen2.5-Coder-7B-VN-Master-Polymath là phiên bản hoàn thiện cao nhất (Final Release), kết tinh từ toàn bộ lộ trình huấn luyện 5 giai đoạn với hơn 150.000+ mẫu dữ liệu tuyển chọn:

⚔️ Về Võ (Kỹ thuật chuyên sâu): Nắm vững C++20/23, Concurrency, ASan, Python Backend, Web SPA (React/Vite/Tailwind), vá lỗi bảo mật chuẩn quốc tế CWE và vận hành trơn tru quy trình ReAct Coding Agent (<thought> + <tool_call>).
📜 Về Văn (Tri thức & Nghệ thuật): Am hiểu sâu sắc lịch sử 63 tỉnh thành, địa lý, pháp luật, khoa học tự nhiên và có khả năng xuất khẩu thành thơ Lục Bát chuẩn luật Bằng - Trắc, viết tản văn truyền cảm hứng chuẩn phong cách Gemini Style.

📦 2. DANH SÁCH 5 BẢN NÉN GGUF ĐA MỨC NĂNG LƯỢNG

Repo này cung cấp đầy đủ 5 phiên bản GGUF để phù hợp với mọi cấu hình máy tính:

Tên File GGUF	Mức nén (Quant)	Dung lượng	Cấu hình máy khuyến nghị
`qwen2.5-coder-7b-instruct.Q4_K_M.gguf`	4-bit Medium	~4.68 GB	🌟 Bản Quốc Dân: Máy 8GB VRAM (RTX 5060/3060) hoặc 16GB RAM.
`qwen2.5-coder-7b-instruct.Q5_K_M.gguf`	5-bit Medium	~5.30 GB	💎 Chất Lượng Cao: Câu từ mượt mà, giữ 99.5% độ chính xác.
`qwen2.5-coder-7b-instruct.Q8_0.gguf`	8-bit	~7.80 GB	👑 Chính Xác Tuyệt Đối: Dành cho máy tính mạnh hoặc Server.
`qwen2.5-coder-7b-instruct.Q6_K.gguf`	6-bit	~6.20 GB	⚡ Bản Sắc Nét: Dành cho card 12GB – 16GB VRAM.
`qwen2.5-coder-7b-instruct.Q3_K_M.gguf`	3-bit Medium	~3.60 GB	🪶 Siêu Nhẹ: Máy RAM yếu (8GB), Raspberry Pi.

💻 3. HƯỚNG DẪN SỬ DỤNG VỚI OLLAMA

# 1. Tạo model từ Modelfile
ollama create qwen-polymath -f Modelfile

# 2. Chạy thử nghiệm ngay lập tức
ollama run qwen-polymath

📜 4. BẢN QUYỀN & TÁC GIẢ Phát triển và huấn luyện bởi: @khoin68. Công nghệ tối ưu: Unsloth AI & Alibaba Cloud Qwen Team.

Downloads last month: 121

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for khoin68/Qwen2.5-Coder-7B-Vietnamese-Agent-FINAL-GGUF

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Finetuned

Qwen/Qwen2.5-Coder-7B-Instruct

Quantized

(219)

this model